___ ____ ____ ____ ____(R) /__ / ____/ / ____/ ___/ / /___/ / /___/ Statistics/Data Analysis 1 . set linesize 80 2 . set seed 1010101 3 . set matsize 11000 4 . 5 . 6 . ******* 7 . 8 . * This script requires pre-installation of spost2 by J. Scott Long for fits > tat command 9 . * It also requires installation of title2.ado, title3.ado 10 . * 11 . * for the fitstat command to function 12 . ****** 13 . di "$User" Robert Alan Yaffee 14 . * 16 June 2012 15 . 16 . *------- Primary objective: Hypothesis 1 tests for Part 2 of Nottingham heal > th profile 17 . 18 . ********* Hypothesis tests Robert A. Yaffee 10 June 2012 main effect > s and moderator identification approach 19 . * protocol is to test Health profile subscales against potential confounders > including socio-demog vars, 20 . * major neg life events, stresses and hassles, social supports, perceived > health, distance, 21 . * threat and dose to see whether there is a dose-psych response 22 . 23 . * We construct a full model, trimmed model (at .1 level), and then test inte > ractions with dose if there is a 24 . * significant main effect dose psych response 25 . 26 . * Trimming is performed with backward elimination to the .1 level 27 . * 28 . * This approach identifies the moderating variables for our path analysis. > We analyze our 29 . * final models for congruence with regression assumptions with the rdiag > program for a validity assessment 30 . 31 . *---------------------------------------------------------------------------- > ------------------------------ 32 . 33 . *----------- Organization of the program ------------------------------------ > -------------------------------------- 34 . * main effects regresssions are run for all part 1 health profile subscales > except that of emotional 35 . * reaction for both males and females separately 36 . * these models are trimmed with backward elimination to determine whether th > e main effect of avg cumulative dose 37 . * is significant for that wave 38 . * If the main effect of average cumulative dose for that wave is not statis > tically significant with the 39 . * covariates controlled we do not go further along that path 40 . * If the main effect of average cumulative dose for that wave is statistica > lly significant, we trim the 41 . * model to a p = .1 42 . * If average cumulative dose is not significant, we stop 43 . * If average cumulative dose is significant we perform a hierarchical regre > ssion with interactions between dose 44 . * and other significant main effects 45 . * We proceed to test for mediating effects of those other significant expla > natory variable 46 . * We evaluate the model for statistical conguency. 47 . * This concludes the test of part 1 of H1 48 . ***-------------------------------------------------------------------------- > ---------------------------------------- 49 . 50 . * Part 2 Nottingham subscales 51 . * 1: hp2work 52 . * 2: hp2hmcare 53 . * 3: hp2probsoc 54 . * 4: hp2pbfhm 55 . * 5: hp2sexlife 56 . * 6: hp2inthob 57 . * 7: hp2vactn 58 . 59 . 60 . local dvwhole HP2work-HP2vacatn 61 . local dv2 HP2work HP2hmcare HP2probsoc HP2pbfhm HP2sxlife HP2inthob HP2vacatn 62 . 63 . 64 . 65 . di "$User" Robert Alan Yaffee 66 . 67 . title "Testing part 2 of hypothesis 1 for wave three" ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Testing part 2 of hypothesis 1 for wave three ***** ***** ***** ***** ***** ***** 1 Jul 2012 20:32:48 ***** ******************************************************************************* ******************************************************************************* 68 . 69 . cd /Users/robertyaffee/Documents/data/research/chwk/phase3/Htests/H1tests/h1p > t2 /Users/robertyaffee/Documents/data/research/chwk/phase3/Htests/H1tests/h1pt2 70 . use chwide1jul2012, clear (Zero for missing on all icdx) 71 . cd /Users/robertyaffee/Documents/data/research/chwk/phase3/Htests/H1tests/h1p > t2 /Users/robertyaffee/Documents/data/research/chwk/phase3/Htests/H1tests/h1pt2 72 . 73 . 74 . di "{hline}" ------------------------------------------------------------------------------- 75 . di "{hline}" ------------------------------------------------------------------------------- 76 . 77 . title "Chunk 1 Hyp 1:radiation dose and Nottingham Health profile subscales" ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** *****Chunk 1 Hyp 1:radiation dose and Nottingham Health profile subscales ***** ***** ***** ***** ***** ***** 1 Jul 2012 20:32:48 ***** ******************************************************************************* ******************************************************************************* 78 . 79 . 80 . // there is substantial intercorrelation among the items warranting a 81 . // multivariate regression model 82 . cap dummies educ 83 . cap order educ1-educ8, after(educ) 84 . 85 . * These variables are substantially correlated 86 . pwcorr HP2work HP2hmcare HP2probsoc HP2pbfhm HP2sxlife HP2inthob HP2vacatn, / > // > obs sig | HP2work HP2hmc~e HP2pro~c HP2pbfhm HP2sxl~e HP2int~b HP2vac~n -------------+--------------------------------------------------------------- HP2work | 1.0000 | | 703 | HP2hmcare | 0.4878 1.0000 | 0.0000 | 703 703 | HP2probsoc | 0.4587 0.5420 1.0000 | 0.0000 0.0000 | 703 703 703 | HP2pbfhm | 0.2832 0.4150 0.4745 1.0000 | 0.0000 0.0000 0.0000 | 703 703 703 703 | HP2sxlife | 0.4968 0.4576 0.5589 0.4192 1.0000 | 0.0000 0.0000 0.0000 0.0000 | 703 703 703 703 703 | HP2inthob | 0.3787 0.4757 0.5956 0.5089 0.5401 1.0000 | 0.0000 0.0000 0.0000 0.0000 0.0000 | 703 703 703 703 703 703 | HP2vacatn | 0.4166 0.4757 0.5956 0.4416 0.5211 0.6840 1.0000 | 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 | 703 703 703 703 703 703 703 | 87 . 88 . cap gen havmilsq = havmil^2 89 . 90 . cap rename Havmil havmil 91 . // controlling for potential confounders 92 . // socio-demographics age gender educ income occp marstat children inc 93 . // distance from accident side 94 . // perceived Chornobyl related health threat to oneself 95 . 96 . local w1bf bf1 bf4 bf9 bf10 bf11 bf4m bf15m bf20 bf22 bf30 bf40 97 . local w3bf bf1 bf4 bf6 bf7 bf14 bf15 bf40 98 . local w3bf bf1 bf4 bf2 bf4m bf5m bf7m bf8 bf15m bf17 bf20 bf22 bf29 bf30 bf40 99 . 100 . *---------------------------------------------------------------------------- > --- 101 . * Hypothesis 1 Part 2 wave 3 tests male and female 102 . * endogneous Nottingham pt 2 subscales: HP2work HP2hmcare HP2probsoc HP2pbfhm > /// > * HP2sxlife HP2inthob HP2vacatn 103 . * structure of models 104 . * 1. general models on all Pt 2 subscales with all potential confounders 105 . * 2. trimmed models on all Pt 2 subscales with from all potential confound > ers 106 . * 3. from trimmed models examination of possible moderator variables 107 . * 4. from trimmed models examination of possible mediator variables 108 . * 5. Summary analysis and model evaluation of final models only 109 . * program is divided into 8 chunks one a general model and 1 for each 110 . * endogenous variable 111 . *---------------------------------------------------------------------------- > --- 112 . * Chunk 1 General models for all part 2 of Nottingham Health Profile 113 . est clear 114 . set linesize 80 115 . title "Zero order effects test for wave 3" ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Zero order effects test for wave 3 ***** ***** ***** ***** ***** ***** 1 Jul 2012 20:32:48 ***** ******************************************************************************* ******************************************************************************* 116 . 117 . 118 . 119 . foreach var in hp2work hp2hmcare hp2prbsoc HP2pbfhm HP2sxlife /// > HP2inthob HP2vacatn { 2. forvalues k=2/2 { 3. set more off 4. logit `var' avgcumdosew3 if gender==`k', nolog 5. eststo `var' 6. } 7. } Logistic regression Number of obs = 363 LR chi2(1) = 5.91 Prob > chi2 = 0.0150 Log likelihood = -203.60666 Pseudo R2 = 0.0143 ------------------------------------------------------------------------------ hp2work | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | .1515886 .0639414 2.37 0.018 .0262658 .2769114 _cons | -1.258846 .1466856 -8.58 0.000 -1.546344 -.9713471 ------------------------------------------------------------------------------ Logistic regression Number of obs = 363 LR chi2(1) = 0.04 Prob > chi2 = 0.8368 Log likelihood = -233.70738 Pseudo R2 = 0.0001 ------------------------------------------------------------------------------ hp2hmcare | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | -.0131553 .0643514 -0.20 0.838 -.1392816 .1129711 _cons | -.6282335 .1343551 -4.68 0.000 -.8915646 -.3649023 ------------------------------------------------------------------------------ Logistic regression Number of obs = 363 LR chi2(1) = 25.59 Prob > chi2 = 0.0000 Log likelihood = -170.77453 Pseudo R2 = 0.0697 ------------------------------------------------------------------------------ hp2prbsoc | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | .3818633 .1004161 3.80 0.000 .1850514 .5786752 _cons | -1.855996 .1805781 -10.28 0.000 -2.209923 -1.50207 ------------------------------------------------------------------------------ Logistic regression Number of obs = 363 LR chi2(1) = 1.39 Prob > chi2 = 0.2389 Log likelihood = -139.20329 Pseudo R2 = 0.0050 ------------------------------------------------------------------------------ HP2pbfhm | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | .0875242 .0693786 1.26 0.207 -.0484553 .2235037 _cons | -2.020197 .1850603 -10.92 0.000 -2.382909 -1.657486 ------------------------------------------------------------------------------ Logistic regression Number of obs = 363 LR chi2(1) = 13.23 Prob > chi2 = 0.0003 Log likelihood = -201.00372 Pseudo R2 = 0.0319 ------------------------------------------------------------------------------ HP2sxlife | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | .2420078 .0764553 3.17 0.002 .0921582 .3918573 _cons | -1.357074 .1533357 -8.85 0.000 -1.657606 -1.056541 ------------------------------------------------------------------------------ Logistic regression Number of obs = 363 LR chi2(1) = 5.02 Prob > chi2 = 0.0250 Log likelihood = -169.60139 Pseudo R2 = 0.0146 ------------------------------------------------------------------------------ HP2inthob | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | .1444902 .0628294 2.30 0.021 .0213469 .2676336 _cons | -1.695781 .1633385 -10.38 0.000 -2.015919 -1.375643 ------------------------------------------------------------------------------ Logistic regression Number of obs = 363 LR chi2(1) = 4.68 Prob > chi2 = 0.0305 Log likelihood = -165.17453 Pseudo R2 = 0.0140 ------------------------------------------------------------------------------ HP2vacatn | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | .1408134 .0629055 2.24 0.025 .017521 .2641059 _cons | -1.748135 .1659602 -10.53 0.000 -2.073411 -1.422859 ------------------------------------------------------------------------------ 120 . 121 . title "Summary of zero-order tests for females in wave three" ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Summary of zero-order tests for females in wave three ***** ***** ***** ***** ***** ***** 1 Jul 2012 20:32:58 ***** ******************************************************************************* ******************************************************************************* 122 . 123 . 124 . estout hp2work hp2hmcare hp2prbsoc HP2pbfhm, cells(b(star fmt(%9.3f)) se(pa > r) t p) /// > stats(r2_p bic N, fmt(%9.3f %9.0g) labels(Psuedo R^2)) /// > legend collabels(none) varlabels(_cons Constant) /// > mlabels( work homecare socialprbs famprobs) /// > title("Zero-order regression coefficients" /// > "of reconstructed dose on Nottingham Part 2") Zero-order regression coefficients of reconstructed dose on Nottingham Part 2 ---------------------------------------------------------------------------- work homecare socialprbs famprobs ---------------------------------------------------------------------------- main avgcumdosew3 0.152* -0.013 0.382*** 0.088 (0.064) (0.064) (0.100) (0.069) 2.371 -0.204 3.803 1.262 0.018 0.838 0.000 0.207 Constant -1.259*** -0.628*** -1.856*** -2.020*** (0.147) (0.134) (0.181) (0.185) -8.582 -4.676 -10.278 -10.916 0.000 0.000 0.000 0.000 ---------------------------------------------------------------------------- Psuedo 0.014 0.000 0.070 0.005 R^2 419.0021 479.2036 353.3379 290.1954 N 363 363 363 363 ---------------------------------------------------------------------------- * p<0.05, ** p<0.01, *** p<0.001 125 . estout HP2sxlife HP2inthob HP2vacatn, cells(b(star fmt(%9.3f)) se(par) t p) > /// > stats(r2_p bic N, fmt(%9.3f %9.0g) labels(Pseudo R^2)) /// > legend collabels(none) varlabels(_cons Constant) /// > mlabels(sexlife intshobbies vacatnPlans) /// > title("Zero-order regression coefficients" /// > "of reconstructed dose on Nottingham Part 2") Zero-order regression coefficients of reconstructed dose on Nottingham Part 2 ------------------------------------------------------------ sexlife intshobbies vacatnPlans ------------------------------------------------------------ main avgcumdosew3 0.242** 0.144* 0.141* (0.076) (0.063) (0.063) 3.165 2.300 2.238 0.002 0.021 0.025 Constant -1.357*** -1.696*** -1.748*** (0.153) (0.163) (0.166) -8.850 -10.382 -10.533 0.000 0.000 0.000 ------------------------------------------------------------ Pseudo 0.032 0.015 0.014 R^2 413.7963 350.9916 342.1379 N 363 363 363 ------------------------------------------------------------ * p<0.05, ** p<0.01, *** p<0.001 126 . 127 . title "Trimmed model summary for females in wave three" ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Trimmed model summary for females in wave three ***** ***** ***** ***** ***** ***** 1 Jul 2012 20:32:59 ***** ******************************************************************************* ******************************************************************************* 128 . 129 . forvalues j=3/3 { 2. des age avgcumdosew`j' 3. logistic HP2work age /// > avgcumdosew3 if gender==2, coef nolog 4. eststo work 5. } storage display value variable name type format label variable label ------------------------------------------------------------------------------- age double %8.0g * Respondent's age avgcumdosew3 double %8.0g Avg Mean dose of CS137 ending 12/31/2009 Logistic regression Number of obs = 363 LR chi2(2) = 44.24 Prob > chi2 = 0.0000 Log likelihood = -184.44118 Pseudo R2 = 0.1071 ------------------------------------------------------------------------------ HP2work | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0677348 .01171 5.78 0.000 .0447836 .0906861 avgcumdosew3 | .102922 .0642392 1.60 0.109 -.0229846 .2288285 _cons | -4.750307 .6479129 -7.33 0.000 -6.020193 -3.480421 ------------------------------------------------------------------------------ 130 . 131 . title "Trimmed female homecare in wave three" ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Trimmed female homecare in wave three ***** ***** ***** ***** ***** ***** 1 Jul 2012 20:33:00 ***** ******************************************************************************* ******************************************************************************* 132 . * Dose work relationship for females in wave 3 washes out also 133 . set more off 134 . forvalues j=3/3 { 2. local w3bf bf1 bf4 bf2 bf4m bf5m bf7m bf8 bf15m bf17 bf20 bf22 bf29 bf30 b > f40 3. di _skip(4) 4. di as input "For females hp2hmcare on wave 1 with dose ns" 5. des age avgcumdosew`j' `w3bf' 6. logistic HP2work age radhlw3 /// > avgcumdosew3 shhlw`j' if gender==2, coef nolog 7. eststo homecare 8. 135 . } For females hp2hmcare on wave 1 with dose ns storage display value variable name type format label variable label ------------------------------------------------------------------------------- age double %8.0g * Respondent's age avgcumdosew3 double %8.0g Avg Mean dose of CS137 ending 12/31/2009 bf1 float %9.0g bf1 = max(0, kzchorn - 40) bf4 float %9.0g bf4 = max(0, 24 - BSIsoma) bf2 float %9.0g bf2 = max(0, efradw3 - 1.61252E-006) * bf1 bf4m float %9.0g bf4m = max(0, 32 - BSIsoma) bf5m float %9.0g bf5m = max(0, ecprw3 - 75) * bf4m bf7m float %9.0g bf7m = max(0, radtlw3 - 2.12558E-007) * bf4m bf8 float %9.0g bf8 = max(0, radtlw3 - 40) * bf5m bf15m float %9.0g bf15m= max(0, 1 - icdxcnt) * bf2 bf17 float %9.0g bf17 = max(0, 20 - ecprw3) * bf15m bf20 float %9.0g bf20 = max(0, kzchorn - 2.53946E-006) bf22 float %9.0g bf22 = max(0, icdxcnt - 1.01635E-007) * bf7m bf29 float %9.0g bf29 = max(0, 18 - CSsocspt) * bf8 bf30 float %9.0g bf30 = max(0, neiw1 - 85) * bf20 bf40 float %9.0g bf40 = max(0, icdxcnt - 1.01635E-007) Logistic regression Number of obs = 363 LR chi2(4) = 54.20 Prob > chi2 = 0.0000 Log likelihood = -179.46218 Pseudo R2 = 0.1312 ------------------------------------------------------------------------------ HP2work | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0604261 .0121821 4.96 0.000 .0365495 .0843027 radhlw3 | .0091245 .0041171 2.22 0.027 .0010551 .0171938 avgcumdosew3 | .0744838 .0646958 1.15 0.250 -.0523177 .2012853 shhlw3 | .0068705 .0039339 1.75 0.081 -.0008399 .0145808 _cons | -5.221192 .6904908 -7.56 0.000 -6.574529 -3.867855 ------------------------------------------------------------------------------ 136 . 137 . title "Trimmed female dose-social problems in wave three model B: Dose is sig > nificant" ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** *****Trimmed female dose-social problems in wave three model B: Dose is signifi > cant***** ***** ***** ***** ***** ***** 1 Jul 2012 20:33:01 ***** ******************************************************************************* ******************************************************************************* 138 . set more off 139 . logit HP2probsoc age radhlw3 illw3 //// > shrelaw3 avgcumdosew3 if gender==2 Iteration 0: log likelihood = -183.5701 Iteration 1: log likelihood = -125.28517 Iteration 2: log likelihood = -117.19625 Iteration 3: log likelihood = -116.97888 Iteration 4: log likelihood = -116.97825 Iteration 5: log likelihood = -116.97825 Logistic regression Number of obs = 363 LR chi2(5) = 133.18 Prob > chi2 = 0.0000 Log likelihood = -116.97825 Pseudo R2 = 0.3628 ------------------------------------------------------------------------------ HP2probsoc | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .12216 .0187462 6.52 0.000 .0854181 .1589019 radhlw3 | .0215768 .0055327 3.90 0.000 .0107328 .0324208 illw3 | .2697796 .1359094 1.98 0.047 .0034019 .5361572 shrelaw3 | -.0157291 .0056433 -2.79 0.005 -.0267898 -.0046685 avgcumdosew3 | .3226135 .1095794 2.94 0.003 .1078418 .5373853 _cons | -9.764122 1.1857 -8.23 0.000 -12.08805 -7.440193 ------------------------------------------------------------------------------ 140 . eststo probsoc 141 . 142 . 143 . title "More partly female Trimmed wave 3" "Dose => Problems with Family at h > ome models" ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** More partly female Trimmed wave 3 ***** ***** Dose => Problems with Family at home models ***** ***** ***** ***** ***** ***** 1 Jul 2012 20:33:03 ***** ******************************************************************************* ******************************************************************************* 144 . local w3bf bf1 bf4 bf2 bf8 bf15m bf17 bf20 bf22 bf29 bf30 bf40 145 . logit HP2pbfhm age bf4 bf40 if gender==2, iterate(50) Iteration 0: log likelihood = -139.89675 Iteration 1: log likelihood = -112.36921 Iteration 2: log likelihood = -106.24923 Iteration 3: log likelihood = -106.12137 Iteration 4: log likelihood = -106.12091 Iteration 5: log likelihood = -106.12091 Logistic regression Number of obs = 363 LR chi2(3) = 67.55 Prob > chi2 = 0.0000 Log likelihood = -106.12091 Pseudo R2 = 0.2414 ------------------------------------------------------------------------------ HP2pbfhm | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0636233 .017269 3.68 0.000 .0297767 .0974699 bf4 | -.2029758 .0392585 -5.17 0.000 -.2799211 -.1260305 bf40 | -.1942568 .091411 -2.13 0.034 -.373419 -.0150946 _cons | -3.085643 1.113267 -2.77 0.006 -5.267607 -.9036792 ------------------------------------------------------------------------------ 146 . eststo familyprbs 147 . 148 . title "trimmed HP2sexlife main effects models" "wave 3 for H1 part 2 with dos > e ns" ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** trimmed HP2sexlife main effects models ***** ***** wave 3 for H1 part 2 with dose ns ***** ***** ***** ***** ***** ***** 1 Jul 2012 20:33:04 ***** ******************************************************************************* ******************************************************************************* 149 . logit HP2sxlife age marrw31-marrw36 radhlw3 bf4 bf4m /// > shfamw3 shrelaw3 avgcumdosew3 if gender==2 note: marrw36 omitted because of collinearity Iteration 0: log likelihood = -207.62116 Iteration 1: log likelihood = -144.17685 Iteration 2: log likelihood = -138.48259 Iteration 3: log likelihood = -138.36775 Iteration 4: log likelihood = -138.36738 Iteration 5: log likelihood = -138.36738 Logistic regression Number of obs = 363 LR chi2(12) = 138.51 Prob > chi2 = 0.0000 Log likelihood = -138.36738 Pseudo R2 = 0.3336 ------------------------------------------------------------------------------ HP2sxlife | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0754579 .0170423 4.43 0.000 .0420555 .1088603 marrw31 | -.9421212 .8010808 -1.18 0.240 -2.512211 .6279684 marrw32 | -.440823 1.344699 -0.33 0.743 -3.076384 2.194738 marrw33 | -.9501207 .4286832 -2.22 0.027 -1.790324 -.109917 marrw34 | -.9642797 1.745537 -0.55 0.581 -4.38547 2.45691 marrw35 | -.8586239 .6388872 -1.34 0.179 -2.11082 .393572 marrw36 | 0 (omitted) radhlw3 | .0100484 .0049263 2.04 0.041 .000393 .0197038 bf4 | -.5151847 .1744193 -2.95 0.003 -.8570402 -.1733292 bf4m | .3491023 .1586783 2.20 0.028 .0380985 .6601061 shfamw3 | .0106246 .0054177 1.96 0.050 6.14e-06 .0212431 shrelaw3 | -.0125055 .00593 -2.11 0.035 -.024128 -.0008829 avgcumdosew3 | .1255823 .0854354 1.47 0.142 -.0418679 .2930326 _cons | -6.549884 1.704204 -3.84 0.000 -9.890063 -3.209705 ------------------------------------------------------------------------------ 150 . eststo sexlife 151 . 152 . 153 . 154 . set more off 155 . logistic HP2inthob age /// > radhlw3 avgcumdosew3 /// > bf4 /// > if gender==2, coef nolog difficult iterate(50) Logistic regression Number of obs = 363 LR chi2(4) = 85.17 Prob > chi2 = 0.0000 Log likelihood = -129.52718 Pseudo R2 = 0.2474 ------------------------------------------------------------------------------ HP2inthob | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0747817 .0159584 4.69 0.000 .0435038 .1060596 radhlw3 | .0177314 .0055334 3.20 0.001 .0068862 .0285766 avgcumdosew3 | .0423064 .0679809 0.62 0.534 -.0909337 .1755466 bf4 | -.092667 .0312315 -2.97 0.003 -.1538797 -.0314543 _cons | -6.042759 1.092151 -5.53 0.000 -8.183336 -3.902181 ------------------------------------------------------------------------------ 156 . eststo intshobbies 157 . 158 . logistic hp2vacatn age radhlw3 avgcumdosew3 /// > deaw3 suchrw3 /// > if gender==2, coef nolog difficult iterate(50) Logistic regression Number of obs = 363 LR chi2(5) = 69.60 Prob > chi2 = 0.0000 Log likelihood = -132.71672 Pseudo R2 = 0.2077 ------------------------------------------------------------------------------ hp2vacatn | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0916152 .0157813 5.81 0.000 .0606844 .1225459 radhlw3 | .0117344 .0050394 2.33 0.020 .0018573 .0216115 avgcumdosew3 | .0985606 .0692713 1.42 0.155 -.0372087 .2343299 deaw3 | .3433813 .158229 2.17 0.030 .0332581 .6535045 suchrw3 | -.0061918 .0037117 -1.67 0.095 -.0134666 .0010831 _cons | -7.50211 .9350027 -8.02 0.000 -9.334682 -5.669539 ------------------------------------------------------------------------------ 159 . eststo vacations 160 . 161 . 162 . title "Summary of Female Trimmed Main effect models for wave three" ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Summary of Female Trimmed Main effect models for wave three ***** ***** ***** ***** ***** ***** 1 Jul 2012 20:33:08 ***** ******************************************************************************* ******************************************************************************* 163 . 164 . 165 . 166 . set more off 167 . estout work homecare probsoc familyprbs, cells(b(star fmt(%9.3f)) se(par) t > p) /// > stats(r2_p bic N, fmt(%9.3f %9.0g) labels(Psuedo R^2)) /// > legend collabels(none) varlabels(_cons Constant) /// > mlabels( work homecare socialprbs famprobs) /// > title("Trimmed main effect models" /// > "of reconstructed dose on Nottingham Part 2") Trimmed main effect models of reconstructed dose on Nottingham Part 2 ---------------------------------------------------------------------------- work homecare socialprbs famprobs ---------------------------------------------------------------------------- main age 0.068*** 0.060*** 0.122*** 0.064*** (0.012) (0.012) (0.019) (0.017) 5.784 4.960 6.517 3.684 0.000 0.000 0.000 0.000 avgcumdosew3 0.103 0.074 0.323** (0.064) (0.065) (0.110) 1.602 1.151 2.944 0.109 0.250 0.003 radhlw3 0.009* 0.022*** (0.004) (0.006) 2.216 3.900 0.027 0.000 shhlw3 0.007 (0.004) 1.746 0.081 illw3 0.270* (0.136) 1.985 0.047 shrelaw3 -0.016** (0.006) -2.787 0.005 bf4 -0.203*** (0.039) -5.170 0.000 bf40 -0.194* (0.091) -2.125 0.034 Constant -4.750*** -5.221*** -9.764*** -3.086** (0.648) (0.690) (1.186) (1.113) -7.332 -7.562 -8.235 -2.772 0.000 0.000 0.000 0.006 ---------------------------------------------------------------------------- Psuedo 0.107 0.131 0.363 0.241 R^2 386.5656 388.3964 269.3229 235.8194 N 363 363 363 363 ---------------------------------------------------------------------------- * p<0.05, ** p<0.01, *** p<0.001 168 . estout sexlife intshobbies vacations, cells(b(star fmt(%9.3f)) se(par) t p) > /// > stats(r2_p bic N, fmt(%9.3f %9.0g) labels(Pseudo R^2)) /// > legend collabels(none) varlabels(_cons Constant) /// > mlabels(sexlife intshobbies vacatnPlans) /// > title("Trimmed main effect models" /// > "of reconstructed dose on Nottingham Part 2") Trimmed main effect models of reconstructed dose on Nottingham Part 2 ------------------------------------------------------------ sexlife intshobbies vacatnPlans ------------------------------------------------------------ main age 0.075*** 0.075*** 0.092*** (0.017) (0.016) (0.016) 4.428 4.686 5.805 0.000 0.000 0.000 marrw31 -0.942 (0.801) -1.176 0.240 marrw32 -0.441 (1.345) -0.328 0.743 marrw33 -0.950* (0.429) -2.216 0.027 marrw34 -0.964 (1.746) -0.552 0.581 marrw35 -0.859 (0.639) -1.344 0.179 o.marrw36 0.000 (.) . . radhlw3 0.010* 0.018** 0.012* (0.005) (0.006) (0.005) 2.040 3.204 2.329 0.041 0.001 0.020 bf4 -0.515** -0.093** (0.174) (0.031) -2.954 -2.967 0.003 0.003 bf4m 0.349* (0.159) 2.200 0.028 shfamw3 0.011* (0.005) 1.961 0.050 shrelaw3 -0.013* (0.006) -2.109 0.035 avgcumdosew3 0.126 0.042 0.099 (0.085) (0.068) (0.069) 1.470 0.622 1.423 0.142 0.534 0.155 deaw3 0.343* (0.158) 2.170 0.030 suchrw3 -0.006 (0.004) -1.668 0.095 Constant -6.550*** -6.043*** -7.502*** (1.704) (1.092) (0.935) -3.843 -5.533 -8.024 0.000 0.000 0.000 ------------------------------------------------------------ Pseudo 0.334 0.247 0.208 R^2 353.362 288.5264 300.7999 N 363 363 363 ------------------------------------------------------------ * p<0.05, ** p<0.01, *** p<0.001 169 . 170 . 171 . 172 . 173 . 174 . 175 . 176 . title " Hypothesis 1 part2 wave 3 H1: General models" ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Hypothesis 1 part2 wave 3 H1: General models ***** ***** ***** ***** ***** ***** 1 Jul 2012 20:33:09 ***** ******************************************************************************* ******************************************************************************* 177 . forvalues j=3/3 { 2. set more off 3. 178 . des age educ1-educ7 marrw`j'1-marrw`j'6 inc1w`j'-inc4w`j' /// > bf1 bf4 bf9 bf11 bf4m bf15m bf30 bf40 4. 179 . foreach var in HP2work HP2hmcare HP2probsoc HP2pbfhm HP2sxlife HP2inthob // > / > HP2vacatn { 5. forvalues k=1/2 { 6. local w3bf bf1 bf4 bf2 bf4m bf5m bf7m bf8 bf15m bf17 bf20 bf22 bf29 bf30 b > f40 7. 180 . di as input "Full main model for `var' for wave= `j' " 8. di _skip(4) 9. di as input "chunk 2 H1 test:Gender= `k' model Wave = `j' for `e(depvar > )' " 10. di _skip(4) 11. 181 . xi: logistic `var' age i.educ occ1w`j'-occ8w`j' /// > marrw`j'1- marrw`j'3 marrw`j'5-marrw`j'6 inc1w`j'-inc4w`j' // > / > radhlw`j' havmil avgcumdosew`j' `w`j'bf' /// > deaw`j' dvcew`j' sepaw`j' accdw`j' movew`j' /// > illw`j' shfamw`j' shhlw`j' shjobw`j' shrelaw`j' suprtw`j' suc > hrw`j' /// > havmilsq if gender==`k', coef nolog difficult iterate(50) 12. estat class 13. estat gof 14. fitstat 15. } 16. } 17. } storage display value variable name type format label variable label ------------------------------------------------------------------------------- age double %8.0g * Respondent's age educ1 byte %8.0g educ==1. did not graduate high school educ2 byte %8.0g educ==2. graduated high school educ3 byte %8.0g educ==3. technical degree educ4 byte %8.0g educ==4. did not finish college/bachelor's educ5 byte %8.0g educ==5. graduated college/bachelor's educ6 byte %8.0g educ==6. finished specialist/master's degree educ7 byte %8.0g educ==7. doctor of science/phd marrw31 byte %8.0g marrw3==1. single marrw32 byte %8.0g marrw3==2. cohabitating marrw33 byte %8.0g marrw3==3. married marrw34 byte %8.0g marrw3==4. separated marrw35 byte %8.0g marrw3==5. divorced marrw36 byte %8.0g marrw3==6. widowed inc1w3 double %15.0g LABJ Income is not sufficient for basic neccessities NOW inc2w3 double %15.0g LABJ Income is just sufficient for basic neccessities NOW inc3w3 double %15.0g LABJ Income is sufficient for basics plus extra purchases/savings NOW inc4w3 double %15.0g LABJ Income allows to comfortably afford luxury items NOW bf1 float %9.0g bf1 = max(0, kzchorn - 40) bf4 float %9.0g bf4 = max(0, 24 - BSIsoma) bf9 float %9.0g bf9= max(0, 30 - shhlw1) bf11 float %9.0g bf11= max(0, 20 - sufamw1) bf4m float %9.0g bf4m = max(0, 32 - BSIsoma) bf15m float %9.0g bf15m= max(0, 1 - icdxcnt) * bf2 bf30 float %9.0g bf30 = max(0, neiw1 - 85) * bf20 bf40 float %9.0g bf40 = max(0, icdxcnt - 1.01635E-007) Full main model for HP2work for wave= 3 chunk 2 H1 test:Gender= 1 model Wave = 3 for hp2vacatn i.educ _Ieduc_1-8 (naturally coded; _Ieduc_1 omitted) note: _Ieduc_7 != 0 predicts failure perfectly _Ieduc_7 dropped and 4 obs not used note: _Ieduc_8 != 0 predicts failure perfectly _Ieduc_8 dropped and 2 obs not used note: occ6w3 != 0 predicts failure perfectly occ6w3 dropped and 4 obs not used note: bf17 != 0 predicts failure perfectly bf17 dropped and 5 obs not used note: _Ieduc_6 omitted because of collinearity note: occ8w3 omitted because of collinearity note: marrw36 omitted because of collinearity Logistic regression Number of obs = 325 LR chi2(48) = 107.62 Prob > chi2 = 0.0000 Log likelihood = -115.51874 Pseudo R2 = 0.3178 ------------------------------------------------------------------------------ HP2work | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0398855 .0274181 1.45 0.146 -.0138531 .0936241 _Ieduc_2 | 1.063444 .984496 1.08 0.280 -.8661327 2.993021 _Ieduc_3 | .0594211 .4628201 0.13 0.898 -.8476896 .9665319 _Ieduc_4 | -.6292279 1.199379 -0.52 0.600 -2.979968 1.721512 _Ieduc_5 | -.0324117 .5603466 -0.06 0.954 -1.130671 1.065848 _Ieduc_6 | 0 (omitted) _Ieduc_7 | 0 (omitted) _Ieduc_8 | 0 (omitted) occ1w3 | -16.21183 2056.545 -0.01 0.994 -4046.966 4014.542 occ2w3 | -15.9512 2056.545 -0.01 0.994 -4046.705 4014.803 occ3w3 | -16.80618 2056.545 -0.01 0.993 -4047.56 4013.948 occ4w3 | -15.08231 2056.545 -0.01 0.994 -4045.836 4015.672 occ5w3 | -15.97511 2056.545 -0.01 0.994 -4046.729 4014.779 occ6w3 | 0 (omitted) occ7w3 | -15.17432 2056.545 -0.01 0.994 -4045.928 4015.58 occ8w3 | 0 (omitted) marrw31 | 1.816033 1.097265 1.66 0.098 -.3345671 3.966633 marrw32 | .0757168 1.330041 0.06 0.955 -2.531115 2.682549 marrw33 | -.7164591 1.109884 -0.65 0.519 -2.891791 1.458873 marrw35 | .9690805 1.275825 0.76 0.448 -1.53149 3.469651 marrw36 | 0 (omitted) inc1w3 | 16.44823 2056.545 0.01 0.994 -4014.306 4047.202 inc2w3 | 16.79255 2056.545 0.01 0.993 -4013.961 4047.546 inc3w3 | 16.28275 2056.545 0.01 0.994 -4014.471 4047.037 inc4w3 | 16.19339 2056.545 0.01 0.994 -4014.561 4046.948 radhlw3 | .0018951 .0075342 0.25 0.801 -.0128717 .0166619 havmil | -.0003047 .0050542 -0.06 0.952 -.0102109 .0096014 avgcumdosew3 | .0388524 .0643134 0.60 0.546 -.0871996 .1649043 bf1 | -.1090167 .0689067 -1.58 0.114 -.2440713 .026038 bf4 | -.1845645 .1878566 -0.98 0.326 -.5527567 .1836277 bf2 | .0001393 .0001535 0.91 0.364 -.0001616 .0004401 bf4m | -.0184667 .1657846 -0.11 0.911 -.3433984 .3064651 bf5m | .0009023 .0015537 0.58 0.561 -.0021429 .0039475 bf7m | .0008163 .0004923 1.66 0.097 -.0001485 .0017811 bf8 | -.0001145 .0000456 -2.51 0.012 -.000204 -.0000251 bf15m | .0001838 .0002744 0.67 0.503 -.000354 .0007216 bf17 | 0 (omitted) bf20 | .0923153 .0637829 1.45 0.148 -.0326969 .2173275 bf22 | .0000533 .0001499 0.36 0.722 -.0002405 .0003471 bf29 | .0000161 .0000149 1.08 0.282 -.0000132 .0000453 bf30 | -.0004903 .0003941 -1.24 0.214 -.0012627 .0002822 bf40 | .0752527 .2023106 0.37 0.710 -.3212688 .4717743 deaw3 | -.1202184 .2295198 -0.52 0.600 -.570069 .3296321 dvcew3 | -.0534217 1.08605 -0.05 0.961 -2.18204 2.075197 sepaw3 | -.3670246 1.185339 -0.31 0.757 -2.690246 1.956196 accdw3 | -.058659 .5773335 -0.10 0.919 -1.190212 1.072894 movew3 | -.5628223 .5250647 -1.07 0.284 -1.59193 .4662856 illw3 | .6145655 .2492311 2.47 0.014 .1260816 1.103049 shfamw3 | -.0028773 .0074782 -0.38 0.700 -.0175343 .0117797 shhlw3 | -.0003705 .0066844 -0.06 0.956 -.0134717 .0127307 shjobw3 | .0119897 .0066255 1.81 0.070 -.0009961 .0249755 shrelaw3 | -.0011615 .0067798 -0.17 0.864 -.0144496 .0121266 suprtw3 | .0138766 .0081512 1.70 0.089 -.0020993 .0298526 suchrw3 | -.0097666 .0065695 -1.49 0.137 -.0226425 .0031093 havmilsq | 7.20e-07 7.22e-06 0.10 0.921 -.0000134 .0000149 _cons | -6.713085 3.586597 -1.87 0.061 -13.74269 .3165157 ------------------------------------------------------------------------------ Note: 4 failures and 0 successes completely determined. Logistic model for HP2work -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 30 15 | 45 - | 40 240 | 280 -----------+--------------------------+----------- Total | 70 255 | 325 Classified + if predicted Pr(D) >= .5 True D defined as HP2work != 0 -------------------------------------------------- Sensitivity Pr( +| D) 42.86% Specificity Pr( -|~D) 94.12% Positive predictive value Pr( D| +) 66.67% Negative predictive value Pr(~D| -) 85.71% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 5.88% False - rate for true D Pr( -| D) 57.14% False + rate for classified + Pr(~D| +) 33.33% False - rate for classified - Pr( D| -) 14.29% -------------------------------------------------- Correctly classified 83.08% -------------------------------------------------- Logistic model for HP2work, goodness-of-fit test number of observations = 325 number of covariate patterns = 325 Pearson chi2(276) = 298.51 Prob > chi2 = 0.1682 Measures of Fit for logistic of HP2work Log-Lik Intercept Only: -169.326 Log-Lik Full Model: -115.519 D(269): 231.037 LR(48): 107.615 Prob > LR: 0.000 McFadden's R2: 0.318 McFadden's Adj R2: -0.013 Maximum Likelihood R2: 0.282 Cragg & Uhler's R2: 0.436 McKelvey and Zavoina's R2: 0.713 Efron's R2: 0.332 Variance of y*: 11.462 Variance of error: 3.290 Count R2: 0.831 Adj Count R2: 0.214 AIC: 1.055 AIC*n: 343.037 BIC: -1324.811 BIC': 170.008 Full main model for HP2work for wave= 3 chunk 2 H1 test:Gender= 2 model Wave = 3 for HP2work i.educ _Ieduc_1-8 (naturally coded; _Ieduc_1 omitted) note: occ6w3 != 0 predicts failure perfectly occ6w3 dropped and 4 obs not used note: occ8w3 != 0 predicts failure perfectly occ8w3 dropped and 1 obs not used note: bf15m != 0 predicts failure perfectly bf15m dropped and 12 obs not used note: _Ieduc_8 omitted because of collinearity note: bf17 omitted because of collinearity Logistic regression Number of obs = 345 LR chi2(50) = 106.32 Prob > chi2 = 0.0000 Log likelihood = -147.91609 Pseudo R2 = 0.2644 ------------------------------------------------------------------------------ HP2work | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0539741 .0202532 2.66 0.008 .0142786 .0936696 _Ieduc_2 | -12.55341 623.5872 -0.02 0.984 -1234.762 1209.655 _Ieduc_3 | -13.54577 623.5871 -0.02 0.983 -1235.754 1208.663 _Ieduc_4 | -12.04583 623.5872 -0.02 0.985 -1234.254 1210.163 _Ieduc_5 | -13.6714 623.5873 -0.02 0.983 -1235.88 1208.537 _Ieduc_6 | -13.3439 623.5871 -0.02 0.983 -1235.552 1208.864 _Ieduc_7 | -14.44833 623.5903 -0.02 0.982 -1236.663 1207.766 _Ieduc_8 | 0 (omitted) occ1w3 | .1126048 1.869311 0.06 0.952 -3.551177 3.776386 occ2w3 | .1300177 1.92152 0.07 0.946 -3.636092 3.896127 occ3w3 | .4109427 1.89228 0.22 0.828 -3.297858 4.119743 occ4w3 | -.168581 2.072728 -0.08 0.935 -4.231054 3.893892 occ5w3 | 1.045375 2.389172 0.44 0.662 -3.637316 5.728065 occ6w3 | 0 (omitted) occ7w3 | -.3503943 1.867461 -0.19 0.851 -4.01055 3.309761 occ8w3 | 0 (omitted) marrw31 | -.807006 1.451843 -0.56 0.578 -3.652566 2.038554 marrw32 | -.3908773 1.745393 -0.22 0.823 -3.811785 3.030031 marrw33 | -.3675069 1.295392 -0.28 0.777 -2.906429 2.171415 marrw35 | -.1977292 1.318807 -0.15 0.881 -2.782543 2.387085 marrw36 | .7011152 1.329741 0.53 0.598 -1.90513 3.30736 inc1w3 | .9742727 1.913 0.51 0.611 -2.775139 4.723684 inc2w3 | .8770803 1.873885 0.47 0.640 -2.795667 4.549827 inc3w3 | .6085909 1.869674 0.33 0.745 -3.055903 4.273085 inc4w3 | -.7888601 2.462315 -0.32 0.749 -5.614908 4.037188 radhlw3 | .0045205 .0073058 0.62 0.536 -.0097986 .0188397 havmil | -.0009271 .0024979 -0.37 0.711 -.0058229 .0039686 avgcumdosew3 | .115088 .0796177 1.45 0.148 -.0409598 .2711358 bf1 | .0054828 .0325747 0.17 0.866 -.0583624 .069328 bf4 | -.7222893 .236357 -3.06 0.002 -1.18554 -.2590382 bf2 | -.0000397 .0001011 -0.39 0.694 -.0002378 .0001584 bf4m | .5355567 .2180534 2.46 0.014 .1081798 .9629336 bf5m | .0021761 .0013897 1.57 0.117 -.0005476 .0048998 bf7m | .0008931 .0005154 1.73 0.083 -.0001171 .0019033 bf8 | -.000022 .0000319 -0.69 0.491 -.0000845 .0000406 bf15m | 0 (omitted) bf17 | 0 (omitted) bf20 | -.0052234 .0270949 -0.19 0.847 -.0583285 .0478817 bf22 | -.0001469 .0001125 -1.31 0.192 -.0003673 .0000736 bf29 | .0000122 .0000367 0.33 0.740 -.0000598 .0000841 bf30 | .0000264 .0002891 0.09 0.927 -.0005402 .000593 bf40 | .2842481 .1315066 2.16 0.031 .0264999 .5419962 deaw3 | .0612074 .1656786 0.37 0.712 -.2635167 .3859315 dvcew3 | -.3890334 .779063 -0.50 0.618 -1.915969 1.137902 sepaw3 | 1.192013 .8154298 1.46 0.144 -.4062002 2.790226 accdw3 | .0577299 .4605728 0.13 0.900 -.8449761 .9604359 movew3 | -1.554315 1.416782 -1.10 0.273 -4.331156 1.222526 illw3 | -.2170464 .1492827 -1.45 0.146 -.5096352 .0755424 shfamw3 | -.006443 .0065281 -0.99 0.324 -.0192379 .0063519 shhlw3 | .0069987 .00596 1.17 0.240 -.0046826 .0186801 shjobw3 | .002409 .0061202 0.39 0.694 -.0095863 .0144043 shrelaw3 | -.0078238 .0063566 -1.23 0.218 -.0202824 .0046348 suprtw3 | .0085376 .0067506 1.26 0.206 -.0046933 .0217685 suchrw3 | -.007482 .0046136 -1.62 0.105 -.0165246 .0015606 havmilsq | -3.28e-09 1.73e-06 -0.00 0.998 -3.39e-06 3.38e-06 _cons | 4.903623 623.5943 0.01 0.994 -1217.319 1227.126 ------------------------------------------------------------------------------ Logistic model for HP2work -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 45 24 | 69 - | 48 228 | 276 -----------+--------------------------+----------- Total | 93 252 | 345 Classified + if predicted Pr(D) >= .5 True D defined as HP2work != 0 -------------------------------------------------- Sensitivity Pr( +| D) 48.39% Specificity Pr( -|~D) 90.48% Positive predictive value Pr( D| +) 65.22% Negative predictive value Pr(~D| -) 82.61% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 9.52% False - rate for true D Pr( -| D) 51.61% False + rate for classified + Pr(~D| +) 34.78% False - rate for classified - Pr( D| -) 17.39% -------------------------------------------------- Correctly classified 79.13% -------------------------------------------------- Logistic model for HP2work, goodness-of-fit test number of observations = 345 number of covariate patterns = 345 Pearson chi2(294) = 317.37 Prob > chi2 = 0.1668 Measures of Fit for logistic of HP2work Log-Lik Intercept Only: -201.075 Log-Lik Full Model: -147.916 D(289): 295.832 LR(50): 106.318 Prob > LR: 0.000 McFadden's R2: 0.264 McFadden's Adj R2: -0.014 Maximum Likelihood R2: 0.265 Cragg & Uhler's R2: 0.385 McKelvey and Zavoina's R2: 0.488 Efron's R2: 0.291 Variance of y*: 6.432 Variance of error: 3.290 Count R2: 0.791 Adj Count R2: 0.226 AIC: 1.182 AIC*n: 407.832 BIC: -1392.952 BIC': 185.860 Full main model for HP2hmcare for wave= 3 chunk 2 H1 test:Gender= 1 model Wave = 3 for HP2work i.educ _Ieduc_1-8 (naturally coded; _Ieduc_1 omitted) note: _Ieduc_4 != 0 predicts failure perfectly _Ieduc_4 dropped and 14 obs not used note: _Ieduc_8 != 0 predicts failure perfectly _Ieduc_8 dropped and 2 obs not used note: occ6w3 != 0 predicts failure perfectly occ6w3 dropped and 4 obs not used note: bf17 != 0 predicts failure perfectly bf17 dropped and 5 obs not used note: _Ieduc_7 omitted because of collinearity note: occ8w3 omitted because of collinearity note: marrw36 omitted because of collinearity Logistic regression Number of obs = 315 LR chi2(48) = 139.93 Prob > chi2 = 0.0000 Log likelihood = -96.893664 Pseudo R2 = 0.4193 ------------------------------------------------------------------------------ HP2hmcare | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0323974 .0293162 1.11 0.269 -.0250612 .089856 _Ieduc_2 | -4.152531 2.287775 -1.82 0.070 -8.636488 .3314257 _Ieduc_3 | -1.864493 1.608696 -1.16 0.246 -5.017479 1.288493 _Ieduc_4 | 0 (omitted) _Ieduc_5 | -1.404302 1.64491 -0.85 0.393 -4.628265 1.819662 _Ieduc_6 | -2.017048 1.54335 -1.31 0.191 -5.041958 1.007861 _Ieduc_7 | 0 (omitted) _Ieduc_8 | 0 (omitted) occ1w3 | -11.82929 1296.263 -0.01 0.993 -2552.458 2528.799 occ2w3 | -11.65702 1296.263 -0.01 0.993 -2552.286 2528.972 occ3w3 | -12.78325 1296.263 -0.01 0.992 -2553.412 2527.846 occ4w3 | -10.84152 1296.263 -0.01 0.993 -2551.47 2529.787 occ5w3 | -10.72665 1296.263 -0.01 0.993 -2551.356 2529.903 occ6w3 | 0 (omitted) occ7w3 | -11.31316 1296.263 -0.01 0.993 -2551.942 2529.316 occ8w3 | 0 (omitted) marrw31 | .3643704 1.429352 0.25 0.799 -2.437107 3.165848 marrw32 | -2.206121 1.844343 -1.20 0.232 -5.820966 1.408725 marrw33 | -.7934545 1.390519 -0.57 0.568 -3.518821 1.931912 marrw35 | -.2775718 1.556356 -0.18 0.858 -3.327973 2.772829 marrw36 | 0 (omitted) inc1w3 | 14.70395 1296.262 0.01 0.991 -2525.924 2555.332 inc2w3 | 14.77269 1296.262 0.01 0.991 -2525.855 2555.4 inc3w3 | 14.57764 1296.262 0.01 0.991 -2526.05 2555.205 inc4w3 | 15.74154 1296.263 0.01 0.990 -2524.887 2556.37 radhlw3 | .0078686 .0080582 0.98 0.329 -.007925 .0236623 havmil | .0027954 .0078952 0.35 0.723 -.0126789 .0182698 avgcumdosew3 | .0057068 .0769937 0.07 0.941 -.1451981 .1566117 bf1 | -.0445389 .0484618 -0.92 0.358 -.1395224 .0504446 bf4 | -.0327423 .2796012 -0.12 0.907 -.5807506 .515266 bf2 | .0000822 .0001677 0.49 0.624 -.0002465 .0004108 bf4m | -.341802 .2609957 -1.31 0.190 -.8533441 .1697402 bf5m | .0012439 .0017995 0.69 0.489 -.0022831 .0047709 bf7m | .0005614 .0005422 1.04 0.300 -.0005013 .0016241 bf8 | -.0000499 .0000448 -1.11 0.265 -.0001376 .0000379 bf15m | -.0000712 .0003918 -0.18 0.856 -.0008391 .0006966 bf17 | 0 (omitted) bf20 | .019063 .0407736 0.47 0.640 -.0608518 .0989778 bf22 | .0000146 .0001733 0.08 0.933 -.0003251 .0003543 bf29 | .0000124 .0000229 0.54 0.589 -.0000325 .0000572 bf30 | -.000416 .0004185 -0.99 0.320 -.0012364 .0004043 bf40 | .1486565 .2411791 0.62 0.538 -.3240459 .6213588 deaw3 | -.6566764 .3112091 -2.11 0.035 -1.266635 -.0467177 dvcew3 | .7731044 1.122755 0.69 0.491 -1.427455 2.973664 sepaw3 | .1659839 1.359372 0.12 0.903 -2.498337 2.830305 accdw3 | .7493757 .6472786 1.16 0.247 -.519267 2.018018 movew3 | .9688514 .5333557 1.82 0.069 -.0765066 2.014209 illw3 | .2806377 .2813528 1.00 0.319 -.2708037 .832079 shfamw3 | .0045809 .0088802 0.52 0.606 -.0128239 .0219857 shhlw3 | -.0144819 .0077 -1.88 0.060 -.0295736 .0006098 shjobw3 | -.0101653 .0077745 -1.31 0.191 -.0254031 .0050725 shrelaw3 | -.0092584 .0083742 -1.11 0.269 -.0256716 .0071547 suprtw3 | -.0009401 .0080071 -0.12 0.907 -.0166337 .0147535 suchrw3 | -.004683 .0069496 -0.67 0.500 -.0183041 .008938 havmilsq | -7.50e-06 .0000145 -0.52 0.604 -.0000359 .0000209 _cons | 3.229911 4.235709 0.76 0.446 -5.071927 11.53175 ------------------------------------------------------------------------------ Note: 3 failures and 0 successes completely determined. Logistic model for HP2hmcare -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 37 14 | 51 - | 33 231 | 264 -----------+--------------------------+----------- Total | 70 245 | 315 Classified + if predicted Pr(D) >= .5 True D defined as HP2hmcare != 0 -------------------------------------------------- Sensitivity Pr( +| D) 52.86% Specificity Pr( -|~D) 94.29% Positive predictive value Pr( D| +) 72.55% Negative predictive value Pr(~D| -) 87.50% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 5.71% False - rate for true D Pr( -| D) 47.14% False + rate for classified + Pr(~D| +) 27.45% False - rate for classified - Pr( D| -) 12.50% -------------------------------------------------- Correctly classified 85.08% -------------------------------------------------- Logistic model for HP2hmcare, goodness-of-fit test number of observations = 315 number of covariate patterns = 315 Pearson chi2(266) = 247.97 Prob > chi2 = 0.7796 Measures of Fit for logistic of HP2hmcare Log-Lik Intercept Only: -166.857 Log-Lik Full Model: -96.894 D(259): 193.787 LR(48): 139.928 Prob > LR: 0.000 McFadden's R2: 0.419 McFadden's Adj R2: 0.084 Maximum Likelihood R2: 0.359 Cragg & Uhler's R2: 0.549 McKelvey and Zavoina's R2: 0.758 Efron's R2: 0.437 Variance of y*: 13.609 Variance of error: 3.290 Count R2: 0.851 Adj Count R2: 0.329 AIC: 0.971 AIC*n: 305.787 BIC: -1296.129 BIC': 136.196 Full main model for HP2hmcare for wave= 3 chunk 2 H1 test:Gender= 2 model Wave = 3 for HP2hmcare i.educ _Ieduc_1-8 (naturally coded; _Ieduc_1 omitted) note: occ6w3 != 0 predicts failure perfectly occ6w3 dropped and 4 obs not used note: occ8w3 != 0 predicts failure perfectly occ8w3 dropped and 1 obs not used note: bf29 != 0 predicts success perfectly bf29 dropped and 4 obs not used note: _Ieduc_8 omitted because of collinearity convergence not achieved Logistic regression Number of obs = 353 LR chi2(50) = 144.83 Prob > chi2 = 0.0000 Log likelihood = -154.51255 Pseudo R2 = 0.3191 ------------------------------------------------------------------------------ HP2hmcare | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0784128 .0199184 3.94 0.000 .0393735 .1174521 _Ieduc_2 | -16.15888 2.72009 -5.94 0.000 -21.49016 -10.8276 _Ieduc_3 | -16.70929 2.647032 -6.31 0.000 -21.89738 -11.5212 _Ieduc_4 | -15.65932 2.672964 -5.86 0.000 -20.89823 -10.4204 _Ieduc_5 | -16.93546 2.621945 -6.46 0.000 -22.07438 -11.79654 _Ieduc_6 | -17.12993 2.678622 -6.40 0.000 -22.37993 -11.87993 _Ieduc_7 | -16.6826 3.290952 -5.07 0.000 -23.13274 -10.23245 _Ieduc_8 | 0 (omitted) occ1w3 | -17.5089 2870.035 -0.01 0.995 -5642.674 5607.656 occ2w3 | -17.42465 2870.035 -0.01 0.995 -5642.59 5607.741 occ3w3 | -17.38618 2870.035 -0.01 0.995 -5642.551 5607.779 occ4w3 | -17.97919 2870.035 -0.01 0.995 -5643.145 5607.186 occ5w3 | -16.19886 2870.036 -0.01 0.995 -5641.366 5608.968 occ6w3 | 0 (omitted) occ7w3 | -17.37679 2870.035 -0.01 0.995 -5642.542 5607.789 occ8w3 | 0 (omitted) marrw31 | .1254457 1.662878 0.08 0.940 -3.133735 3.384627 marrw32 | .689276 1.963389 0.35 0.726 -3.158896 4.537448 marrw33 | 1.411752 1.537008 0.92 0.358 -1.600728 4.424232 marrw35 | .6824445 1.564972 0.44 0.663 -2.384843 3.749732 marrw36 | .9604788 1.548632 0.62 0.535 -2.074784 3.995742 inc1w3 | 18.76205 2870.035 0.01 0.995 -5606.403 5643.927 inc2w3 | 18.64464 2870.035 0.01 0.995 -5606.521 5643.81 inc3w3 | 18.13548 2870.035 0.01 0.995 -5607.03 5643.301 inc4w3 | 18.63139 2870.035 0.01 0.995 -5606.534 5643.797 radhlw3 | -.0056373 .0071331 -0.79 0.429 -.0196178 .0083433 havmil | .0003358 .0026887 0.12 0.901 -.004934 .0056056 avgcumdosew3 | -.1458757 .0962788 -1.52 0.130 -.3345787 .0428273 bf1 | -.0155333 .0271811 -0.57 0.568 -.0688074 .0377407 bf4 | -.4865728 .1784134 -2.73 0.006 -.8362567 -.136889 bf2 | .0000926 .0001019 0.91 0.364 -.0001072 .0002923 bf4m | .3213367 .1603015 2.00 0.045 .0071516 .6355219 bf5m | -.000883 .0014167 -0.62 0.533 -.0036598 .0018937 bf7m | .0002998 .000443 0.68 0.499 -.0005684 .001168 bf8 | 6.84e-06 .0000322 0.21 0.832 -.0000563 .00007 bf15m | -.0163738 .5454291 -0.03 0.976 -1.085395 1.052648 bf17 | .0008202 .0272715 0.03 0.976 -.0526309 .0542713 bf20 | .00093 .0215397 0.04 0.966 -.041287 .043147 bf22 | -.0000872 .0001081 -0.81 0.420 -.0002991 .0001247 bf29 | 0 (omitted) bf30 | .0000251 .0002916 0.09 0.931 -.0005465 .0005967 bf40 | .130008 .1227916 1.06 0.290 -.1106591 .3706751 deaw3 | .0165154 .1614822 0.10 0.919 -.2999838 .3330147 dvcew3 | .6982802 .7163029 0.97 0.330 -.7056476 2.102208 sepaw3 | -.4992309 .8307882 -0.60 0.548 -2.127546 1.129084 accdw3 | -.1706856 .4639657 -0.37 0.713 -1.080042 .7386705 movew3 | -.4464406 1.157043 -0.39 0.700 -2.714203 1.821322 illw3 | -.0890835 .1513588 -0.59 0.556 -.3857412 .2075743 shfamw3 | -.0035627 .0062149 -0.57 0.566 -.0157436 .0086183 shhlw3 | .0080044 .0056769 1.41 0.159 -.0031221 .0191309 shjobw3 | -.0042351 .0058007 -0.73 0.465 -.0156042 .0071341 shrelaw3 | -.010315 .0062344 -1.65 0.098 -.0225341 .0019041 suprtw3 | -.0017061 .0061593 -0.28 0.782 -.0137782 .010366 suchrw3 | -.0030007 .0044692 -0.67 0.502 -.0117602 .0057587 havmilsq | -1.55e-06 2.58e-06 -0.60 0.549 -6.61e-06 3.52e-06 _cons | 10.07155 . . . . . ------------------------------------------------------------------------------ Note: 4 failures and 0 successes completely determined. Warning: convergence not achieved Logistic model for HP2hmcare -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 76 29 | 105 - | 45 203 | 248 -----------+--------------------------+----------- Total | 121 232 | 353 Classified + if predicted Pr(D) >= .5 True D defined as HP2hmcare != 0 -------------------------------------------------- Sensitivity Pr( +| D) 62.81% Specificity Pr( -|~D) 87.50% Positive predictive value Pr( D| +) 72.38% Negative predictive value Pr(~D| -) 81.85% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 12.50% False - rate for true D Pr( -| D) 37.19% False + rate for classified + Pr(~D| +) 27.62% False - rate for classified - Pr( D| -) 18.15% -------------------------------------------------- Correctly classified 79.04% -------------------------------------------------- Logistic model for HP2hmcare, goodness-of-fit test number of observations = 353 number of covariate patterns = 353 Pearson chi2(301) = 338.41 Prob > chi2 = 0.0677 Measures of Fit for logistic of HP2hmcare Log-Lik Intercept Only: -226.929 Log-Lik Full Model: -154.513 D(297): 309.025 LR(50): 144.834 Prob > LR: 0.000 McFadden's R2: 0.319 McFadden's Adj R2: 0.072 Maximum Likelihood R2: 0.337 Cragg & Uhler's R2: 0.465 McKelvey and Zavoina's R2: 0.954 Efron's R2: 0.369 Variance of y*: 71.429 Variance of error: 3.290 Count R2: 0.790 Adj Count R2: 0.388 AIC: 1.193 AIC*n: 421.025 BIC: -1433.316 BIC': 148.490 Full main model for HP2probsoc for wave= 3 chunk 2 H1 test:Gender= 1 model Wave = 3 for HP2hmcare i.educ _Ieduc_1-8 (naturally coded; _Ieduc_1 omitted) note: _Ieduc_4 != 0 predicts failure perfectly _Ieduc_4 dropped and 14 obs not used note: _Ieduc_7 != 0 predicts failure perfectly _Ieduc_7 dropped and 4 obs not used note: _Ieduc_8 != 0 predicts failure perfectly _Ieduc_8 dropped and 2 obs not used note: occ5w3 != 0 predicts failure perfectly occ5w3 dropped and 15 obs not used note: occ6w3 != 0 predicts failure perfectly occ6w3 dropped and 4 obs not used note: marrw32 != 0 predicts failure perfectly marrw32 dropped and 20 obs not used note: bf15m != 0 predicts failure perfectly bf15m dropped and 15 obs not used note: _Ieduc_6 omitted because of collinearity note: occ8w3 omitted because of collinearity note: marrw36 omitted because of collinearity note: bf17 omitted because of collinearity Logistic regression Number of obs = 266 LR chi2(44) = 125.89 Prob > chi2 = 0.0000 Log likelihood = -51.38371 Pseudo R2 = 0.5506 ------------------------------------------------------------------------------ HP2probsoc | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .1094616 .0479486 2.28 0.022 .015484 .2034392 _Ieduc_2 | .7414425 1.297886 0.57 0.568 -1.802367 3.285252 _Ieduc_3 | -1.614771 .8291042 -1.95 0.051 -3.239785 .0102435 _Ieduc_4 | 0 (omitted) _Ieduc_5 | -1.309884 1.008415 -1.30 0.194 -3.286342 .6665737 _Ieduc_6 | 0 (omitted) _Ieduc_7 | 0 (omitted) _Ieduc_8 | 0 (omitted) occ1w3 | -14.19493 1124.783 -0.01 0.990 -2218.729 2190.339 occ2w3 | -12.80013 1124.783 -0.01 0.991 -2217.335 2191.734 occ3w3 | -14.84881 1124.785 -0.01 0.989 -2219.387 2189.689 occ4w3 | -13.35572 1124.784 -0.01 0.991 -2217.891 2191.18 occ5w3 | 0 (omitted) occ6w3 | 0 (omitted) occ7w3 | -14.19043 1124.784 -0.01 0.990 -2218.726 2190.345 occ8w3 | 0 (omitted) marrw31 | 3.074981 1.891094 1.63 0.104 -.6314958 6.781458 marrw32 | 0 (omitted) marrw33 | 1.087086 1.851071 0.59 0.557 -2.540947 4.715119 marrw35 | 2.144183 1.926965 1.11 0.266 -1.632599 5.920964 marrw36 | 0 (omitted) inc1w3 | 12.66541 1124.784 0.01 0.991 -2191.87 2217.201 inc2w3 | 14.23621 1124.783 0.01 0.990 -2190.299 2218.771 inc3w3 | 11.68224 1124.783 0.01 0.992 -2192.853 2216.217 inc4w3 | 13.15717 1124.785 0.01 0.991 -2191.381 2217.695 radhlw3 | .0116102 .013936 0.83 0.405 -.0157038 .0389242 havmil | .010259 .0190025 0.54 0.589 -.0269853 .0475032 avgcumdosew3 | .013934 .0740721 0.19 0.851 -.1312447 .1591127 bf1 | .0049612 .0648373 0.08 0.939 -.1221176 .1320399 bf4 | .3309901 .3608169 0.92 0.359 -.376198 1.038178 bf2 | .0003753 .0003121 1.20 0.229 -.0002364 .000987 bf4m | -.7073564 .3457629 -2.05 0.041 -1.385039 -.0296735 bf5m | .0055743 .0030295 1.84 0.066 -.0003633 .0115119 bf7m | .0005904 .001055 0.56 0.576 -.0014774 .0026582 bf8 | -.0001253 .0000745 -1.68 0.093 -.0002713 .0000207 bf15m | 0 (omitted) bf17 | 0 (omitted) bf20 | -.0283325 .0488173 -0.58 0.562 -.1240127 .0673477 bf22 | .000352 .0002932 1.20 0.230 -.0002227 .0009267 bf29 | -.0000333 .0000588 -0.57 0.572 -.0001486 .000082 bf30 | -.0013785 .0007131 -1.93 0.053 -.0027761 .0000191 bf40 | -.3600239 .3692219 -0.98 0.330 -1.083686 .3636377 deaw3 | -.5217994 .4891348 -1.07 0.286 -1.480486 .4368872 dvcew3 | -.5047921 1.728469 -0.29 0.770 -3.892529 2.882945 sepaw3 | 1.877558 1.625412 1.16 0.248 -1.308191 5.063307 accdw3 | -1.417017 1.419234 -1.00 0.318 -4.198664 1.364631 movew3 | -1.057894 1.576256 -0.67 0.502 -4.1473 2.031511 illw3 | .0330976 .3751226 0.09 0.930 -.7021292 .7683243 shfamw3 | .012083 .0115403 1.05 0.295 -.0105354 .0347015 shhlw3 | -.0165557 .0125582 -1.32 0.187 -.0411693 .0080578 shjobw3 | .032774 .0134379 2.44 0.015 .0064363 .0591118 shrelaw3 | -.0108059 .0117883 -0.92 0.359 -.0339106 .0122988 suprtw3 | -.014138 .0155065 -0.91 0.362 -.0445303 .0162542 suchrw3 | .0131393 .0111977 1.17 0.241 -.0088078 .0350865 havmilsq | -.000014 .0000386 -0.36 0.717 -.0000896 .0000616 _cons | .4495347 5.049973 0.09 0.929 -9.44823 10.3473 ------------------------------------------------------------------------------ Note: 3 failures and 0 successes completely determined. Logistic model for HP2probsoc -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 27 5 | 32 - | 14 220 | 234 -----------+--------------------------+----------- Total | 41 225 | 266 Classified + if predicted Pr(D) >= .5 True D defined as HP2probsoc != 0 -------------------------------------------------- Sensitivity Pr( +| D) 65.85% Specificity Pr( -|~D) 97.78% Positive predictive value Pr( D| +) 84.38% Negative predictive value Pr(~D| -) 94.02% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 2.22% False - rate for true D Pr( -| D) 34.15% False + rate for classified + Pr(~D| +) 15.62% False - rate for classified - Pr( D| -) 5.98% -------------------------------------------------- Correctly classified 92.86% -------------------------------------------------- Logistic model for HP2probsoc, goodness-of-fit test number of observations = 266 number of covariate patterns = 266 Pearson chi2(221) = 138.28 Prob > chi2 = 1.0000 Measures of Fit for logistic of HP2probsoc Log-Lik Intercept Only: -114.331 Log-Lik Full Model: -51.384 D(210): 102.767 LR(44): 125.895 Prob > LR: 0.000 McFadden's R2: 0.551 McFadden's Adj R2: 0.061 Maximum Likelihood R2: 0.377 Cragg & Uhler's R2: 0.654 McKelvey and Zavoina's R2: 0.833 Efron's R2: 0.549 Variance of y*: 19.713 Variance of error: 3.290 Count R2: 0.929 Adj Count R2: 0.537 AIC: 0.807 AIC*n: 214.767 BIC: -1069.767 BIC': 119.779 Full main model for HP2probsoc for wave= 3 chunk 2 H1 test:Gender= 2 model Wave = 3 for HP2probsoc i.educ _Ieduc_1-8 (naturally coded; _Ieduc_1 omitted) note: occ4w3 != 0 predicts failure perfectly occ4w3 dropped and 8 obs not used note: occ5w3 != 0 predicts failure perfectly occ5w3 dropped and 5 obs not used note: occ6w3 != 0 predicts failure perfectly occ6w3 dropped and 4 obs not used note: occ8w3 != 0 predicts failure perfectly occ8w3 dropped and 1 obs not used note: bf15m != 0 predicts failure perfectly bf15m dropped and 11 obs not used note: _Ieduc_8 omitted because of collinearity note: bf17 omitted because of collinearity Logistic regression Number of obs = 333 LR chi2(48) = 182.65 Prob > chi2 = 0.0000 Log likelihood = -85.065495 Pseudo R2 = 0.5177 ------------------------------------------------------------------------------ HP2probsoc | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .1095324 .0321452 3.41 0.001 .0465289 .1725358 _Ieduc_2 | -13.53237 1231.492 -0.01 0.991 -2427.212 2400.147 _Ieduc_3 | -13.52493 1231.492 -0.01 0.991 -2427.204 2400.154 _Ieduc_4 | -12.60239 1231.492 -0.01 0.992 -2426.282 2401.077 _Ieduc_5 | -12.71374 1231.492 -0.01 0.992 -2426.393 2400.966 _Ieduc_6 | -14.01871 1231.492 -0.01 0.991 -2427.698 2399.66 _Ieduc_7 | -14.42024 1231.563 -0.01 0.991 -2428.239 2399.398 _Ieduc_8 | 0 (omitted) occ1w3 | -1.43031 4.480321 -0.32 0.750 -10.21158 7.350959 occ2w3 | -.9422793 4.54239 -0.21 0.836 -9.8452 7.960641 occ3w3 | -.9893619 4.495549 -0.22 0.826 -9.800476 7.821752 occ4w3 | 0 (omitted) occ5w3 | 0 (omitted) occ6w3 | 0 (omitted) occ7w3 | -.3813499 4.479039 -0.09 0.932 -9.160105 8.397405 occ8w3 | 0 (omitted) marrw31 | -1.356413 4.804963 -0.28 0.778 -10.77397 8.061141 marrw32 | 1.424321 4.907376 0.29 0.772 -8.193959 11.0426 marrw33 | .9014745 4.669929 0.19 0.847 -8.251419 10.05437 marrw35 | .1665893 4.645112 0.04 0.971 -8.937664 9.270842 marrw36 | .3174753 4.648882 0.07 0.946 -8.794166 9.429116 inc1w3 | .8600896 4.513897 0.19 0.849 -7.986987 9.707166 inc2w3 | 1.384829 4.490321 0.31 0.758 -7.416038 10.1857 inc3w3 | .4792744 4.482989 0.11 0.915 -8.307222 9.26577 inc4w3 | 2.266942 4.835774 0.47 0.639 -7.211 11.74488 radhlw3 | .0131788 .0108242 1.22 0.223 -.0080363 .0343939 havmil | .0001731 .0072695 0.02 0.981 -.0140748 .014421 avgcumdosew3 | .4373021 .1594734 2.74 0.006 .12474 .7498642 bf1 | .0565003 .0423978 1.33 0.183 -.0265978 .1395985 bf4 | -.5202783 .2238014 -2.32 0.020 -.9589209 -.0816356 bf2 | .0000421 .0001478 0.28 0.776 -.0002477 .0003318 bf4m | .2426577 .1977977 1.23 0.220 -.1450185 .630334 bf5m | -.0017451 .0026768 -0.65 0.514 -.0069915 .0035013 bf7m | .0007865 .0007919 0.99 0.321 -.0007656 .0023387 bf8 | .0000207 .0000544 0.38 0.704 -.000086 .0001273 bf15m | 0 (omitted) bf17 | 0 (omitted) bf20 | -.0669294 .0330398 -2.03 0.043 -.1316862 -.0021726 bf22 | -.0000944 .0001823 -0.52 0.605 -.0004517 .0002629 bf29 | -.0000309 .000047 -0.66 0.511 -.0001229 .0000611 bf30 | .0003246 .0004246 0.76 0.445 -.0005076 .0011567 bf40 | .0606979 .1844629 0.33 0.742 -.3008427 .4222385 deaw3 | .1696097 .2295421 0.74 0.460 -.2802844 .6195039 dvcew3 | .3810548 1.285314 0.30 0.767 -2.138115 2.900224 sepaw3 | -2.876602 1.529689 -1.88 0.060 -5.874737 .1215322 accdw3 | .1226563 .714668 0.17 0.864 -1.278067 1.52338 movew3 | 1.918652 1.360681 1.41 0.159 -.7482334 4.585538 illw3 | .2671943 .2045213 1.31 0.191 -.1336601 .6680487 shfamw3 | -.0003116 .0095404 -0.03 0.974 -.0190104 .0183873 shhlw3 | -.0026048 .0074647 -0.35 0.727 -.0172353 .0120256 shjobw3 | .006075 .0086284 0.70 0.481 -.0108364 .0229864 shrelaw3 | -.0267274 .010033 -2.66 0.008 -.0463918 -.007063 suprtw3 | -.0065983 .0100162 -0.66 0.510 -.0262297 .0130331 suchrw3 | .0015649 .0064519 0.24 0.808 -.0110806 .0142105 havmilsq | -3.19e-06 .0000124 -0.26 0.797 -.0000275 .0000211 _cons | 6.986764 1231.505 0.01 0.995 -2406.718 2420.692 ------------------------------------------------------------------------------ Note: 1 failure and 0 successes completely determined. Logistic model for HP2probsoc -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 54 13 | 67 - | 20 246 | 266 -----------+--------------------------+----------- Total | 74 259 | 333 Classified + if predicted Pr(D) >= .5 True D defined as HP2probsoc != 0 -------------------------------------------------- Sensitivity Pr( +| D) 72.97% Specificity Pr( -|~D) 94.98% Positive predictive value Pr( D| +) 80.60% Negative predictive value Pr(~D| -) 92.48% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 5.02% False - rate for true D Pr( -| D) 27.03% False + rate for classified + Pr(~D| +) 19.40% False - rate for classified - Pr( D| -) 7.52% -------------------------------------------------- Correctly classified 90.09% -------------------------------------------------- Logistic model for HP2probsoc, goodness-of-fit test number of observations = 333 number of covariate patterns = 333 Pearson chi2(284) = 335.12 Prob > chi2 = 0.0199 Measures of Fit for logistic of HP2probsoc Log-Lik Intercept Only: -176.392 Log-Lik Full Model: -85.065 D(277): 170.131 LR(48): 182.653 Prob > LR: 0.000 McFadden's R2: 0.518 McFadden's Adj R2: 0.200 Maximum Likelihood R2: 0.422 Cragg & Uhler's R2: 0.646 McKelvey and Zavoina's R2: 0.810 Efron's R2: 0.561 Variance of y*: 17.273 Variance of error: 3.290 Count R2: 0.901 Adj Count R2: 0.554 AIC: 0.847 AIC*n: 282.131 BIC: -1438.724 BIC': 96.138 Full main model for HP2pbfhm for wave= 3 chunk 2 H1 test:Gender= 1 model Wave = 3 for HP2probsoc i.educ _Ieduc_1-8 (naturally coded; _Ieduc_1 omitted) note: _Ieduc_2 != 0 predicts failure perfectly _Ieduc_2 dropped and 10 obs not used note: _Ieduc_4 != 0 predicts failure perfectly _Ieduc_4 dropped and 14 obs not used note: _Ieduc_7 != 0 predicts failure perfectly _Ieduc_7 dropped and 4 obs not used note: _Ieduc_8 != 0 predicts failure perfectly _Ieduc_8 dropped and 2 obs not used note: occ5w3 != 0 predicts failure perfectly occ5w3 dropped and 13 obs not used note: occ6w3 != 0 predicts failure perfectly occ6w3 dropped and 4 obs not used note: bf15m != 0 predicts failure perfectly bf15m dropped and 17 obs not used note: bf29 != 0 predicts failure perfectly bf29 dropped and 6 obs not used note: movew3 != 0 predicts failure perfectly movew3 dropped and 22 obs not used note: _Ieduc_6 omitted because of collinearity note: occ8w3 omitted because of collinearity note: marrw36 omitted because of collinearity note: bf17 omitted because of collinearity Logistic regression Number of obs = 248 LR chi2(42) = 61.10 Prob > chi2 = 0.0286 Log likelihood = -43.736999 Pseudo R2 = 0.4112 ------------------------------------------------------------------------------ HP2pbfhm | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0762859 .0508028 1.50 0.133 -.0232857 .1758575 _Ieduc_2 | 0 (omitted) _Ieduc_3 | -.1477637 .8109786 -0.18 0.855 -1.737253 1.441725 _Ieduc_4 | 0 (omitted) _Ieduc_5 | -.7596947 1.090598 -0.70 0.486 -2.897227 1.377837 _Ieduc_6 | 0 (omitted) _Ieduc_7 | 0 (omitted) _Ieduc_8 | 0 (omitted) occ1w3 | -10.90364 2018.344 -0.01 0.996 -3966.785 3944.977 occ2w3 | -10.89538 2018.344 -0.01 0.996 -3966.777 3944.986 occ3w3 | -9.963313 2018.344 -0.00 0.996 -3965.846 3945.919 occ4w3 | -10.3499 2018.344 -0.01 0.996 -3966.232 3945.532 occ5w3 | 0 (omitted) occ6w3 | 0 (omitted) occ7w3 | -10.56369 2018.344 -0.01 0.996 -3966.445 3945.318 occ8w3 | 0 (omitted) marrw31 | 1.938945 1.834088 1.06 0.290 -1.655802 5.533692 marrw32 | 2.869349 2.03424 1.41 0.158 -1.117687 6.856385 marrw33 | -2.070881 2.007923 -1.03 0.302 -6.006338 1.864576 marrw35 | 3.548252 2.186549 1.62 0.105 -.7373048 7.833809 marrw36 | 0 (omitted) inc1w3 | 12.37597 2018.344 0.01 0.995 -3943.505 3968.257 inc2w3 | 12.75723 2018.343 0.01 0.995 -3943.123 3968.637 inc3w3 | 11.01982 2018.344 0.01 0.996 -3944.861 3966.9 inc4w3 | 11.952 2018.345 0.01 0.995 -3943.931 3967.835 radhlw3 | .032589 .0182947 1.78 0.075 -.0032679 .0684459 havmil | .0129536 .013774 0.94 0.347 -.0140429 .0399501 avgcumdosew3 | -.3791136 .3273992 -1.16 0.247 -1.020804 .2625771 bf1 | -.1029605 .0825755 -1.25 0.212 -.2648056 .0588846 bf4 | -.1906164 .3464978 -0.55 0.582 -.8697396 .4885069 bf2 | .0004772 .0003548 1.35 0.179 -.0002181 .0011725 bf4m | .0772469 .2972932 0.26 0.795 -.505437 .6599308 bf5m | -.0019382 .0047879 -0.40 0.686 -.0113224 .007446 bf7m | .0012129 .001013 1.20 0.231 -.0007725 .0031983 bf8 | -3.27e-06 .0000957 -0.03 0.973 -.0001909 .0001843 bf15m | 0 (omitted) bf17 | 0 (omitted) bf20 | .0430617 .0653802 0.66 0.510 -.0850811 .1712045 bf22 | -4.46e-06 .0002995 -0.01 0.988 -.0005915 .0005826 bf29 | 0 (omitted) bf30 | .000126 .0007197 0.18 0.861 -.0012845 .0015365 bf40 | .071783 .4795976 0.15 0.881 -.8682111 1.011777 deaw3 | .3272315 .4280065 0.76 0.445 -.5116458 1.166109 dvcew3 | 1.631036 1.568401 1.04 0.298 -1.442973 4.705045 sepaw3 | .2595898 1.605075 0.16 0.872 -2.886299 3.405479 accdw3 | -.9114258 2.076173 -0.44 0.661 -4.980649 3.157798 movew3 | 0 (omitted) illw3 | -.5480408 .5150453 -1.06 0.287 -1.557511 .4614294 shfamw3 | .0143257 .0164517 0.87 0.384 -.017919 .0465703 shhlw3 | -.0109085 .0129224 -0.84 0.399 -.0362359 .014419 shjobw3 | -.0129256 .0143995 -0.90 0.369 -.0411481 .0152969 shrelaw3 | -.0047884 .012683 -0.38 0.706 -.0296466 .0200697 suprtw3 | .025454 .0177967 1.43 0.153 -.0094269 .0603349 suchrw3 | .0037567 .0120299 0.31 0.755 -.0198214 .0273349 havmilsq | -.0000259 .0000249 -1.04 0.299 -.0000746 .0000229 _cons | -12.84498 6.147159 -2.09 0.037 -24.89319 -.79677 ------------------------------------------------------------------------------ Note: 5 failures and 0 successes completely determined. Logistic model for HP2pbfhm -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 9 4 | 13 - | 13 222 | 235 -----------+--------------------------+----------- Total | 22 226 | 248 Classified + if predicted Pr(D) >= .5 True D defined as HP2pbfhm != 0 -------------------------------------------------- Sensitivity Pr( +| D) 40.91% Specificity Pr( -|~D) 98.23% Positive predictive value Pr( D| +) 69.23% Negative predictive value Pr(~D| -) 94.47% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 1.77% False - rate for true D Pr( -| D) 59.09% False + rate for classified + Pr(~D| +) 30.77% False - rate for classified - Pr( D| -) 5.53% -------------------------------------------------- Correctly classified 93.15% -------------------------------------------------- Logistic model for HP2pbfhm, goodness-of-fit test number of observations = 248 number of covariate patterns = 248 Pearson chi2(205) = 151.48 Prob > chi2 = 0.9980 Measures of Fit for logistic of HP2pbfhm Log-Lik Intercept Only: -74.286 Log-Lik Full Model: -43.737 D(192): 87.474 LR(42): 61.099 Prob > LR: 0.029 McFadden's R2: 0.411 McFadden's Adj R2: -0.343 Maximum Likelihood R2: 0.218 Cragg & Uhler's R2: 0.485 McKelvey and Zavoina's R2: 0.816 Efron's R2: 0.329 Variance of y*: 17.878 Variance of error: 3.290 Count R2: 0.931 Adj Count R2: 0.227 AIC: 0.804 AIC*n: 199.474 BIC: -971.104 BIC': 170.465 Full main model for HP2pbfhm for wave= 3 chunk 2 H1 test:Gender= 2 model Wave = 3 for HP2pbfhm i.educ _Ieduc_1-8 (naturally coded; _Ieduc_1 omitted) note: occ2w3 != 0 predicts failure perfectly occ2w3 dropped and 37 obs not used note: occ4w3 != 0 predicts failure perfectly occ4w3 dropped and 8 obs not used note: occ6w3 != 0 predicts failure perfectly occ6w3 dropped and 4 obs not used note: occ8w3 != 0 predicts failure perfectly occ8w3 dropped and 1 obs not used note: marrw32 != 0 predicts failure perfectly marrw32 dropped and 7 obs not used note: inc4w3 != 0 predicts failure perfectly inc4w3 dropped and 8 obs not used note: bf15m != 0 predicts failure perfectly bf15m dropped and 11 obs not used note: movew3 != 0 predicts failure perfectly movew3 dropped and 9 obs not used note: _Ieduc_8 omitted because of collinearity note: bf17 omitted because of collinearity Logistic regression Number of obs = 277 LR chi2(45) = 88.17 Prob > chi2 = 0.0001 Log likelihood = -80.45257 Pseudo R2 = 0.3540 ------------------------------------------------------------------------------ HP2pbfhm | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0605232 .0301499 2.01 0.045 .0014305 .1196159 _Ieduc_2 | 14.33097 3050.48 0.00 0.996 -5964.5 5993.162 _Ieduc_3 | 14.57814 3050.48 0.00 0.996 -5964.253 5993.409 _Ieduc_4 | 14.71229 3050.48 0.00 0.996 -5964.118 5993.543 _Ieduc_5 | 14.46503 3050.48 0.00 0.996 -5964.366 5993.296 _Ieduc_6 | 14.13284 3050.48 0.00 0.996 -5964.698 5992.963 _Ieduc_7 | 16.45371 3050.482 0.01 0.996 -5962.381 5995.289 _Ieduc_8 | 0 (omitted) occ1w3 | -.9142061 3.466224 -0.26 0.792 -7.70788 5.879468 occ2w3 | 0 (omitted) occ3w3 | -.2867411 3.495557 -0.08 0.935 -7.137908 6.564426 occ4w3 | 0 (omitted) occ5w3 | 2.578209 4.53518 0.57 0.570 -6.310581 11.467 occ6w3 | 0 (omitted) occ7w3 | -.5244179 3.46458 -0.15 0.880 -7.31487 6.266034 occ8w3 | 0 (omitted) marrw31 | 13.57521 900.684 0.02 0.988 -1751.733 1778.884 marrw32 | 0 (omitted) marrw33 | 15.5368 900.6835 0.02 0.986 -1749.77 1780.844 marrw35 | 15.43053 900.6834 0.02 0.986 -1749.877 1780.738 marrw36 | 15.00571 900.6833 0.02 0.987 -1750.301 1780.313 inc1w3 | 2.006505 3.516446 0.57 0.568 -4.885601 8.898612 inc2w3 | 2.111761 3.483985 0.61 0.544 -4.716724 8.940246 inc3w3 | 1.911831 3.463507 0.55 0.581 -4.876519 8.70018 inc4w3 | 0 (omitted) radhlw3 | .0113673 .0123354 0.92 0.357 -.0128096 .0355442 havmil | -.0010166 .0142076 -0.07 0.943 -.0288629 .0268297 avgcumdosew3 | -.0338506 .1440343 -0.24 0.814 -.3161526 .2484513 bf1 | -.0040962 .0453653 -0.09 0.928 -.0930105 .0848181 bf4 | -.3790747 .2483688 -1.53 0.127 -.8658686 .1077192 bf2 | .0000525 .0001469 0.36 0.721 -.0002354 .0003404 bf4m | .1263528 .2275811 0.56 0.579 -.3196979 .5724036 bf5m | -.0049342 .0041169 -1.20 0.231 -.0130031 .0031348 bf7m | -.0004133 .0008454 -0.49 0.625 -.0020703 .0012437 bf8 | .0001156 .0000755 1.53 0.125 -.0000323 .0002635 bf15m | 0 (omitted) bf17 | 0 (omitted) bf20 | -.0078983 .0366468 -0.22 0.829 -.0797248 .0639282 bf22 | .000158 .0001863 0.85 0.396 -.0002071 .0005231 bf29 | 9.34e-06 .0000425 0.22 0.826 -.000074 .0000927 bf30 | -.0000869 .0004483 -0.19 0.846 -.0009655 .0007917 bf40 | -.2779981 .1983152 -1.40 0.161 -.6666887 .1106924 deaw3 | -.0223131 .2253092 -0.10 0.921 -.4639109 .4192848 dvcew3 | 1.571998 1.037736 1.51 0.130 -.4619271 3.605923 sepaw3 | -1.894764 1.527486 -1.24 0.215 -4.888582 1.099055 accdw3 | -.2729555 .6926052 -0.39 0.694 -1.630437 1.084526 movew3 | 0 (omitted) illw3 | -.1949663 .2468671 -0.79 0.430 -.6788169 .2888842 shfamw3 | -.0082258 .0094908 -0.87 0.386 -.0268274 .0103758 shhlw3 | .0062899 .0080613 0.78 0.435 -.00951 .0220898 shjobw3 | -.0009012 .0093159 -0.10 0.923 -.0191601 .0173576 shrelaw3 | -.0126452 .0092607 -1.37 0.172 -.0307958 .0055054 suprtw3 | -.004099 .0105306 -0.39 0.697 -.0247385 .0165405 suchrw3 | -.0078922 .0065901 -1.20 0.231 -.0208085 .0050241 havmilsq | -4.43e-06 .000039 -0.11 0.909 -.0000808 .000072 _cons | -32.88256 3180.671 -0.01 0.992 -6266.884 6201.119 ------------------------------------------------------------------------------ Note: 5 failures and 0 successes completely determined. Logistic model for HP2pbfhm -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 22 9 | 31 - | 24 222 | 246 -----------+--------------------------+----------- Total | 46 231 | 277 Classified + if predicted Pr(D) >= .5 True D defined as HP2pbfhm != 0 -------------------------------------------------- Sensitivity Pr( +| D) 47.83% Specificity Pr( -|~D) 96.10% Positive predictive value Pr( D| +) 70.97% Negative predictive value Pr(~D| -) 90.24% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 3.90% False - rate for true D Pr( -| D) 52.17% False + rate for classified + Pr(~D| +) 29.03% False - rate for classified - Pr( D| -) 9.76% -------------------------------------------------- Correctly classified 88.09% -------------------------------------------------- Logistic model for HP2pbfhm, goodness-of-fit test number of observations = 277 number of covariate patterns = 277 Pearson chi2(231) = 439.38 Prob > chi2 = 0.0000 Measures of Fit for logistic of HP2pbfhm Log-Lik Intercept Only: -124.537 Log-Lik Full Model: -80.453 D(221): 160.905 LR(45): 88.169 Prob > LR: 0.000 McFadden's R2: 0.354 McFadden's Adj R2: -0.096 Maximum Likelihood R2: 0.273 Cragg & Uhler's R2: 0.460 McKelvey and Zavoina's R2: 0.796 Efron's R2: 0.384 Variance of y*: 16.128 Variance of error: 3.290 Count R2: 0.881 Adj Count R2: 0.283 AIC: 0.985 AIC*n: 272.905 BIC: -1082.003 BIC': 164.912 Full main model for HP2sxlife for wave= 3 chunk 2 H1 test:Gender= 1 model Wave = 3 for HP2pbfhm i.educ _Ieduc_1-8 (naturally coded; _Ieduc_1 omitted) note: _Ieduc_7 != 0 predicts failure perfectly _Ieduc_7 dropped and 4 obs not used note: occ6w3 != 0 predicts failure perfectly occ6w3 dropped and 4 obs not used note: bf15m != 0 predicts failure perfectly bf15m dropped and 20 obs not used note: bf29 != 0 predicts failure perfectly bf29 dropped and 8 obs not used note: _Ieduc_8 omitted because of collinearity note: occ8w3 omitted because of collinearity note: marrw36 omitted because of collinearity note: bf17 omitted because of collinearity Logistic regression Number of obs = 304 LR chi2(47) = 153.48 Prob > chi2 = 0.0000 Log likelihood = -86.082561 Pseudo R2 = 0.4713 ------------------------------------------------------------------------------ HP2sxlife | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .1069256 .0319906 3.34 0.001 .0442252 .169626 _Ieduc_2 | -.7455102 2.711615 -0.27 0.783 -6.060177 4.569157 _Ieduc_3 | -1.187035 2.60622 -0.46 0.649 -6.295133 3.921063 _Ieduc_4 | -2.546669 2.819292 -0.90 0.366 -8.072379 2.979041 _Ieduc_5 | -.9083698 2.596245 -0.35 0.726 -5.996916 4.180177 _Ieduc_6 | -.821989 2.54798 -0.32 0.747 -5.815938 4.17196 _Ieduc_7 | 0 (omitted) _Ieduc_8 | 0 (omitted) occ1w3 | -13.83588 1847.337 -0.01 0.994 -3634.551 3606.879 occ2w3 | -14.1177 1847.337 -0.01 0.994 -3634.833 3606.597 occ3w3 | -15.12911 1847.338 -0.01 0.993 -3635.845 3605.586 occ4w3 | -14.04877 1847.338 -0.01 0.994 -3634.764 3606.666 occ5w3 | -13.39243 1847.338 -0.01 0.994 -3634.108 3607.323 occ6w3 | 0 (omitted) occ7w3 | -14.25779 1847.337 -0.01 0.994 -3634.973 3606.457 occ8w3 | 0 (omitted) marrw31 | 1.917986 1.336919 1.43 0.151 -.7023282 4.538299 marrw32 | -.8798595 1.841469 -0.48 0.633 -4.489073 2.729354 marrw33 | .8814069 1.275273 0.69 0.489 -1.618082 3.380896 marrw35 | 1.398611 1.615954 0.87 0.387 -1.768602 4.565823 marrw36 | 0 (omitted) inc1w3 | 16.59262 1847.337 0.01 0.993 -3604.122 3637.307 inc2w3 | 16.41393 1847.337 0.01 0.993 -3604.3 3637.128 inc3w3 | 14.9931 1847.337 0.01 0.994 -3605.721 3635.708 inc4w3 | 13.76529 1847.339 0.01 0.994 -3606.952 3634.482 radhlw3 | .0155883 .0090158 1.73 0.084 -.0020824 .0332591 havmil | .0032884 .0119659 0.27 0.783 -.0201643 .0267412 avgcumdosew3 | .0366781 .0541231 0.68 0.498 -.0694012 .1427574 bf1 | .0224773 .0438725 0.51 0.608 -.0635113 .108466 bf4 | -.3119601 .2453847 -1.27 0.204 -.7929052 .168985 bf2 | .0000786 .0001745 0.45 0.652 -.0002634 .0004207 bf4m | .0103662 .2174828 0.05 0.962 -.4158923 .4366247 bf5m | .0028825 .0019867 1.45 0.147 -.0010113 .0067763 bf7m | .0013372 .0006507 2.05 0.040 .0000618 .0026126 bf8 | -.0000698 .0000479 -1.46 0.145 -.0001638 .0000241 bf15m | 0 (omitted) bf17 | 0 (omitted) bf20 | -.0288329 .0347084 -0.83 0.406 -.09686 .0391943 bf22 | -.0000907 .0001888 -0.48 0.631 -.0004608 .0002793 bf29 | 0 (omitted) bf30 | -5.44e-06 .0004196 -0.01 0.990 -.0008279 .0008171 bf40 | .3549975 .2522025 1.41 0.159 -.1393104 .8493054 deaw3 | -.1446966 .2515866 -0.58 0.565 -.6377974 .3484041 dvcew3 | .2312151 1.685819 0.14 0.891 -3.07293 3.535361 sepaw3 | 1.563211 1.973158 0.79 0.428 -2.304108 5.430529 accdw3 | -1.029126 .9986452 -1.03 0.303 -2.986435 .9281827 movew3 | -.3161441 .7920977 -0.40 0.690 -1.868627 1.236339 illw3 | .2509498 .2730406 0.92 0.358 -.2841998 .7860995 shfamw3 | -.0049114 .0092237 -0.53 0.594 -.0229895 .0131668 shhlw3 | -.0135671 .0078785 -1.72 0.085 -.0290087 .0018746 shjobw3 | .0090088 .0079953 1.13 0.260 -.0066617 .0246793 shrelaw3 | -.0052844 .0083104 -0.64 0.525 -.0215726 .0110037 suprtw3 | .0083949 .0090554 0.93 0.354 -.0093533 .0261431 suchrw3 | -.0115343 .0079215 -1.46 0.145 -.0270603 .0039916 havmilsq | -.0000122 .0000253 -0.48 0.630 -.0000618 .0000374 _cons | -6.912277 3.93482 -1.76 0.079 -14.62438 .7998281 ------------------------------------------------------------------------------ Note: 4 failures and 0 successes completely determined. Logistic model for HP2sxlife -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 44 14 | 58 - | 25 221 | 246 -----------+--------------------------+----------- Total | 69 235 | 304 Classified + if predicted Pr(D) >= .5 True D defined as HP2sxlife != 0 -------------------------------------------------- Sensitivity Pr( +| D) 63.77% Specificity Pr( -|~D) 94.04% Positive predictive value Pr( D| +) 75.86% Negative predictive value Pr(~D| -) 89.84% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 5.96% False - rate for true D Pr( -| D) 36.23% False + rate for classified + Pr(~D| +) 24.14% False - rate for classified - Pr( D| -) 10.16% -------------------------------------------------- Correctly classified 87.17% -------------------------------------------------- Logistic model for HP2sxlife, goodness-of-fit test number of observations = 304 number of covariate patterns = 304 Pearson chi2(256) = 202.32 Prob > chi2 = 0.9943 Measures of Fit for logistic of HP2sxlife Log-Lik Intercept Only: -162.820 Log-Lik Full Model: -86.083 D(248): 172.165 LR(47): 153.476 Prob > LR: 0.000 McFadden's R2: 0.471 McFadden's Adj R2: 0.127 Maximum Likelihood R2: 0.396 Cragg & Uhler's R2: 0.603 McKelvey and Zavoina's R2: 0.800 Efron's R2: 0.484 Variance of y*: 16.474 Variance of error: 3.290 Count R2: 0.872 Adj Count R2: 0.435 AIC: 0.935 AIC*n: 284.165 BIC: -1245.658 BIC': 115.224 Full main model for HP2sxlife for wave= 3 chunk 2 H1 test:Gender= 2 model Wave = 3 for HP2sxlife i.educ _Ieduc_1-8 (naturally coded; _Ieduc_1 omitted) note: occ8w3 != 0 predicts failure perfectly occ8w3 dropped and 1 obs not used note: bf15m != 0 predicts failure perfectly bf15m dropped and 12 obs not used note: bf29 != 0 predicts success perfectly bf29 dropped and 4 obs not used note: _Ieduc_8 omitted because of collinearity note: bf17 omitted because of collinearity Logistic regression Number of obs = 345 LR chi2(50) = 168.03 Prob > chi2 = 0.0000 Log likelihood = -114.00457 Pseudo R2 = 0.4243 ------------------------------------------------------------------------------ HP2sxlife | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0813848 .0244496 3.33 0.001 .0334644 .1293053 _Ieduc_2 | -12.79022 653.1326 -0.02 0.984 -1292.907 1267.326 _Ieduc_3 | -11.94607 653.1326 -0.02 0.985 -1292.062 1268.17 _Ieduc_4 | -11.36768 653.1328 -0.02 0.986 -1291.484 1268.749 _Ieduc_5 | -12.54328 653.1327 -0.02 0.985 -1292.66 1267.573 _Ieduc_6 | -11.93918 653.1326 -0.02 0.985 -1292.055 1268.177 _Ieduc_7 | -12.87216 653.1524 -0.02 0.984 -1293.027 1267.283 _Ieduc_8 | 0 (omitted) occ1w3 | -2.703036 2.21975 -1.22 0.223 -7.053665 1.647593 occ2w3 | -2.165029 2.323461 -0.93 0.351 -6.718929 2.388871 occ3w3 | -2.030908 2.234964 -0.91 0.364 -6.411358 2.349542 occ4w3 | -1.625969 2.528132 -0.64 0.520 -6.581016 3.329078 occ5w3 | .7269315 2.820396 0.26 0.797 -4.800943 6.254806 occ6w3 | -.7633882 2.518786 -0.30 0.762 -5.700118 4.173342 occ7w3 | -1.433838 2.203631 -0.65 0.515 -5.752876 2.8852 occ8w3 | 0 (omitted) marrw31 | .3247443 1.774101 0.18 0.855 -3.152431 3.801919 marrw32 | .8501767 2.207491 0.39 0.700 -3.476427 5.17678 marrw33 | 1.557872 1.575773 0.99 0.323 -1.530585 4.646329 marrw35 | -.4253418 1.619183 -0.26 0.793 -3.598882 2.748198 marrw36 | 1.703593 1.601915 1.06 0.288 -1.436102 4.843288 inc1w3 | 1.766812 2.253827 0.78 0.433 -2.650608 6.184231 inc2w3 | 2.269344 2.224897 1.02 0.308 -2.091374 6.630061 inc3w3 | .9292343 2.201873 0.42 0.673 -3.386357 5.244826 inc4w3 | 1.449624 2.775037 0.52 0.601 -3.989349 6.888597 radhlw3 | .0277216 .0091569 3.03 0.002 .0097745 .0456688 havmil | .0021336 .0032179 0.66 0.507 -.0041733 .0084405 avgcumdosew3 | .1969924 .1165031 1.69 0.091 -.0313496 .4253343 bf1 | .0285984 .0382244 0.75 0.454 -.04632 .1035168 bf4 | -.4015139 .2038932 -1.97 0.049 -.8011373 -.0018905 bf2 | -.0001649 .0001225 -1.35 0.178 -.0004051 .0000753 bf4m | .3523301 .1864609 1.89 0.059 -.0131266 .7177867 bf5m | -.0026053 .001955 -1.33 0.183 -.006437 .0012264 bf7m | -.0000741 .0006237 -0.12 0.905 -.0012966 .0011483 bf8 | -5.22e-06 .0000423 -0.12 0.902 -.0000881 .0000777 bf15m | 0 (omitted) bf17 | 0 (omitted) bf20 | -.0120216 .031995 -0.38 0.707 -.0747307 .0506874 bf22 | -.0001004 .0001357 -0.74 0.459 -.0003664 .0001655 bf29 | 0 (omitted) bf30 | -.0002441 .0003438 -0.71 0.478 -.0009179 .0004298 bf40 | .095062 .1371931 0.69 0.488 -.1738314 .3639555 deaw3 | .0760781 .1918427 0.40 0.692 -.2999267 .4520829 dvcew3 | 1.127371 .952705 1.18 0.237 -.7398962 2.994639 sepaw3 | .5833047 .936842 0.62 0.534 -1.252872 2.419481 accdw3 | -.5118992 .5859911 -0.87 0.382 -1.660421 .6366223 movew3 | -.6063637 1.823477 -0.33 0.739 -4.180313 2.967586 illw3 | .1168429 .1761008 0.66 0.507 -.2283082 .4619941 shfamw3 | .0084815 .007536 1.13 0.260 -.0062888 .0232518 shhlw3 | .0066923 .0066985 1.00 0.318 -.0064365 .0198212 shjobw3 | -.0046191 .0070704 -0.65 0.514 -.0184767 .0092386 shrelaw3 | -.0123617 .0074084 -1.67 0.095 -.0268819 .0021585 suprtw3 | -.0091554 .0078461 -1.17 0.243 -.0245335 .0062227 suchrw3 | -.0034248 .0055225 -0.62 0.535 -.0142486 .0073991 havmilsq | -2.54e-06 2.55e-06 -1.00 0.319 -7.52e-06 2.45e-06 _cons | 1.83356 653.1407 0.00 0.998 -1278.299 1281.966 ------------------------------------------------------------------------------ Note: 1 failure and 0 successes completely determined. Logistic model for HP2sxlife -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 60 12 | 72 - | 30 243 | 273 -----------+--------------------------+----------- Total | 90 255 | 345 Classified + if predicted Pr(D) >= .5 True D defined as HP2sxlife != 0 -------------------------------------------------- Sensitivity Pr( +| D) 66.67% Specificity Pr( -|~D) 95.29% Positive predictive value Pr( D| +) 83.33% Negative predictive value Pr(~D| -) 89.01% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 4.71% False - rate for true D Pr( -| D) 33.33% False + rate for classified + Pr(~D| +) 16.67% False - rate for classified - Pr( D| -) 10.99% -------------------------------------------------- Correctly classified 87.83% -------------------------------------------------- Logistic model for HP2sxlife, goodness-of-fit test number of observations = 345 number of covariate patterns = 345 Pearson chi2(294) = 343.22 Prob > chi2 = 0.0254 Measures of Fit for logistic of HP2sxlife Log-Lik Intercept Only: -198.018 Log-Lik Full Model: -114.005 D(289): 228.009 LR(50): 168.026 Prob > LR: 0.000 McFadden's R2: 0.424 McFadden's Adj R2: 0.141 Maximum Likelihood R2: 0.386 Cragg & Uhler's R2: 0.565 McKelvey and Zavoina's R2: 0.693 Efron's R2: 0.483 Variance of y*: 10.715 Variance of error: 3.290 Count R2: 0.878 Adj Count R2: 0.533 AIC: 0.986 AIC*n: 340.009 BIC: -1460.775 BIC': 124.151 Full main model for HP2inthob for wave= 3 chunk 2 H1 test:Gender= 1 model Wave = 3 for HP2sxlife i.educ _Ieduc_1-8 (naturally coded; _Ieduc_1 omitted) note: _Ieduc_4 != 0 predicts failure perfectly _Ieduc_4 dropped and 14 obs not used note: _Ieduc_7 != 0 predicts failure perfectly _Ieduc_7 dropped and 4 obs not used note: _Ieduc_8 != 0 predicts failure perfectly _Ieduc_8 dropped and 2 obs not used note: occ5w3 != 0 predicts failure perfectly occ5w3 dropped and 15 obs not used note: occ6w3 != 0 predicts failure perfectly occ6w3 dropped and 4 obs not used note: bf15m != 0 predicts failure perfectly bf15m dropped and 18 obs not used note: bf29 != 0 predicts failure perfectly bf29 dropped and 7 obs not used note: _Ieduc_6 omitted because of collinearity note: occ8w3 omitted because of collinearity note: marrw36 omitted because of collinearity note: bf17 omitted because of collinearity convergence not achieved Logistic regression Number of obs = 276 LR chi2(42) = 117.91 Prob > chi2 = 0.0000 Log likelihood = -51.649162 Pseudo R2 = 0.5330 ------------------------------------------------------------------------------ HP2inthob | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0817005 .0490304 1.67 0.096 -.0143972 .1777983 _Ieduc_2 | -1.531634 1.790651 -0.86 0.392 -5.041245 1.977977 _Ieduc_3 | -1.560462 .8580327 -1.82 0.069 -3.242176 .1212508 _Ieduc_4 | 0 (omitted) _Ieduc_5 | -.5489736 .8124194 -0.68 0.499 -2.141286 1.043339 _Ieduc_6 | 0 (omitted) _Ieduc_7 | 0 (omitted) _Ieduc_8 | 0 (omitted) occ1w3 | -16.51737 2.253408 -7.33 0.000 -20.93397 -12.10077 occ2w3 | -19.33038 2.062721 -9.37 0.000 -23.37324 -15.28752 occ3w3 | -17.4588 2.676679 -6.52 0.000 -22.70499 -12.2126 occ4w3 | -16.4147 2.207406 -7.44 0.000 -20.74113 -12.08826 occ5w3 | 0 (omitted) occ6w3 | 0 (omitted) occ7w3 | -16.18451 2.199404 -7.36 0.000 -20.49527 -11.87376 occ8w3 | 0 (omitted) marrw31 | .8557338 1.989444 0.43 0.667 -3.043506 4.754973 marrw32 | 1.067638 2.133137 0.50 0.617 -3.113233 5.248509 marrw33 | -.0597494 1.809944 -0.03 0.974 -3.607174 3.487675 marrw35 | 4.178796 2.178555 1.92 0.055 -.091092 8.448685 marrw36 | 0 (omitted) inc1w3 | 14.99624 2.039372 7.35 0.000 10.99915 18.99334 inc2w3 | 15.54638 1.847372 8.42 0.000 11.92559 19.16716 inc3w3 | 16.08957 1.659414 9.70 0.000 12.83718 19.34196 inc4w3 | 20.06926 . . . . . radhlw3 | .0608448 .0162567 3.74 0.000 .0289822 .0927074 havmil | .004278 .0106932 0.40 0.689 -.0166802 .0252362 avgcumdosew3 | -.3594081 .1656258 -2.17 0.030 -.6840288 -.0347874 bf1 | -1.832947 .1402107 -13.07 0.000 -2.107755 -1.558139 bf4 | -.1459909 .3386475 -0.43 0.666 -.8097278 .5177459 bf2 | -.0007134 .0002919 -2.44 0.015 -.0012855 -.0001412 bf4m | -.0648788 .3169386 -0.20 0.838 -.6860671 .5563094 bf5m | -.0059221 .0033107 -1.79 0.074 -.0124109 .0005667 bf7m | -.00068 .0010134 -0.67 0.502 -.0026661 .0013062 bf8 | .0000248 .0000707 0.35 0.726 -.0001137 .0001633 bf15m | 0 (omitted) bf17 | 0 (omitted) bf20 | 1.839453 .1331884 13.81 0.000 1.578408 2.100497 bf22 | .000278 .0003035 0.92 0.360 -.0003168 .0008728 bf29 | 0 (omitted) bf30 | .0006467 .000603 1.07 0.284 -.0005352 .0018286 bf40 | .2996033 .3950361 0.76 0.448 -.4746533 1.07386 deaw3 | -.6086988 .5212369 -1.17 0.243 -1.630304 .4129068 dvcew3 | -.2319255 1.621511 -0.14 0.886 -3.410029 2.946178 sepaw3 | -1.758194 2.087814 -0.84 0.400 -5.850234 2.333846 accdw3 | .9189185 1.049895 0.88 0.381 -1.138839 2.976676 movew3 | -1.391188 1.335043 -1.04 0.297 -4.007824 1.225448 illw3 | -.3817302 .3999312 -0.95 0.340 -1.165581 .4021205 shfamw3 | .0654585 .0176224 3.71 0.000 .0309192 .0999978 shhlw3 | -.0105181 .0103515 -1.02 0.310 -.0308067 .0097705 shjobw3 | -.0144707 .0115767 -1.25 0.211 -.0371606 .0082192 shrelaw3 | -.0392022 .0137786 -2.85 0.004 -.0662077 -.0121967 suprtw3 | .0070974 .0130297 0.54 0.586 -.0184403 .0326352 suchrw3 | -.00232 .0110986 -0.21 0.834 -.0240728 .0194327 havmilsq | -7.67e-06 .0000192 -0.40 0.690 -.0000453 .00003 _cons | -80.28913 . . . . . ------------------------------------------------------------------------------ Note: 32 failures and 0 successes completely determined. Warning: convergence not achieved Logistic model for HP2inthob -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 23 7 | 30 - | 15 231 | 246 -----------+--------------------------+----------- Total | 38 238 | 276 Classified + if predicted Pr(D) >= .5 True D defined as HP2inthob != 0 -------------------------------------------------- Sensitivity Pr( +| D) 60.53% Specificity Pr( -|~D) 97.06% Positive predictive value Pr( D| +) 76.67% Negative predictive value Pr(~D| -) 93.90% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 2.94% False - rate for true D Pr( -| D) 39.47% False + rate for classified + Pr(~D| +) 23.33% False - rate for classified - Pr( D| -) 6.10% -------------------------------------------------- Correctly classified 92.03% -------------------------------------------------- Logistic model for HP2inthob, goodness-of-fit test number of observations = 276 number of covariate patterns = 276 Pearson chi2(231) = 123.26 Prob > chi2 = 1.0000 Measures of Fit for logistic of HP2inthob Log-Lik Intercept Only: -110.602 Log-Lik Full Model: -51.649 D(220): 103.298 LR(42): 117.906 Prob > LR: 0.000 McFadden's R2: 0.533 McFadden's Adj R2: 0.027 Maximum Likelihood R2: 0.348 Cragg & Uhler's R2: 0.631 McKelvey and Zavoina's R2: 0.982 Efron's R2: 0.500 Variance of y*: 180.636 Variance of error: 3.290 Count R2: 0.920 Adj Count R2: 0.421 AIC: 0.780 AIC*n: 215.298 BIC: -1133.190 BIC': 118.151 Full main model for HP2inthob for wave= 3 chunk 2 H1 test:Gender= 2 model Wave = 3 for HP2inthob i.educ _Ieduc_1-8 (naturally coded; _Ieduc_1 omitted) note: occ4w3 != 0 predicts failure perfectly occ4w3 dropped and 8 obs not used note: occ5w3 != 0 predicts failure perfectly occ5w3 dropped and 5 obs not used note: occ8w3 != 0 predicts failure perfectly occ8w3 dropped and 1 obs not used note: bf15m != 0 predicts failure perfectly bf15m dropped and 11 obs not used note: _Ieduc_8 omitted because of collinearity note: bf17 omitted because of collinearity Logistic regression Number of obs = 337 LR chi2(49) = 118.21 Prob > chi2 = 0.0000 Log likelihood = -107.57156 Pseudo R2 = 0.3546 ------------------------------------------------------------------------------ HP2inthob | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0683881 .0247447 2.76 0.006 .0198893 .1168869 _Ieduc_2 | -13.79024 962.4068 -0.01 0.989 -1900.073 1872.492 _Ieduc_3 | -12.92792 962.4068 -0.01 0.989 -1899.211 1873.355 _Ieduc_4 | -12.05387 962.4069 -0.01 0.990 -1898.337 1874.229 _Ieduc_5 | -12.19345 962.407 -0.01 0.990 -1898.476 1874.09 _Ieduc_6 | -13.09489 962.4068 -0.01 0.989 -1899.378 1873.188 _Ieduc_7 | -13.1998 962.4102 -0.01 0.989 -1899.489 1873.089 _Ieduc_8 | 0 (omitted) occ1w3 | -1.2723 3.511631 -0.36 0.717 -8.154969 5.61037 occ2w3 | -2.590551 3.713618 -0.70 0.485 -9.869108 4.688006 occ3w3 | -.8635752 3.536644 -0.24 0.807 -7.79527 6.06812 occ4w3 | 0 (omitted) occ5w3 | 0 (omitted) occ6w3 | -.2036246 3.739879 -0.05 0.957 -7.533652 7.126403 occ7w3 | -.4066434 3.50728 -0.12 0.908 -7.280786 6.467499 occ8w3 | 0 (omitted) marrw31 | -2.820802 1.835568 -1.54 0.124 -6.418449 .776846 marrw32 | -2.10882 2.397053 -0.88 0.379 -6.806958 2.589318 marrw33 | -2.047151 1.625637 -1.26 0.208 -5.233341 1.13904 marrw35 | -2.933509 1.682447 -1.74 0.081 -6.231043 .3640262 marrw36 | -2.100943 1.718745 -1.22 0.222 -5.469621 1.267736 inc1w3 | 1.771469 3.538577 0.50 0.617 -5.164014 8.706952 inc2w3 | 1.229926 3.52319 0.35 0.727 -5.675399 8.13525 inc3w3 | 1.602207 3.508288 0.46 0.648 -5.273911 8.478326 inc4w3 | 2.650063 3.832399 0.69 0.489 -4.861301 10.16143 radhlw3 | .0254128 .010363 2.45 0.014 .0051018 .0457239 havmil | .0052121 .0043654 1.19 0.232 -.003344 .0137682 avgcumdosew3 | .0592875 .0898505 0.66 0.509 -.1168163 .2353913 bf1 | -.0386178 .0465636 -0.83 0.407 -.1298807 .0526452 bf4 | -.3299735 .2318908 -1.42 0.155 -.7844712 .1245242 bf2 | 5.14e-06 .0001261 0.04 0.967 -.000242 .0002523 bf4m | .24058 .2177227 1.10 0.269 -.1861487 .6673088 bf5m | -.0019924 .0019912 -1.00 0.317 -.0058951 .0019104 bf7m | -.000918 .0006896 -1.33 0.183 -.0022697 .0004336 bf8 | 6.91e-06 .0000428 0.16 0.872 -.0000771 .0000909 bf15m | 0 (omitted) bf17 | 0 (omitted) bf20 | .0290415 .0410365 0.71 0.479 -.0513885 .1094715 bf22 | .000145 .000139 1.04 0.297 -.0001275 .0004175 bf29 | .0000291 .0000389 0.75 0.455 -.0000472 .0001054 bf30 | .0005863 .0003477 1.69 0.092 -.0000953 .0012679 bf40 | -.1903404 .1540477 -1.24 0.217 -.4922683 .1115876 deaw3 | -.0727208 .201017 -0.36 0.718 -.4667069 .3212652 dvcew3 | -.3675995 .8921998 -0.41 0.680 -2.116279 1.38108 sepaw3 | 1.146748 .9391994 1.22 0.222 -.6940491 2.987545 accdw3 | -.0400125 .5697822 -0.07 0.944 -1.156765 1.07674 movew3 | .1242816 1.400684 0.09 0.929 -2.621008 2.869572 illw3 | .0326786 .1772251 0.18 0.854 -.3146761 .3800333 shfamw3 | -.0089451 .0081686 -1.10 0.273 -.0249552 .0070651 shhlw3 | -.0019331 .0067351 -0.29 0.774 -.0151336 .0112673 shjobw3 | .0022608 .0074164 0.30 0.760 -.012275 .0167966 shrelaw3 | .0045217 .0078937 0.57 0.567 -.0109497 .0199931 suprtw3 | -.0034378 .0085075 -0.40 0.686 -.0201123 .0132366 suchrw3 | -.0106093 .0056039 -1.89 0.058 -.0215928 .0003741 havmilsq | -4.33e-06 6.65e-06 -0.65 0.515 -.0000174 8.70e-06 _cons | 7.330327 962.4125 0.01 0.994 -1878.964 1893.624 ------------------------------------------------------------------------------ Note: 1 failure and 0 successes completely determined. Logistic model for HP2inthob -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 33 12 | 45 - | 33 259 | 292 -----------+--------------------------+----------- Total | 66 271 | 337 Classified + if predicted Pr(D) >= .5 True D defined as HP2inthob != 0 -------------------------------------------------- Sensitivity Pr( +| D) 50.00% Specificity Pr( -|~D) 95.57% Positive predictive value Pr( D| +) 73.33% Negative predictive value Pr(~D| -) 88.70% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 4.43% False - rate for true D Pr( -| D) 50.00% False + rate for classified + Pr(~D| +) 26.67% False - rate for classified - Pr( D| -) 11.30% -------------------------------------------------- Correctly classified 86.65% -------------------------------------------------- Logistic model for HP2inthob, goodness-of-fit test number of observations = 337 number of covariate patterns = 337 Pearson chi2(287) = 317.53 Prob > chi2 = 0.1040 Measures of Fit for logistic of HP2inthob Log-Lik Intercept Only: -166.677 Log-Lik Full Model: -107.572 D(281): 215.143 LR(49): 118.210 Prob > LR: 0.000 McFadden's R2: 0.355 McFadden's Adj R2: 0.019 Maximum Likelihood R2: 0.296 Cragg & Uhler's R2: 0.471 McKelvey and Zavoina's R2: 0.678 Efron's R2: 0.373 Variance of y*: 10.209 Variance of error: 3.290 Count R2: 0.866 Adj Count R2: 0.318 AIC: 0.971 AIC*n: 327.143 BIC: -1420.300 BIC': 166.974 Full main model for HP2vacatn for wave= 3 chunk 2 H1 test:Gender= 1 model Wave = 3 for HP2inthob i.educ _Ieduc_1-8 (naturally coded; _Ieduc_1 omitted) note: _Ieduc_7 != 0 predicts failure perfectly _Ieduc_7 dropped and 4 obs not used note: _Ieduc_8 != 0 predicts failure perfectly _Ieduc_8 dropped and 2 obs not used note: occ5w3 != 0 predicts failure perfectly occ5w3 dropped and 18 obs not used note: occ6w3 != 0 predicts failure perfectly occ6w3 dropped and 4 obs not used note: bf15m != 0 predicts failure perfectly bf15m dropped and 19 obs not used note: bf29 != 0 predicts failure perfectly bf29 dropped and 7 obs not used note: _Ieduc_6 omitted because of collinearity note: occ8w3 omitted because of collinearity note: marrw36 omitted because of collinearity note: bf17 omitted because of collinearity Logistic regression Number of obs = 286 LR chi2(45) = 130.35 Prob > chi2 = 0.0000 Log likelihood = -52.374274 Pseudo R2 = 0.5544 ------------------------------------------------------------------------------ HP2vacatn | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .1141267 .0450696 2.53 0.011 .025792 .2024615 _Ieduc_2 | 1.212945 1.630503 0.74 0.457 -1.982782 4.408672 _Ieduc_3 | -1.181748 .8345653 -1.42 0.157 -2.817465 .4539703 _Ieduc_4 | -.2703336 1.707405 -0.16 0.874 -3.616786 3.076119 _Ieduc_5 | .0781642 .821705 0.10 0.924 -1.532348 1.688676 _Ieduc_6 | 0 (omitted) _Ieduc_7 | 0 (omitted) _Ieduc_8 | 0 (omitted) occ1w3 | -13.38278 1622.421 -0.01 0.993 -3193.27 3166.504 occ2w3 | -12.82938 1622.421 -0.01 0.994 -3192.717 3167.058 occ3w3 | -12.16922 1622.422 -0.01 0.994 -3192.057 3167.719 occ4w3 | -9.847245 1622.421 -0.01 0.995 -3189.735 3170.04 occ5w3 | 0 (omitted) occ6w3 | 0 (omitted) occ7w3 | -10.21639 1622.421 -0.01 0.995 -3190.104 3169.671 occ8w3 | 0 (omitted) marrw31 | 2.471663 1.877772 1.32 0.188 -1.208702 6.152028 marrw32 | 3.882172 2.040109 1.90 0.057 -.116367 7.880711 marrw33 | .7861586 1.848468 0.43 0.671 -2.836772 4.409089 marrw35 | 5.481699 2.097529 2.61 0.009 1.370617 9.592781 marrw36 | 0 (omitted) inc1w3 | 12.51469 1622.421 0.01 0.994 -3167.373 3192.402 inc2w3 | 14.55722 1622.421 0.01 0.993 -3165.329 3194.444 inc3w3 | 14.35316 1622.421 0.01 0.993 -3165.533 3194.24 inc4w3 | 15.92527 1622.422 0.01 0.992 -3163.963 3195.813 radhlw3 | .0197321 .0147075 1.34 0.180 -.0090941 .0485583 havmil | .0234742 .0160068 1.47 0.143 -.0078985 .054847 avgcumdosew3 | .1032883 .1755565 0.59 0.556 -.240796 .4473726 bf1 | -.4769574 .3289335 -1.45 0.147 -1.121655 .1677405 bf4 | -.1442369 .2873042 -0.50 0.616 -.7073429 .4188691 bf2 | .0000186 .0002978 0.06 0.950 -.0005651 .0006023 bf4m | -.1956152 .2497206 -0.78 0.433 -.6850586 .2938281 bf5m | -.0071533 .0043294 -1.65 0.098 -.0156388 .0013321 bf7m | .0000185 .0010386 0.02 0.986 -.0020172 .0020542 bf8 | -.0000173 .0000922 -0.19 0.851 -.0001981 .0001635 bf15m | 0 (omitted) bf17 | 0 (omitted) bf20 | .4362509 .3222411 1.35 0.176 -.1953299 1.067832 bf22 | .0001349 .0003106 0.43 0.664 -.0004739 .0007437 bf29 | 0 (omitted) bf30 | -.0009931 .0006553 -1.52 0.130 -.0022775 .0002912 bf40 | .5185801 .3611964 1.44 0.151 -.1893518 1.226512 deaw3 | .2097501 .3135963 0.67 0.504 -.4048875 .8243876 dvcew3 | 2.012022 1.543197 1.30 0.192 -1.012588 5.036632 sepaw3 | -2.054184 1.443349 -1.42 0.155 -4.883097 .7747288 accdw3 | .2022258 1.25899 0.16 0.872 -2.265349 2.669801 movew3 | -4.177869 1.807922 -2.31 0.021 -7.721331 -.6344073 illw3 | -.4549089 .4293751 -1.06 0.289 -1.296469 .3866508 shfamw3 | .0141549 .0145895 0.97 0.332 -.0144399 .0427498 shhlw3 | .004885 .011315 0.43 0.666 -.0172919 .0270619 shjobw3 | -.0003857 .0112584 -0.03 0.973 -.0224516 .0216803 shrelaw3 | -.008433 .0120996 -0.70 0.486 -.0321477 .0152817 suprtw3 | .0050194 .0152005 0.33 0.741 -.0247729 .0348118 suchrw3 | -.0175411 .0097951 -1.79 0.073 -.0367391 .0016569 havmilsq | -.000046 .0000341 -1.35 0.178 -.0001129 .0000209 _cons | -25.70032 13.82795 -1.86 0.063 -52.80261 1.40197 ------------------------------------------------------------------------------ Note: 8 failures and 0 successes completely determined. Logistic model for HP2vacatn -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 24 6 | 30 - | 17 239 | 256 -----------+--------------------------+----------- Total | 41 245 | 286 Classified + if predicted Pr(D) >= .5 True D defined as HP2vacatn != 0 -------------------------------------------------- Sensitivity Pr( +| D) 58.54% Specificity Pr( -|~D) 97.55% Positive predictive value Pr( D| +) 80.00% Negative predictive value Pr(~D| -) 93.36% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 2.45% False - rate for true D Pr( -| D) 41.46% False + rate for classified + Pr(~D| +) 20.00% False - rate for classified - Pr( D| -) 6.64% -------------------------------------------------- Correctly classified 91.96% -------------------------------------------------- Logistic model for HP2vacatn, goodness-of-fit test number of observations = 286 number of covariate patterns = 286 Pearson chi2(240) = 528.62 Prob > chi2 = 0.0000 Measures of Fit for logistic of HP2vacatn Log-Lik Intercept Only: -117.549 Log-Lik Full Model: -52.374 D(230): 104.749 LR(45): 130.349 Prob > LR: 0.000 McFadden's R2: 0.554 McFadden's Adj R2: 0.078 Maximum Likelihood R2: 0.366 Cragg & Uhler's R2: 0.653 McKelvey and Zavoina's R2: 0.907 Efron's R2: 0.558 Variance of y*: 35.214 Variance of error: 3.290 Count R2: 0.920 Adj Count R2: 0.439 AIC: 0.758 AIC*n: 216.749 BIC: -1196.130 BIC': 124.170 Full main model for HP2vacatn for wave= 3 chunk 2 H1 test:Gender= 2 model Wave = 3 for HP2vacatn i.educ _Ieduc_1-8 (naturally coded; _Ieduc_1 omitted) note: occ4w3 != 0 predicts failure perfectly occ4w3 dropped and 8 obs not used note: occ5w3 != 0 predicts failure perfectly occ5w3 dropped and 5 obs not used note: occ8w3 != 0 predicts failure perfectly occ8w3 dropped and 1 obs not used note: marrw32 != 0 predicts failure perfectly marrw32 dropped and 8 obs not used note: bf15m != 0 predicts failure perfectly bf15m dropped and 11 obs not used note: _Ieduc_8 omitted because of collinearity note: bf17 omitted because of collinearity Logistic regression Number of obs = 329 LR chi2(48) = 107.68 Prob > chi2 = 0.0000 Log likelihood = -106.83646 Pseudo R2 = 0.3351 ------------------------------------------------------------------------------ HP2vacatn | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0746889 .02598 2.87 0.004 .0237689 .1256088 _Ieduc_2 | -16.28929 1372.198 -0.01 0.991 -2705.747 2673.169 _Ieduc_3 | -16.27345 1372.198 -0.01 0.991 -2705.731 2673.185 _Ieduc_4 | -13.92789 1372.198 -0.01 0.992 -2703.386 2675.53 _Ieduc_5 | -15.70958 1372.198 -0.01 0.991 -2705.168 2673.749 _Ieduc_6 | -15.75581 1372.198 -0.01 0.991 -2705.214 2673.702 _Ieduc_7 | -16.71287 1372.201 -0.01 0.990 -2706.178 2672.752 _Ieduc_8 | 0 (omitted) occ1w3 | -.9957645 2.610666 -0.38 0.703 -6.112575 4.121046 occ2w3 | .3619615 2.64581 0.14 0.891 -4.82373 5.547653 occ3w3 | -.2672451 2.620799 -0.10 0.919 -5.403917 4.869426 occ4w3 | 0 (omitted) occ5w3 | 0 (omitted) occ6w3 | .7685654 2.898646 0.27 0.791 -4.912676 6.449807 occ7w3 | -.2239682 2.598386 -0.09 0.931 -5.316711 4.868774 occ8w3 | 0 (omitted) marrw31 | -3.154883 1.936003 -1.63 0.103 -6.949379 .6396133 marrw32 | 0 (omitted) marrw33 | -1.629296 1.549774 -1.05 0.293 -4.666797 1.408206 marrw35 | -.9785838 1.561258 -0.63 0.531 -4.038593 2.081425 marrw36 | -.3736998 1.605068 -0.23 0.816 -3.519575 2.772176 inc1w3 | 1.236811 2.644541 0.47 0.640 -3.946394 6.420017 inc2w3 | .3422181 2.612526 0.13 0.896 -4.778239 5.462675 inc3w3 | .477638 2.599192 0.18 0.854 -4.616684 5.57196 inc4w3 | .3174794 3.090064 0.10 0.918 -5.738935 6.373894 radhlw3 | .0219342 .0098316 2.23 0.026 .0026647 .0412037 havmil | .0027203 .0039816 0.68 0.494 -.0050834 .010524 avgcumdosew3 | .1848178 .1050999 1.76 0.079 -.0211742 .3908099 bf1 | -.0115945 .040594 -0.29 0.775 -.0911573 .0679684 bf4 | -.0350483 .2076999 -0.17 0.866 -.4421326 .372036 bf2 | -.000079 .0001334 -0.59 0.554 -.0003406 .0001825 bf4m | -.0423071 .1886429 -0.22 0.823 -.4120403 .3274261 bf5m | .0008456 .0017602 0.48 0.631 -.0026043 .0042955 bf7m | -.0004985 .0006465 -0.77 0.441 -.0017657 .0007687 bf8 | -.0000606 .0000411 -1.48 0.140 -.0001411 .0000199 bf15m | 0 (omitted) bf17 | 0 (omitted) bf20 | .0059388 .0344891 0.17 0.863 -.0616586 .0735362 bf22 | .000128 .0001403 0.91 0.362 -.000147 .0004031 bf29 | .0000416 .0000406 1.02 0.305 -.000038 .0001212 bf30 | -.0003884 .0003734 -1.04 0.298 -.0011201 .0003434 bf40 | -.1764055 .1673262 -1.05 0.292 -.5043588 .1515477 deaw3 | .3451488 .2008083 1.72 0.086 -.0484283 .7387259 dvcew3 | -.5492396 .9270299 -0.59 0.554 -2.366185 1.267706 sepaw3 | 1.201095 .9159312 1.31 0.190 -.5940969 2.996287 accdw3 | .4787823 .5402897 0.89 0.376 -.5801659 1.537731 movew3 | -.0774101 1.282853 -0.06 0.952 -2.591756 2.436936 illw3 | -.2768508 .1854421 -1.49 0.135 -.6403106 .0866091 shfamw3 | -.0081517 .0081915 -1.00 0.320 -.0242067 .0079032 shhlw3 | .00718 .0069706 1.03 0.303 -.0064821 .0208421 shjobw3 | -.0010439 .0078157 -0.13 0.894 -.0163623 .0142745 shrelaw3 | -.0076648 .0080911 -0.95 0.343 -.0235231 .0081936 suprtw3 | .0076145 .0086776 0.88 0.380 -.0093932 .0246222 suchrw3 | -.0085201 .0055112 -1.55 0.122 -.0193219 .0022816 havmilsq | -2.61e-06 5.42e-06 -0.48 0.630 -.0000132 8.01e-06 _cons | 12.03817 1372.201 0.01 0.993 -2677.427 2701.503 ------------------------------------------------------------------------------ Note: 1 failure and 0 successes completely determined. Logistic model for HP2vacatn -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 27 10 | 37 - | 36 256 | 292 -----------+--------------------------+----------- Total | 63 266 | 329 Classified + if predicted Pr(D) >= .5 True D defined as HP2vacatn != 0 -------------------------------------------------- Sensitivity Pr( +| D) 42.86% Specificity Pr( -|~D) 96.24% Positive predictive value Pr( D| +) 72.97% Negative predictive value Pr(~D| -) 87.67% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 3.76% False - rate for true D Pr( -| D) 57.14% False + rate for classified + Pr(~D| +) 27.03% False - rate for classified - Pr( D| -) 12.33% -------------------------------------------------- Correctly classified 86.02% -------------------------------------------------- Logistic model for HP2vacatn, goodness-of-fit test number of observations = 329 number of covariate patterns = 329 Pearson chi2(280) = 296.45 Prob > chi2 = 0.2388 Measures of Fit for logistic of HP2vacatn Log-Lik Intercept Only: -160.675 Log-Lik Full Model: -106.836 D(273): 213.673 LR(48): 107.678 Prob > LR: 0.000 McFadden's R2: 0.335 McFadden's Adj R2: -0.013 Maximum Likelihood R2: 0.279 Cragg & Uhler's R2: 0.448 McKelvey and Zavoina's R2: 0.632 Efron's R2: 0.351 Variance of y*: 8.945 Variance of error: 3.290 Count R2: 0.860 Adj Count R2: 0.270 AIC: 0.990 AIC*n: 325.673 BIC: -1368.651 BIC': 170.533 182 . 183 . title4 "trimming male moderator models of dose and HP2work relationship in wa > ve 3 " ------------------------------------------------------------------------------- trimming male moderator models of dose and HP2work relationship in wave 3 ------------------------------------------------------------------------------- 184 . * male models 185 . forvalues j=3/3 { 2. di as input "Gender =1 HP2work model" 3. logit HP2work age bf8 illw`j' shjobw`j' havmilsq avgcumdosew`j' if > gender==1 4. estat class 5. estat gof 6. fitstat 7. } Gender =1 HP2work model Iteration 0: log likelihood = -172.87291 Iteration 1: log likelihood = -148.75217 Iteration 2: log likelihood = -147.11486 Iteration 3: log likelihood = -147.09824 Iteration 4: log likelihood = -147.09823 Logistic regression Number of obs = 340 LR chi2(6) = 51.55 Prob > chi2 = 0.0000 Log likelihood = -147.09823 Pseudo R2 = 0.1491 ------------------------------------------------------------------------------ HP2work | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0473544 .0138047 3.43 0.001 .0202977 .0744111 bf8 | -.0000527 .0000245 -2.15 0.032 -.0001007 -4.62e-06 illw3 | .7688236 .1582366 4.86 0.000 .4586855 1.078962 shjobw3 | .0115141 .0039727 2.90 0.004 .0037277 .0193004 havmilsq | -1.04e-06 1.75e-06 -0.59 0.552 -4.46e-06 2.38e-06 avgcumdosew3 | .0105615 .0472406 0.22 0.823 -.0820282 .1031513 _cons | -4.59543 .8195918 -5.61 0.000 -6.201801 -2.98906 ------------------------------------------------------------------------------ Logistic model for HP2work -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 17 6 | 23 - | 53 264 | 317 -----------+--------------------------+----------- Total | 70 270 | 340 Classified + if predicted Pr(D) >= .5 True D defined as HP2work != 0 -------------------------------------------------- Sensitivity Pr( +| D) 24.29% Specificity Pr( -|~D) 97.78% Positive predictive value Pr( D| +) 73.91% Negative predictive value Pr(~D| -) 83.28% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 2.22% False - rate for true D Pr( -| D) 75.71% False + rate for classified + Pr(~D| +) 26.09% False - rate for classified - Pr( D| -) 16.72% -------------------------------------------------- Correctly classified 82.65% -------------------------------------------------- Logistic model for HP2work, goodness-of-fit test number of observations = 340 number of covariate patterns = 324 Pearson chi2(317) = 321.28 Prob > chi2 = 0.4224 Measures of Fit for logit of HP2work Log-Lik Intercept Only: -172.873 Log-Lik Full Model: -147.098 D(333): 294.196 LR(6): 51.549 Prob > LR: 0.000 McFadden's R2: 0.149 McFadden's Adj R2: 0.109 Maximum Likelihood R2: 0.141 Cragg & Uhler's R2: 0.220 McKelvey and Zavoina's R2: 0.240 Efron's R2: 0.164 Variance of y*: 4.329 Variance of error: 3.290 Count R2: 0.826 Adj Count R2: 0.157 AIC: 0.906 AIC*n: 308.196 BIC: -1646.842 BIC': -16.576 186 . 187 . 188 . forvalues j=3/3 { 2. title4 "trimmed HP2work main effects models wave `j' for H1 part 2 with do > se ns" 3. 189 . } ------------------------------------------------------------------------------- trimmed HP2work main effects models wave 3 for H1 part 2 with dose ns ------------------------------------------------------------------------------- 190 . 191 . 192 . forvalues j=3/3 { 2. sw, pr(.1):logistic HP2work age bf8 illw`j' shjobw`j' havm > ilsq /// > avgcumdosew`j' if gender==1, coef nolog 3. estat class 4. estat gof 5. fitstat 6. } begin with full model p = 0.8231 >= 0.1000 removing avgcumdosew3 p = 0.5467 >= 0.1000 removing havmilsq Logistic regression Number of obs = 340 LR chi2(4) = 51.04 Prob > chi2 = 0.0000 Log likelihood = -147.35095 Pseudo R2 = 0.1476 ------------------------------------------------------------------------------ HP2work | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0477661 .0137843 3.47 0.001 .0207495 .0747828 bf8 | -.0000502 .0000239 -2.10 0.036 -.0000971 -3.37e-06 illw3 | .7513091 .1545821 4.86 0.000 .4483337 1.054285 shjobw3 | .011716 .0039653 2.95 0.003 .0039441 .0194878 _cons | -4.626957 .8195405 -5.65 0.000 -6.233227 -3.020687 ------------------------------------------------------------------------------ Logistic model for HP2work -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 16 7 | 23 - | 54 263 | 317 -----------+--------------------------+----------- Total | 70 270 | 340 Classified + if predicted Pr(D) >= .5 True D defined as HP2work != 0 -------------------------------------------------- Sensitivity Pr( +| D) 22.86% Specificity Pr( -|~D) 97.41% Positive predictive value Pr( D| +) 69.57% Negative predictive value Pr(~D| -) 82.97% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 2.59% False - rate for true D Pr( -| D) 77.14% False + rate for classified + Pr(~D| +) 30.43% False - rate for classified - Pr( D| -) 17.03% -------------------------------------------------- Correctly classified 82.06% -------------------------------------------------- Logistic model for HP2work, goodness-of-fit test number of observations = 340 number of covariate patterns = 272 Pearson chi2(267) = 278.53 Prob > chi2 = 0.3013 Measures of Fit for logistic of HP2work Log-Lik Intercept Only: -172.873 Log-Lik Full Model: -147.351 D(335): 294.702 LR(4): 51.044 Prob > LR: 0.000 McFadden's R2: 0.148 McFadden's Adj R2: 0.119 Maximum Likelihood R2: 0.139 Cragg & Uhler's R2: 0.218 McKelvey and Zavoina's R2: 0.237 Efron's R2: 0.162 Variance of y*: 4.312 Variance of error: 3.290 Count R2: 0.821 Adj Count R2: 0.129 AIC: 0.896 AIC*n: 304.702 BIC: -1657.995 BIC': -27.728 193 . 194 . forvalues j=3/3 { 2. sw, pr(.1):logistic HP2work age bf8 illw`j' shjobw`j' havm > ilsq /// > avgcumdosew`j' if gender==2, coef nolog 3. estat class 4. estat gof 5. fitstat 6. } begin with full model p = 0.9255 >= 0.1000 removing bf8 p = 0.8830 >= 0.1000 removing shjobw3 p = 0.5343 >= 0.1000 removing havmilsq p = 0.6152 >= 0.1000 removing illw3 p = 0.1142 >= 0.1000 removing avgcumdosew3 Logistic regression Number of obs = 362 LR chi2(1) = 42.20 Prob > chi2 = 0.0000 Log likelihood = -185.1665 Pseudo R2 = 0.1023 ------------------------------------------------------------------------------ HP2work | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .070115 .0116471 6.02 0.000 .047287 .0929429 _cons | -4.733748 .6446886 -7.34 0.000 -5.997314 -3.470181 ------------------------------------------------------------------------------ Logistic model for HP2work -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 20 14 | 34 - | 73 255 | 328 -----------+--------------------------+----------- Total | 93 269 | 362 Classified + if predicted Pr(D) >= .5 True D defined as HP2work != 0 -------------------------------------------------- Sensitivity Pr( +| D) 21.51% Specificity Pr( -|~D) 94.80% Positive predictive value Pr( D| +) 58.82% Negative predictive value Pr(~D| -) 77.74% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 5.20% False - rate for true D Pr( -| D) 78.49% False + rate for classified + Pr(~D| +) 41.18% False - rate for classified - Pr( D| -) 22.26% -------------------------------------------------- Correctly classified 75.97% -------------------------------------------------- Logistic model for HP2work, goodness-of-fit test number of observations = 362 number of covariate patterns = 49 Pearson chi2(47) = 58.24 Prob > chi2 = 0.1261 Measures of Fit for logistic of HP2work Log-Lik Intercept Only: -206.266 Log-Lik Full Model: -185.167 D(360): 370.333 LR(1): 42.199 Prob > LR: 0.000 McFadden's R2: 0.102 McFadden's Adj R2: 0.093 Maximum Likelihood R2: 0.110 Cragg & Uhler's R2: 0.162 McKelvey and Zavoina's R2: 0.174 Efron's R2: 0.127 Variance of y*: 3.982 Variance of error: 3.290 Count R2: 0.760 Adj Count R2: 0.065 AIC: 1.034 AIC*n: 374.333 BIC: -1750.659 BIC': -36.308 195 . 196 . 197 . scalar SigDoseWkFw3 = "no" 198 . 199 . 200 . des bf8 storage display value variable name type format label variable label ------------------------------------------------------------------------------- bf8 float %9.0g bf8 = max(0, radtlw3 - 40) * bf5m 201 . * male sign main effects in main effects model: 4- age, bf8, illw3 shjobw3 202 . * male main effects model avgcumdosew3 was not signif. 203 . * male hp2wk w3 mediators: age illw3 ageXillw3 bf8 204 . * female signif main effects in main effects model 205 . * female hp2wk w3 mediators: radhlw3 age ageXillw3 bf1 bf4 bf4m bf40 206 . * hypothnuym pt dv wave gender signif 207 . 208 . 209 . 210 . 211 . title4 " 1. Summary matrix construction Paid employment partition: first two > rows" ------------------------------------------------------------------------------- 1. Summary matrix construction Paid employment partition: first two rows ------------------------------------------------------------------------------- 212 . 213 . matrix define HP2wkMw3 = J(1,8, 0) 214 . matrix define HP2wkFw3 = J(1,8, 0) 215 . matrix colnames HP2wkMw3= hypnum ptnum wave gender medsig numMAsig numModsig > numMed 216 . matrix colnames HP2wkFw3= hypnum ptnum wave gender medsig numMAsig numModsig > numMed 217 . matrix rownames HP2wkMw3 = workM 218 . matrix rownames HP2wkFw3 = workF 219 . matrix define HP2wkMw3= (1, 2, 3, 1, 0 ,4, 0, 4 ) 220 . matrix define HP2wkFw3= (1, 2, 3, 2, 0, 1, 0, 6 ) 221 . 222 . matrix define H1pt2w3 = (HP2wkMw3 \ HP2wkFw3) 223 . matrix colnames H1pt2w3 = hypnum ptnum wave medsig numMAsig numModsig n > umMed 224 . matrix rownames H1pt2w3 = HP2wkMw3 WHP2wkFw3 225 . matlist H1pt2w3 | hypnum ptnum wave medsig numMAsig numModsig > -------------+----------------------------------------------------------------- - HP2wkMw3 | 1 2 3 1 0 4 > WHP2wkFw3 | 1 2 3 2 0 1 > | numMed numMed -------------+---------------------- HP2wkMw3 | 0 4 WHP2wkFw3 | 0 6 226 . 227 . scalar SigDoseWKMw3 = "no" 228 . scalar MainEffwkMw3 = "workM: age bf8 illw3 shjobw3" 229 . 230 . scalar list `MainEffwkMw3' VactnMedFw3 = age illw3 radhlw3 VactnMedMw3 = age illw3 VacatnModFw3 = none MainEffVactnFw3 = age radhlw3 deaw3 SigDoseVactnFw3 = no vactnModMw3 = none MainEffVactnMw3 = age bf7m radhlw3 SigDoseVactnMw3 = no sxLifeMedFw3 = age bf4 bf4m sxLifeMedMw3 = age illw3 InthbModFw3 = none MainEffInthbFw3 = age radhlw3 bf4 SigdoseInthbFw3 = no InthbMw3 = none MainEffInthbMw3 = age radhlw3 shfamw3 SigDoseInthbMw3 = no sxlifeMedFw3 = age illw3 radhlw3 bf4 bf4m sxlifeMedMw3 = age illw3 sxlifeModFw3 = none MainEffsxlifeFw3 = age radhlw3 bf4 bf4m shrelaw3 shfamw3 SigDoseSxlifeFw3 = no sxlifeModMw3 = none SigDosesxlifeMw3 = no MainEffsxlifeMw3 = age bf4 illw3 radhlw3 PrbfmhmMedFw3 = age bf4 PrbfmhmMedMw3 = age PrbfmhmModFw3 = none MainEffPrbfmhmFw3 = age bf4 bf40 SigDosePrbfmhmFw3 = no PrbfmhmModw3 = none SigDosePrbfmhmMw3 = no SigDosePrbfhmMw3 = no MainEffPrbfhmMw3 = bf1 bf4 dvcew3 bf7m ProbsocMedFw3 = age radhlw3 ProbsocMedMw3 = age ProbsocModFw3 = none MainEffProbSocFw3 = age radhlw3 illw3 Shrelaw3 avgcumodsew3 SigDoseProbsocFw3 = yes ProbSocModMw3 = none SigDoseProbsocMw3 = no MainEffPrbsocMw3 = age radhlw3 shjobw3 hmcareMedFw3 = age illw3 hmcareMedMw3 = age illw3 hmcareModFw3 = none SigdoseHmcareFw3 = no hmcareModMw3 = none MainEffhmcareMw3 = none SigDoseHmcareMw3 = no wkMedFw3 = radhlw3 age bf40 bf4m bf1 wkMedMw3 = bf8 age illw3 ageXillw3 wkModFw3 = none wkModMw3 = none MainEffwkFw3 = age MainEffwkMw3 = workM: age bf8 illw3 shjobw3 SigDoseWKMw3 = no SigDoseWkFw3 = no medsigFw2 = 1 wkMedMw2 = bf8 age illw2 VactnMedFw2 = age illw2 radhlw2 VactnMedMw2 = age illw2 VacatnModFw2 = none MainEffVactnFw2 = age radhlw2 deaw2 SigDoseVactnFw2 = no vactnModMw2 = none MainEffVactnMw2 = age bf7m radhlw2 SigDoseVactnMw2 = no sxLifeMedFw2 = age bf4 bf4m sxLifeMedMw2 = age illw2 InthbModFw2 = none MainEffInthbFw2 = age radhlw2 bf4 SigdoseInthbFw2 = no InthbMw2 = none MainEffInthbMw2 = age radhlw2 shfamw2 SigDoseInthbMw2 = no sxlifeMedFw2 = age illw2 radhlw2 bf4 bf4m sxlifeMedMw2 = age illw2 sxlifeModFw2 = none MainEffsxlifeFw2 = age radhlw2 bf4 bf4m shrelaw2 shfamw2 SigDoseSxlifeFw2 = no sxlifeModMw2 = none SigDosesxlifeMw2 = no MainEffsxlifeMw2 = age bf4 illw2 radhlw2 PrbfmhmMedFw2 = age bf4 PrbfmhmMedMw2 = age PrbfmhmModFw2 = none MainEffPrbfmhmFw2 = age bf4 bf40 SigDosePrbfmhmFw2 = no PrbfmhmModw2 = none SigDosePrbfmhmMw2 = no SigDosePrbfhmMw2 = no MainEffPrbfhmMw2 = bf1 bf4 dvcew2 bf7m ProbsocMedFw2 = age radhlw2 ProbsocMedMw2 = age ProbsocModFw2 = none MainEffProbSocFw2 = age radhlw2 illw2 Shrelaw2 avgcumodsew2 SigDoseProbsocFw2 = yes ProbSocModMw2 = none SigDoseProbsocMw2 = no MainEffPrbsocMw2 = age radhlw2 shjobw2 hmcareMedFw2 = age illw2 hmcareMedMw2 = age illw2 hmcareModFw2 = none SigDoseWKFw2 = 0 SigdoseHmcareFw2 = no hmcareModMw2 = none MainEffhmcareMw2 = none SigDoseHmcareMw2 = no wkMedFw2 = radhlw2 age bf40 bf4m bf1 wkModFw2 = none wkModMw2 = none MainEffwkFw2 = age MainEffwkMw2 = workM: age bf8 illw2 shjobw2 SigDoseWKMw2 = no SigDoseWkFw2 = no hmcrMedFw1 = age icdxcnt shjobw1 bf4 BSIsoma WHPpain WHPsleep WHPel hmcrMedMw1 = age MainEffhmcrFw1 = illw1 age SigDosehmcrFw1 = no hmcrModMw1 = none MainEffhmcrMw1 = age shjobw1 SigDosehmcrMw1 = no wkMedFw1 = age b4 MainEffwkFw1 = age MainEffwkMw1 = age wkMedMw1 = bf40 WkMedMw1 = none WkModFw1 = none WKModMw1 = none SigDoseWkMw1 = no SigDoseWkFw1 = no SigDoseFw1 = no wkModFw1 = none wkModMw1 = none medsigFw1 = 1 prbsocnumMAsig = 8 231 . 232 . * moderator construction 233 . * none ussed because basic dose work relationship washes out 234 . 235 . 236 . 237 . title4 "testing male hp2work moderators for hypothesis 1 pt 2 wave 3" ------------------------------------------------------------------------------- testing male hp2work moderators for hypothesis 1 pt 2 wave 3 ------------------------------------------------------------------------------- 238 . * Dose work relationship washes out for males in wave 3 also 239 . cap gen hp2hmcare=HP2hmcare 240 . 241 . forvalues j=3/3 { 2. local w3bf bf1 bf4 bf2 bf4m bf5m bf7m bf8 bf15m bf17 bf20 bf22 bf29 bf30 b > f40 3. di as input "For females HP2work on wave 3 with dose ns" 4. des age occ1w`j'-occ8w`j' inc1w`j'-inc4w`j' avgcumdosew`j' bf8 // > / > marrw`j'1-marrw`j'6 `w3bf' 5. sw, pr(.1): logistic HP2work marrw`j'3-marrw`j'6 age havmilsq /// > avgcumdosew3 bf8 illw`j' shjobw`j' suprtw`j' if gender==2, co > ef nolog 6. estat gof 7. estat class 8. fitstat 9. } For females HP2work on wave 3 with dose ns storage display value variable name type format label variable label ------------------------------------------------------------------------------- age double %8.0g * Respondent's age occ1w3 double %15.0g LABJ professional executive administration now occ2w3 double %15.0g LABJ technical sales admin support now occ3w3 double %15.0g LABJ service occup protective services now occ4w3 double %15.0g LABJ precision prod mechan craft construction now occ5w3 double %15.0g LABJ factory laborer machinist transp cleaner now occ6w3 double %15.0g LABJ farming agricul forestry fishing trapping logging now occ7w3 double %15.0g LABJ homemaking or caregiving now occ8w3 double %15.0g LABJ student now inc1w3 double %15.0g LABJ Income is not sufficient for basic neccessities NOW inc2w3 double %15.0g LABJ Income is just sufficient for basic neccessities NOW inc3w3 double %15.0g LABJ Income is sufficient for basics plus extra purchases/savings NOW inc4w3 double %15.0g LABJ Income allows to comfortably afford luxury items NOW avgcumdosew3 double %8.0g Avg Mean dose of CS137 ending 12/31/2009 bf8 float %9.0g bf8 = max(0, radtlw3 - 40) * bf5m marrw31 byte %8.0g marrw3==1. single marrw32 byte %8.0g marrw3==2. cohabitating marrw33 byte %8.0g marrw3==3. married marrw34 byte %8.0g marrw3==4. separated marrw35 byte %8.0g marrw3==5. divorced marrw36 byte %8.0g marrw3==6. widowed bf1 float %9.0g bf1 = max(0, kzchorn - 40) bf4 float %9.0g bf4 = max(0, 24 - BSIsoma) bf2 float %9.0g bf2 = max(0, efradw3 - 1.61252E-006) * bf1 bf4m float %9.0g bf4m = max(0, 32 - BSIsoma) bf5m float %9.0g bf5m = max(0, ecprw3 - 75) * bf4m bf7m float %9.0g bf7m = max(0, radtlw3 - 2.12558E-007) * bf4m bf8 float %9.0g bf8 = max(0, radtlw3 - 40) * bf5m bf15m float %9.0g bf15m= max(0, 1 - icdxcnt) * bf2 bf17 float %9.0g bf17 = max(0, 20 - ecprw3) * bf15m bf20 float %9.0g bf20 = max(0, kzchorn - 2.53946E-006) bf22 float %9.0g bf22 = max(0, icdxcnt - 1.01635E-007) * bf7m bf29 float %9.0g bf29 = max(0, 18 - CSsocspt) * bf8 bf30 float %9.0g bf30 = max(0, neiw1 - 85) * bf20 bf40 float %9.0g bf40 = max(0, icdxcnt - 1.01635E-007) begin with full model p = 0.9521 >= 0.1000 removing bf8 p = 0.9034 >= 0.1000 removing marrw33 p = 0.8340 >= 0.1000 removing shjobw3 p = 0.6525 >= 0.1000 removing marrw35 p = 0.5244 >= 0.1000 removing havmilsq p = 0.5971 >= 0.1000 removing illw3 p = 0.5333 >= 0.1000 removing suprtw3 p = 0.5822 >= 0.1000 removing marrw34 p = 0.4224 >= 0.1000 removing marrw36 p = 0.1142 >= 0.1000 removing avgcumdosew3 Logistic regression Number of obs = 362 LR chi2(1) = 42.20 Prob > chi2 = 0.0000 Log likelihood = -185.1665 Pseudo R2 = 0.1023 ------------------------------------------------------------------------------ HP2work | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .070115 .0116471 6.02 0.000 .047287 .0929429 _cons | -4.733748 .6446886 -7.34 0.000 -5.997314 -3.470181 ------------------------------------------------------------------------------ Logistic model for HP2work, goodness-of-fit test number of observations = 362 number of covariate patterns = 49 Pearson chi2(47) = 58.24 Prob > chi2 = 0.1261 Logistic model for HP2work -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 20 14 | 34 - | 73 255 | 328 -----------+--------------------------+----------- Total | 93 269 | 362 Classified + if predicted Pr(D) >= .5 True D defined as HP2work != 0 -------------------------------------------------- Sensitivity Pr( +| D) 21.51% Specificity Pr( -|~D) 94.80% Positive predictive value Pr( D| +) 58.82% Negative predictive value Pr(~D| -) 77.74% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 5.20% False - rate for true D Pr( -| D) 78.49% False + rate for classified + Pr(~D| +) 41.18% False - rate for classified - Pr( D| -) 22.26% -------------------------------------------------- Correctly classified 75.97% -------------------------------------------------- Measures of Fit for logistic of HP2work Log-Lik Intercept Only: -206.266 Log-Lik Full Model: -185.167 D(360): 370.333 LR(1): 42.199 Prob > LR: 0.000 McFadden's R2: 0.102 McFadden's Adj R2: 0.093 Maximum Likelihood R2: 0.110 Cragg & Uhler's R2: 0.162 McKelvey and Zavoina's R2: 0.174 Efron's R2: 0.127 Variance of y*: 3.982 Variance of error: 3.290 Count R2: 0.760 Adj Count R2: 0.065 AIC: 1.034 AIC*n: 374.333 BIC: -1750.659 BIC': -36.308 242 . 243 . scalar MainEffwkFw3 = "age" 244 . 245 . 246 . 247 . forvalues j=3/3 { 2. local w3bf bf1 bf4 bf2 bf4m bf5m bf7m bf8 bf15m bf17 bf20 bf22 bf29 bf30 b > f40 3. 248 . di as input "For females HP2work on wave 3 with dose ns" 4. des age occ1w`j'-occ8w`j' inc1w`j'-inc4w`j' avgcumdosew`j' bf8 // > / > marrw`j'1-marrw`j'6 `w3bf' 5. sw, pr(.1): logistic HP2work marrw`j'3-marrw`j'6 age havmilsq /// > avgcumdosew3 bf8 illw`j' shjobw`j' suprtw`j' if gender==1, co > ef nolog 6. estat gof 7. estat class 8. fitstat 9. } For females HP2work on wave 3 with dose ns storage display value variable name type format label variable label ------------------------------------------------------------------------------- age double %8.0g * Respondent's age occ1w3 double %15.0g LABJ professional executive administration now occ2w3 double %15.0g LABJ technical sales admin support now occ3w3 double %15.0g LABJ service occup protective services now occ4w3 double %15.0g LABJ precision prod mechan craft construction now occ5w3 double %15.0g LABJ factory laborer machinist transp cleaner now occ6w3 double %15.0g LABJ farming agricul forestry fishing trapping logging now occ7w3 double %15.0g LABJ homemaking or caregiving now occ8w3 double %15.0g LABJ student now inc1w3 double %15.0g LABJ Income is not sufficient for basic neccessities NOW inc2w3 double %15.0g LABJ Income is just sufficient for basic neccessities NOW inc3w3 double %15.0g LABJ Income is sufficient for basics plus extra purchases/savings NOW inc4w3 double %15.0g LABJ Income allows to comfortably afford luxury items NOW avgcumdosew3 double %8.0g Avg Mean dose of CS137 ending 12/31/2009 bf8 float %9.0g bf8 = max(0, radtlw3 - 40) * bf5m marrw31 byte %8.0g marrw3==1. single marrw32 byte %8.0g marrw3==2. cohabitating marrw33 byte %8.0g marrw3==3. married marrw34 byte %8.0g marrw3==4. separated marrw35 byte %8.0g marrw3==5. divorced marrw36 byte %8.0g marrw3==6. widowed bf1 float %9.0g bf1 = max(0, kzchorn - 40) bf4 float %9.0g bf4 = max(0, 24 - BSIsoma) bf2 float %9.0g bf2 = max(0, efradw3 - 1.61252E-006) * bf1 bf4m float %9.0g bf4m = max(0, 32 - BSIsoma) bf5m float %9.0g bf5m = max(0, ecprw3 - 75) * bf4m bf7m float %9.0g bf7m = max(0, radtlw3 - 2.12558E-007) * bf4m bf8 float %9.0g bf8 = max(0, radtlw3 - 40) * bf5m bf15m float %9.0g bf15m= max(0, 1 - icdxcnt) * bf2 bf17 float %9.0g bf17 = max(0, 20 - ecprw3) * bf15m bf20 float %9.0g bf20 = max(0, kzchorn - 2.53946E-006) bf22 float %9.0g bf22 = max(0, icdxcnt - 1.01635E-007) * bf7m bf29 float %9.0g bf29 = max(0, 18 - CSsocspt) * bf8 bf30 float %9.0g bf30 = max(0, neiw1 - 85) * bf20 bf40 float %9.0g bf40 = max(0, icdxcnt - 1.01635E-007) note: marrw34 dropped because of collinearity begin with full model p = 0.6924 >= 0.1000 removing avgcumdosew3 p = 0.5691 >= 0.1000 removing marrw36 p = 0.5489 >= 0.1000 removing havmilsq p = 0.5439 >= 0.1000 removing marrw35 Logistic regression Number of obs = 340 LR chi2(6) = 54.97 Prob > chi2 = 0.0000 Log likelihood = -145.3871 Pseudo R2 = 0.1590 ------------------------------------------------------------------------------ HP2work | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- marrw33 | -.9533134 .4976353 -1.92 0.055 -1.928661 .0220339 bf8 | -.0000528 .0000242 -2.18 0.029 -.0001002 -5.32e-06 shjobw3 | .0109505 .0039896 2.74 0.006 .003131 .0187701 age | .0475117 .0137133 3.46 0.001 .0206342 .0743892 illw3 | .7534933 .157365 4.79 0.000 .4450635 1.061923 suprtw3 | .0095264 .0057237 1.66 0.096 -.0016919 .0207447 _cons | -4.534902 .8292162 -5.47 0.000 -6.160136 -2.909668 ------------------------------------------------------------------------------ Logistic model for HP2work, goodness-of-fit test number of observations = 340 number of covariate patterns = 320 Pearson chi2(313) = 320.59 Prob > chi2 = 0.3716 Logistic model for HP2work -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 18 7 | 25 - | 52 263 | 315 -----------+--------------------------+----------- Total | 70 270 | 340 Classified + if predicted Pr(D) >= .5 True D defined as HP2work != 0 -------------------------------------------------- Sensitivity Pr( +| D) 25.71% Specificity Pr( -|~D) 97.41% Positive predictive value Pr( D| +) 72.00% Negative predictive value Pr(~D| -) 83.49% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 2.59% False - rate for true D Pr( -| D) 74.29% False + rate for classified + Pr(~D| +) 28.00% False - rate for classified - Pr( D| -) 16.51% -------------------------------------------------- Correctly classified 82.65% -------------------------------------------------- Measures of Fit for logistic of HP2work Log-Lik Intercept Only: -172.873 Log-Lik Full Model: -145.387 D(333): 290.774 LR(6): 54.972 Prob > LR: 0.000 McFadden's R2: 0.159 McFadden's Adj R2: 0.119 Maximum Likelihood R2: 0.149 Cragg & Uhler's R2: 0.234 McKelvey and Zavoina's R2: 0.253 Efron's R2: 0.177 Variance of y*: 4.403 Variance of error: 3.290 Count R2: 0.826 Adj Count R2: 0.157 AIC: 0.896 AIC*n: 304.774 BIC: -1650.265 BIC': -19.998 249 . 250 . 251 . 252 . * capturing significant vars from last analysis 253 . local cn1: colnames(e(b)) 254 . di "`cn1'" marrw33 bf8 shjobw3 age illw3 suprtw3 _cons 255 . local leng1 = length( "`cn1'") 256 . di `leng1' 43 257 . local leng1b `leng1'-6 258 . di `leng1b' 37 259 . local nuvlist = substr("`cn1'",1,`leng1b') 260 . di "`nuvlist'" marrw33 bf8 shjobw3 age illw3 suprtw3 261 . local rhsvars = "`nuvlist'" 262 . local nuvlist= "`nuvlist'" 263 . local nuvlist= substr("`cn1'",1,`leng1b') 264 . di "`nuvlist'" marrw33 bf8 shjobw3 age illw3 suprtw3 265 . sw, pr(.1):logit hp2hmcare `nuvlist' if gender==1 begin with full model p = 0.9998 >= 0.1000 removing marrw33 p = 0.9539 >= 0.1000 removing shjobw3 p = 0.4193 >= 0.1000 removing suprtw3 p = 0.1605 >= 0.1000 removing bf8 Logistic regression Number of obs = 340 LR chi2(2) = 37.81 Prob > chi2 = 0.0000 Log likelihood = -153.96835 Pseudo R2 = 0.1094 ------------------------------------------------------------------------------ hp2hmcare | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .050053 .0120837 4.14 0.000 .0263694 .0737367 illw3 | .450018 .1335457 3.37 0.001 .1882732 .7117629 _cons | -4.209924 .6577161 -6.40 0.000 -5.499024 -2.920824 ------------------------------------------------------------------------------ 266 . di "`rhsvars'" marrw33 bf8 shjobw3 age illw3 suprtw3 267 . matrix define c=e(b) 268 . local cn2: colnames(c) 269 . di "`cn2'" age illw3 _cons 270 . local leng2 = length("`cn2'") 271 . local leng2b = `leng2'-6 272 . local rhsvars = substr("`cn2'",1,`leng2b') 273 . logit hp2work `rhsvars' if gender==1 Iteration 0: log likelihood = -172.87291 Iteration 1: log likelihood = -155.70854 Iteration 2: log likelihood = -154.73483 Iteration 3: log likelihood = -154.7292 Iteration 4: log likelihood = -154.7292 Logistic regression Number of obs = 340 LR chi2(2) = 36.29 Prob > chi2 = 0.0000 Log likelihood = -154.7292 Pseudo R2 = 0.1050 ------------------------------------------------------------------------------ hp2work | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .029911 .0118759 2.52 0.012 .0066346 .0531873 illw3 | .6323839 .1414947 4.47 0.000 .3550594 .9097083 _cons | -3.26854 .6276516 -5.21 0.000 -4.498715 -2.038366 ------------------------------------------------------------------------------ 274 . 275 . 276 . 277 . di "`rhsvars'" age illw3 278 . local varlist2 =substr("`rhsvars'",1,9) 279 . di "`varlist2'" age illw3 280 . 281 . * constructing potential moderators 282 . foreach var in age illw3 { 2. cap gen `var'Xd3 = `var'* avgcumdosew3 3. } 283 . 284 . * main effects model 285 . 286 . logit hp2work `rhsvars' if gender==1, nolog Logistic regression Number of obs = 340 LR chi2(2) = 36.29 Prob > chi2 = 0.0000 Log likelihood = -154.7292 Pseudo R2 = 0.1050 ------------------------------------------------------------------------------ hp2work | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .029911 .0118759 2.52 0.012 .0066346 .0531873 illw3 | .6323839 .1414947 4.47 0.000 .3550594 .9097083 _cons | -3.26854 .6276516 -5.21 0.000 -4.498715 -2.038366 ------------------------------------------------------------------------------ 287 . 288 . *x no signif male moderators for paid employment 289 . 290 . logit hp2work `rhsvars' illw3Xd3 if gender==1 Iteration 0: log likelihood = -172.87291 Iteration 1: log likelihood = -155.25678 Iteration 2: log likelihood = -154.38518 Iteration 3: log likelihood = -154.38145 Iteration 4: log likelihood = -154.38145 Logistic regression Number of obs = 340 LR chi2(3) = 36.98 Prob > chi2 = 0.0000 Log likelihood = -154.38145 Pseudo R2 = 0.1070 ------------------------------------------------------------------------------ hp2work | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0293019 .0119141 2.46 0.014 .0059507 .0526531 illw3 | .5890952 .14968 3.94 0.000 .2957278 .8824626 illw3Xd3 | .0284995 .0363345 0.78 0.433 -.0427148 .0997139 _cons | -3.238806 .6288194 -5.15 0.000 -4.471269 -2.006342 ------------------------------------------------------------------------------ 291 . fitstat Measures of Fit for logit of hp2work Log-Lik Intercept Only: -172.873 Log-Lik Full Model: -154.381 D(336): 308.763 LR(3): 36.983 Prob > LR: 0.000 McFadden's R2: 0.107 McFadden's Adj R2: 0.084 Maximum Likelihood R2: 0.103 Cragg & Uhler's R2: 0.161 McKelvey and Zavoina's R2: 0.160 Efron's R2: 0.127 Variance of y*: 3.919 Variance of error: 3.290 Count R2: 0.818 Adj Count R2: 0.114 AIC: 0.932 AIC*n: 316.763 BIC: -1649.763 BIC': -19.496 292 . 293 . scalar wkModMw3 = "none" 294 . * Testing female moderator models xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx > xxxx 295 . 296 . title4 "testing general female moderator models for hp2work" ------------------------------------------------------------------------------- testing general female moderator models for hp2work ------------------------------------------------------------------------------- 297 . local w3bf bf1 bf4 bf2 bf4m bf5m bf7m bf8 bf15m bf17 bf20 bf22 bf29 bf30 bf40 298 . * Moderator testing for women also 299 . * Dose work relationship for females in wave 3 washes out also 300 . 301 . forvalues j=3/3 { 2. di as input "For females HP2work on wave 3 with dose ns" 3. des age occ1w`j'-occ8w`j' inc1w`j'-inc4w`j' avgcumdosew`j' `w3bf' 4. sw, pr(.1): logistic HP2work age havmilsq /// > avgcumdosew3 illw`j' shjobw`j' suprtw`j' if gender==2, coef nolog 5. estat gof 6. estat class 7. fitstat 8. } For females HP2work on wave 3 with dose ns storage display value variable name type format label variable label ------------------------------------------------------------------------------- age double %8.0g * Respondent's age occ1w3 double %15.0g LABJ professional executive administration now occ2w3 double %15.0g LABJ technical sales admin support now occ3w3 double %15.0g LABJ service occup protective services now occ4w3 double %15.0g LABJ precision prod mechan craft construction now occ5w3 double %15.0g LABJ factory laborer machinist transp cleaner now occ6w3 double %15.0g LABJ farming agricul forestry fishing trapping logging now occ7w3 double %15.0g LABJ homemaking or caregiving now occ8w3 double %15.0g LABJ student now inc1w3 double %15.0g LABJ Income is not sufficient for basic neccessities NOW inc2w3 double %15.0g LABJ Income is just sufficient for basic neccessities NOW inc3w3 double %15.0g LABJ Income is sufficient for basics plus extra purchases/savings NOW inc4w3 double %15.0g LABJ Income allows to comfortably afford luxury items NOW avgcumdosew3 double %8.0g Avg Mean dose of CS137 ending 12/31/2009 bf1 float %9.0g bf1 = max(0, kzchorn - 40) bf4 float %9.0g bf4 = max(0, 24 - BSIsoma) bf2 float %9.0g bf2 = max(0, efradw3 - 1.61252E-006) * bf1 bf4m float %9.0g bf4m = max(0, 32 - BSIsoma) bf5m float %9.0g bf5m = max(0, ecprw3 - 75) * bf4m bf7m float %9.0g bf7m = max(0, radtlw3 - 2.12558E-007) * bf4m bf8 float %9.0g bf8 = max(0, radtlw3 - 40) * bf5m bf15m float %9.0g bf15m= max(0, 1 - icdxcnt) * bf2 bf17 float %9.0g bf17 = max(0, 20 - ecprw3) * bf15m bf20 float %9.0g bf20 = max(0, kzchorn - 2.53946E-006) bf22 float %9.0g bf22 = max(0, icdxcnt - 1.01635E-007) * bf7m bf29 float %9.0g bf29 = max(0, 18 - CSsocspt) * bf8 bf30 float %9.0g bf30 = max(0, neiw1 - 85) * bf20 bf40 float %9.0g bf40 = max(0, icdxcnt - 1.01635E-007) begin with full model p = 0.8907 >= 0.1000 removing suprtw3 p = 0.8830 >= 0.1000 removing shjobw3 p = 0.5343 >= 0.1000 removing havmilsq p = 0.6152 >= 0.1000 removing illw3 p = 0.1142 >= 0.1000 removing avgcumdosew3 Logistic regression Number of obs = 362 LR chi2(1) = 42.20 Prob > chi2 = 0.0000 Log likelihood = -185.1665 Pseudo R2 = 0.1023 ------------------------------------------------------------------------------ HP2work | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .070115 .0116471 6.02 0.000 .047287 .0929429 _cons | -4.733748 .6446886 -7.34 0.000 -5.997314 -3.470181 ------------------------------------------------------------------------------ Logistic model for HP2work, goodness-of-fit test number of observations = 362 number of covariate patterns = 49 Pearson chi2(47) = 58.24 Prob > chi2 = 0.1261 Logistic model for HP2work -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 20 14 | 34 - | 73 255 | 328 -----------+--------------------------+----------- Total | 93 269 | 362 Classified + if predicted Pr(D) >= .5 True D defined as HP2work != 0 -------------------------------------------------- Sensitivity Pr( +| D) 21.51% Specificity Pr( -|~D) 94.80% Positive predictive value Pr( D| +) 58.82% Negative predictive value Pr(~D| -) 77.74% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 5.20% False - rate for true D Pr( -| D) 78.49% False + rate for classified + Pr(~D| +) 41.18% False - rate for classified - Pr( D| -) 22.26% -------------------------------------------------- Correctly classified 75.97% -------------------------------------------------- Measures of Fit for logistic of HP2work Log-Lik Intercept Only: -206.266 Log-Lik Full Model: -185.167 D(360): 370.333 LR(1): 42.199 Prob > LR: 0.000 McFadden's R2: 0.102 McFadden's Adj R2: 0.093 Maximum Likelihood R2: 0.110 Cragg & Uhler's R2: 0.162 McKelvey and Zavoina's R2: 0.174 Efron's R2: 0.127 Variance of y*: 3.982 Variance of error: 3.290 Count R2: 0.760 Adj Count R2: 0.065 AIC: 1.034 AIC*n: 374.333 BIC: -1750.659 BIC': -36.308 302 . 303 . replace ageXd3 = age*avgcumdosew3 (0 real changes made) 304 . 305 . * capturing significant vars 306 . local cn3: colnames(e(b)) 307 . di "`cn3'" age _cons 308 . local leng1 = length( "`cn3'") 309 . di `leng3' 310 . local leng1b `leng1'-6 311 . di `leng3b' 312 . local nuvlist3 = substr("`cn1'",1,`leng1b') 313 . di "`nuvlist3'" mar 314 . local rhsvars3 = "`nuvlist3'" 315 . local nuvlist3= "`nuvlist3'" 316 . local nuvlist3= substr("`cn1'",1,`leng1b') 317 . di "`nuvlist3'" mar 318 . 319 . * moderators for hp2work female and male are saved as scalars: 320 . scalar wkModFw3="none" 321 . scalar wkModMw3="none" 322 . 323 . *x trimmed female main effects model for paid employment 324 . forvalues j=3/3 { 2. di as input "For females hp2probsoc on wave 1 with dose ns" 3. des age occ1w`j'-occ8w`j' inc1w`j'-inc4w`j' avgcumdosew`j' `w3bf' 4. logistic HP2work age /// > avgcumdosew3 illw`j' if gender==2, coef nolog 5. 325 . } For females hp2probsoc on wave 1 with dose ns storage display value variable name type format label variable label ------------------------------------------------------------------------------- age double %8.0g * Respondent's age occ1w3 double %15.0g LABJ professional executive administration now occ2w3 double %15.0g LABJ technical sales admin support now occ3w3 double %15.0g LABJ service occup protective services now occ4w3 double %15.0g LABJ precision prod mechan craft construction now occ5w3 double %15.0g LABJ factory laborer machinist transp cleaner now occ6w3 double %15.0g LABJ farming agricul forestry fishing trapping logging now occ7w3 double %15.0g LABJ homemaking or caregiving now occ8w3 double %15.0g LABJ student now inc1w3 double %15.0g LABJ Income is not sufficient for basic neccessities NOW inc2w3 double %15.0g LABJ Income is just sufficient for basic neccessities NOW inc3w3 double %15.0g LABJ Income is sufficient for basics plus extra purchases/savings NOW inc4w3 double %15.0g LABJ Income allows to comfortably afford luxury items NOW avgcumdosew3 double %8.0g Avg Mean dose of CS137 ending 12/31/2009 bf1 float %9.0g bf1 = max(0, kzchorn - 40) bf4 float %9.0g bf4 = max(0, 24 - BSIsoma) bf2 float %9.0g bf2 = max(0, efradw3 - 1.61252E-006) * bf1 bf4m float %9.0g bf4m = max(0, 32 - BSIsoma) bf5m float %9.0g bf5m = max(0, ecprw3 - 75) * bf4m bf7m float %9.0g bf7m = max(0, radtlw3 - 2.12558E-007) * bf4m bf8 float %9.0g bf8 = max(0, radtlw3 - 40) * bf5m bf15m float %9.0g bf15m= max(0, 1 - icdxcnt) * bf2 bf17 float %9.0g bf17 = max(0, 20 - ecprw3) * bf15m bf20 float %9.0g bf20 = max(0, kzchorn - 2.53946E-006) bf22 float %9.0g bf22 = max(0, icdxcnt - 1.01635E-007) * bf7m bf29 float %9.0g bf29 = max(0, 18 - CSsocspt) * bf8 bf30 float %9.0g bf30 = max(0, neiw1 - 85) * bf20 bf40 float %9.0g bf40 = max(0, icdxcnt - 1.01635E-007) Logistic regression Number of obs = 363 LR chi2(3) = 44.36 Prob > chi2 = 0.0000 Log likelihood = -184.38047 Pseudo R2 = 0.1074 ------------------------------------------------------------------------------ HP2work | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0671516 .0118118 5.69 0.000 .044001 .0903022 avgcumdosew3 | .098591 .0655698 1.50 0.133 -.0299235 .2271054 illw3 | .0384557 .1099365 0.35 0.726 -.1770159 .2539274 _cons | -4.743303 .6477105 -7.32 0.000 -6.012792 -3.473814 ------------------------------------------------------------------------------ 326 . 327 . title4 " Mediator analysis for Dose=>paid employment wave three" ------------------------------------------------------------------------------- Mediator analysis for Dose=>paid employment wave three ------------------------------------------------------------------------------- 328 . title4 "age may be a male mediator for dose- paid employment impact" ------------------------------------------------------------------------------- age may be a male mediator for dose- paid employment impact ------------------------------------------------------------------------------- 329 . 330 . * we test for the possibility by testing a probit analysis 331 . glm radhlw3 avgcumdosew3 if gender==1, fam(gaussian) link(identity) Iteration 0: log likelihood = -1695.1855 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = 1261.052 Deviance = 426235.7205 (1/df) Deviance = 1261.052 Pearson = 426235.7205 (1/df) Pearson = 1261.052 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 9.983444 Log likelihood = -1695.185473 BIC = 424265.5 ------------------------------------------------------------------------------ | OIM radhlw3 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | .9606492 .7224692 1.33 0.184 -.4553645 2.376663 _cons | 46.19995 2.117563 21.82 0.000 42.0496 50.3503 ------------------------------------------------------------------------------ 332 . glm hp2work radhlw3 if gender==1, fam(binomial) irls scale(dev) link(probit) Iteration 1: deviance = 327.9117 Iteration 2: deviance = 327.3424 Iteration 3: deviance = 327.342 Iteration 4: deviance = 327.342 Generalized linear models No. of obs = 340 Optimization : MQL Fisher scoring Residual df = 338 (IRLS EIM) Scale parameter = 1 Deviance = 327.3419871 (1/df) Deviance = .9684674 Pearson = 339.544695 (1/df) Pearson = 1.00457 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1642.842 ------------------------------------------------------------------------------ | EIM hp2work | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- radhlw3 | .0094116 .0021904 4.30 0.000 .0051185 .0137048 _cons | -1.312207 .1427935 -9.19 0.000 -1.592077 -1.032337 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 333 . 334 . 335 . di as input "age is a possible male mediator for paid employment" age is a possible male mediator for paid employment 336 . 337 . glm age avgcumdosew3 if gender==1, family(gaussian) link(identity) Iteration 0: log likelihood = -1330.6336 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = 147.7142 Deviance = 49927.38549 (1/df) Deviance = 147.7142 Pearson = 49927.38549 (1/df) Pearson = 147.7142 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 7.839021 Log likelihood = -1330.633586 BIC = 47957.2 ------------------------------------------------------------------------------ | OIM age | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | .5433648 .2472657 2.20 0.028 .058733 1.027997 _cons | 48.52021 .7247376 66.95 0.000 47.09975 49.94067 ------------------------------------------------------------------------------ 338 . glm hp2work age if gender==1, family(binomial) irls scale(dev) link(probit) Iteration 1: deviance = 332.6127 Iteration 2: deviance = 332.2035 Iteration 3: deviance = 332.2034 Iteration 4: deviance = 332.2034 Generalized linear models No. of obs = 340 Optimization : MQL Fisher scoring Residual df = 338 (IRLS EIM) Scale parameter = 1 Deviance = 332.2034085 (1/df) Deviance = .9828503 Pearson = 339.5831812 (1/df) Pearson = 1.004684 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1637.98 ------------------------------------------------------------------------------ | EIM hp2work | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0233394 .0063554 3.67 0.000 .0108831 .0357956 _cons | -2.001321 .3351159 -5.97 0.000 -2.658136 -1.344506 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 339 . 340 . 341 . di as input "Illness in wave 3 is a possible mediator for dose-paid employmen > t impact" Illness in wave 3 is a possible mediator for dose-paid employment impact 342 . glm illw3 avgcumdosew3 if gender==1, family(gaussian) link(identity) Iteration 0: log likelihood = -461.99206 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = .8919217 Deviance = 301.469521 (1/df) Deviance = .8919217 Pearson = 301.469521 (1/df) Pearson = .8919217 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 2.729365 Log likelihood = -461.9920626 BIC = -1668.714 ------------------------------------------------------------------------------ | OIM illw3 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | .038211 .0192139 1.99 0.047 .0005524 .0758696 _cons | .4504952 .0563162 8.00 0.000 .3401176 .5608729 ------------------------------------------------------------------------------ 343 . glm hp2work illw3 if gender==1, family(binomial) irls scale(dev) link(probit) > Iteration 1: deviance = 315.5535 Iteration 2: deviance = 315.5149 Iteration 3: deviance = 315.5148 Iteration 4: deviance = 315.5148 Generalized linear models No. of obs = 340 Optimization : MQL Fisher scoring Residual df = 338 (IRLS EIM) Scale parameter = 1 Deviance = 315.5148102 (1/df) Deviance = .9334758 Pearson = 336.1884602 (1/df) Pearson = .9946404 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1654.669 ------------------------------------------------------------------------------ | EIM hp2work | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- illw3 | .4173011 .0774431 5.39 0.000 .2655154 .5690869 _cons | -1.077182 .0906493 -11.88 0.000 -1.254852 -.899513 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 344 . * constructing an interaction 345 . 346 . 347 . di as input "Interaction of age & illness in wave 3 is moderator that mediate > s for males" Interaction of age & illness in wave 3 is moderator that mediates for males 348 . 349 . cap gen ageXillw3 = age*illw3 350 . glm illw3 avgcumdosew3 if gender==1, family(gaussian) link(identity) Iteration 0: log likelihood = -461.99206 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = .8919217 Deviance = 301.469521 (1/df) Deviance = .8919217 Pearson = 301.469521 (1/df) Pearson = .8919217 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 2.729365 Log likelihood = -461.9920626 BIC = -1668.714 ------------------------------------------------------------------------------ | OIM illw3 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | .038211 .0192139 1.99 0.047 .0005524 .0758696 _cons | .4504952 .0563162 8.00 0.000 .3401176 .5608729 ------------------------------------------------------------------------------ 351 . glm hp2work illw3 avgcumdosew3 ageXillw3 if gender==1, family(binomial) /// > irls scale(dev) link(probit) Iteration 1: deviance = 306.4966 Iteration 2: deviance = 306.1716 Iteration 3: deviance = 306.1695 Iteration 4: deviance = 306.1695 Generalized linear models No. of obs = 340 Optimization : MQL Fisher scoring Residual df = 336 (IRLS EIM) Scale parameter = 1 Deviance = 306.1695162 (1/df) Deviance = .9112188 Pearson = 333.6560038 (1/df) Pearson = .9930238 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1652.356 ------------------------------------------------------------------------------ | EIM hp2work | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- illw3 | -.9049112 .4534263 -2.00 0.046 -1.79361 -.0162121 avgcumdosew3 | -.004425 .0291879 -0.15 0.879 -.0616323 .0527822 ageXillw3 | .0235805 .0080114 2.94 0.003 .0078785 .0392825 _cons | -1.048466 .0954586 -10.98 0.000 -1.235561 -.8613702 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 352 . 353 . 354 . 355 . des bf8 storage display value variable name type format label variable label ------------------------------------------------------------------------------- bf8 float %9.0g bf8 = max(0, radtlw3 - 40) * bf5m 356 . title4 "bf8 is a male mediator of paid employment" ------------------------------------------------------------------------------- bf8 is a male mediator of paid employment ------------------------------------------------------------------------------- 357 . local w3bf bf1 bf4 bf2 bf4m bf5m bf7m bf8 bf15m bf17 bf20 bf22 bf29 bf30 bf40 358 . foreach var in `w3bf'{ 2. glm `var' avgcumdosew3 if gender==1, family(gaussian) link(identity) 3. glm hp2work `var' illw3 avgcumdosew3 ageXillw3 if gender==1, family(binomi > al) /// > irls scale(dev) link(probit) 4. } Iteration 0: log likelihood = -1551.9192 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = 542.9186 Deviance = 183506.4901 (1/df) Deviance = 542.9186 Pearson = 183506.4901 (1/df) Pearson = 542.9186 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 9.140701 Log likelihood = -1551.91925 BIC = 181536.3 ------------------------------------------------------------------------------ | OIM bf1 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | -.002304 .4740456 -0.00 0.996 -.9314164 .9268084 _cons | 32.04104 1.389431 23.06 0.000 29.31781 34.76428 ------------------------------------------------------------------------------ Iteration 1: deviance = 301.0309 Iteration 2: deviance = 300.1656 Iteration 3: deviance = 300.1621 Iteration 4: deviance = 300.1621 Iteration 5: deviance = 300.1621 Generalized linear models No. of obs = 340 Optimization : MQL Fisher scoring Residual df = 335 (IRLS EIM) Scale parameter = 1 Deviance = 300.1621391 (1/df) Deviance = .8960064 Pearson = 331.1205639 (1/df) Pearson = .9884196 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1652.535 ------------------------------------------------------------------------------ | EIM hp2work | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- bf1 | .0089452 .0034596 2.59 0.010 .0021644 .0157259 illw3 | -.77203 .4386134 -1.76 0.078 -1.631697 .0876365 avgcumdosew3 | -.00216 .0295424 -0.07 0.942 -.0600621 .0557421 ageXillw3 | .020558 .0077394 2.66 0.008 .005389 .0357271 _cons | -1.346332 .1529226 -8.80 0.000 -1.646055 -1.04661 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) Iteration 0: log likelihood = -1027.1072 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = 24.77487 Deviance = 8373.906252 (1/df) Deviance = 24.77487 Pearson = 8373.906252 (1/df) Pearson = 24.77487 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 6.053572 Log likelihood = -1027.107224 BIC = 6403.723 ------------------------------------------------------------------------------ | OIM bf4 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | -.0357675 .1012648 -0.35 0.724 -.2342429 .1627078 _cons | 12.54064 .2968079 42.25 0.000 11.95891 13.12238 ------------------------------------------------------------------------------ Iteration 1: deviance = 282.7342 Iteration 2: deviance = 280.9952 Iteration 3: deviance = 280.9756 Iteration 4: deviance = 280.9756 Iteration 5: deviance = 280.9756 Generalized linear models No. of obs = 340 Optimization : MQL Fisher scoring Residual df = 335 (IRLS EIM) Scale parameter = 1 Deviance = 280.975559 (1/df) Deviance = .838733 Pearson = 310.5734169 (1/df) Pearson = .9270848 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1671.721 ------------------------------------------------------------------------------ | EIM hp2work | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- bf4 | -.0819747 .0150372 -5.45 0.000 -.1114471 -.0525023 illw3 | -.5388859 .4267744 -1.26 0.207 -1.375348 .2975765 avgcumdosew3 | .0024099 .0278188 0.09 0.931 -.052114 .0569338 ageXillw3 | .0153271 .0074554 2.06 0.040 .0007149 .0299394 _cons | -.0701321 .2003312 -0.35 0.726 -.4627742 .3225099 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) Iteration 0: log likelihood = -3110.5209 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = 5205387 Deviance = 1759420733 (1/df) Deviance = 5205387 Pearson = 1759420733 (1/df) Pearson = 5205387 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 18.30895 Log likelihood = -3110.520925 BIC = 1.76e+09 ------------------------------------------------------------------------------ | OIM bf2 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | -40.64822 46.41724 -0.88 0.381 -131.6243 50.3279 _cons | 1991.578 136.0493 14.64 0.000 1724.926 2258.229 ------------------------------------------------------------------------------ Iteration 1: deviance = 299.7774 Iteration 2: deviance = 299.1194 Iteration 3: deviance = 299.1177 Iteration 4: deviance = 299.1177 Iteration 5: deviance = 299.1177 Generalized linear models No. of obs = 340 Optimization : MQL Fisher scoring Residual df = 335 (IRLS EIM) Scale parameter = 1 Deviance = 299.1177398 (1/df) Deviance = .8928888 Pearson = 333.2413587 (1/df) Pearson = .9947503 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1653.579 ------------------------------------------------------------------------------ | EIM hp2work | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- bf2 | .0000949 .0000336 2.82 0.005 .000029 .0001608 illw3 | -.6262331 .449099 -1.39 0.163 -1.506451 .2539847 avgcumdosew3 | .0027738 .0281975 0.10 0.922 -.0524922 .0580398 ageXillw3 | .0180516 .0079115 2.28 0.023 .0025454 .0335579 _cons | -1.256084 .1228394 -10.23 0.000 -1.496845 -1.015323 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) Iteration 0: log likelihood = -1060.7697 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = 30.20008 Deviance = 10207.62832 (1/df) Deviance = 30.20008 Pearson = 10207.62832 (1/df) Pearson = 30.20008 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 6.251587 Log likelihood = -1060.769747 BIC = 8237.445 ------------------------------------------------------------------------------ | OIM bf4m | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | -.0292413 .1118039 -0.26 0.794 -.2483729 .1898903 _cons | 20.35328 .327698 62.11 0.000 19.711 20.99556 ------------------------------------------------------------------------------ Iteration 1: deviance = 284.2146 Iteration 2: deviance = 282.8347 Iteration 3: deviance = 282.8223 Iteration 4: deviance = 282.8223 Iteration 5: deviance = 282.8223 Generalized linear models No. of obs = 340 Optimization : MQL Fisher scoring Residual df = 335 (IRLS EIM) Scale parameter = 1 Deviance = 282.8222621 (1/df) Deviance = .8442456 Pearson = 311.8592054 (1/df) Pearson = .930923 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1669.875 ------------------------------------------------------------------------------ | EIM hp2work | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- bf4m | -.0702538 .0135383 -5.19 0.000 -.0967884 -.0437191 illw3 | -.5205682 .4244129 -1.23 0.220 -1.352402 .3112658 avgcumdosew3 | .0026156 .0277534 0.09 0.925 -.05178 .0570112 ageXillw3 | .0151759 .0074121 2.05 0.041 .0006484 .0297034 _cons | .3364223 .2818414 1.19 0.233 -.2159766 .8888213 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) Iteration 0: log likelihood = -2273.014 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = 37748.2 Deviance = 12758891.39 (1/df) Deviance = 37748.2 Pearson = 12758891.39 (1/df) Pearson = 37748.2 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 13.38244 Log likelihood = -2273.013968 BIC = 1.28e+07 ------------------------------------------------------------------------------ | OIM bf5m | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | 9.087842 3.952764 2.30 0.021 1.340566 16.83512 _cons | 102.4403 11.58558 8.84 0.000 79.73302 125.1477 ------------------------------------------------------------------------------ Iteration 1: deviance = 304.1111 Iteration 2: deviance = 303.3297 Iteration 3: deviance = 303.318 Iteration 4: deviance = 303.318 Iteration 5: deviance = 303.318 Generalized linear models No. of obs = 340 Optimization : MQL Fisher scoring Residual df = 335 (IRLS EIM) Scale parameter = 1 Deviance = 303.3180183 (1/df) Deviance = .9054269 Pearson = 334.3846422 (1/df) Pearson = .9981631 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1649.379 ------------------------------------------------------------------------------ | EIM hp2work | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- bf5m | -.0008032 .0004666 -1.72 0.085 -.0017178 .0001114 illw3 | -.8955598 .4670831 -1.92 0.055 -1.811026 .0199063 avgcumdosew3 | .0024508 .0286972 0.09 0.932 -.0537946 .0586962 ageXillw3 | .0244622 .0082752 2.96 0.003 .0082431 .0406812 _cons | -1.001258 .0981618 -10.20 0.000 -1.193652 -.8088645 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) Iteration 0: log likelihood = -2733.8489 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = 567778.4 Deviance = 191909111.2 (1/df) Deviance = 567778.4 Pearson = 191909111.2 (1/df) Pearson = 567778.4 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 16.09323 Log likelihood = -2733.848861 BIC = 1.92e+08 ------------------------------------------------------------------------------ | OIM bf7m | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | 9.565438 15.33 0.62 0.533 -20.48082 39.61169 _cons | 1022.573 44.93236 22.76 0.000 934.5073 1110.639 ------------------------------------------------------------------------------ Iteration 1: deviance = 306.253 Iteration 2: deviance = 305.9082 Iteration 3: deviance = 305.9062 Iteration 4: deviance = 305.9062 Iteration 5: deviance = 305.9062 Generalized linear models No. of obs = 340 Optimization : MQL Fisher scoring Residual df = 335 (IRLS EIM) Scale parameter = 1 Deviance = 305.9062256 (1/df) Deviance = .9131529 Pearson = 334.7424736 (1/df) Pearson = .9992313 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1646.791 ------------------------------------------------------------------------------ | EIM hp2work | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- bf7m | -.000056 .0001041 -0.54 0.591 -.00026 .000148 illw3 | -.8870307 .45488 -1.95 0.051 -1.778579 .0045177 avgcumdosew3 | -.0034059 .0290164 -0.12 0.907 -.060277 .0534652 ageXillw3 | .0233076 .0080353 2.90 0.004 .0075586 .0390565 _cons | -.9935662 .1388801 -7.15 0.000 -1.265766 -.7213662 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) Iteration 0: log likelihood = -3529.6624 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = 6.13e+07 Deviance = 2.07081e+10 (1/df) Deviance = 6.13e+07 Pearson = 2.07081e+10 (1/df) Pearson = 6.13e+07 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 20.77448 Log likelihood = -3529.662384 BIC = 2.07e+10 ------------------------------------------------------------------------------ | OIM bf8 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | 355.615 159.2444 2.23 0.026 43.5018 667.7282 _cons | 2733.121 466.7464 5.86 0.000 1818.315 3647.927 ------------------------------------------------------------------------------ Iteration 1: deviance = 302.6209 Iteration 2: deviance = 301.3338 Iteration 3: deviance = 301.2925 Iteration 4: deviance = 301.2924 Iteration 5: deviance = 301.2924 Generalized linear models No. of obs = 340 Optimization : MQL Fisher scoring Residual df = 335 (IRLS EIM) Scale parameter = 1 Deviance = 301.2924095 (1/df) Deviance = .8993803 Pearson = 336.2938827 (1/df) Pearson = 1.003862 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1651.404 ------------------------------------------------------------------------------ | EIM hp2work | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- bf8 | -.000027 .0000125 -2.15 0.031 -.0000516 -2.44e-06 illw3 | -.9474576 .4820727 -1.97 0.049 -1.892303 -.0026126 avgcumdosew3 | .0061317 .0278623 0.22 0.826 -.0484774 .0607408 ageXillw3 | .0256323 .008669 2.96 0.003 .0086413 .0426233 _cons | -1.016811 .0955984 -10.64 0.000 -1.204181 -.8294416 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) Iteration 0: log likelihood = -2696.8709 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = 456785.4 Deviance = 154393458.8 (1/df) Deviance = 456785.4 Pearson = 154393458.8 (1/df) Pearson = 456785.4 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 15.87571 Log likelihood = -2696.870867 BIC = 1.54e+08 ------------------------------------------------------------------------------ | OIM bf15m | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | -3.628301 13.7502 -0.26 0.792 -30.57819 23.32159 _cons | 115.892 40.30193 2.88 0.004 36.90167 194.8823 ------------------------------------------------------------------------------ Iteration 1: deviance = 306.0016 Iteration 2: deviance = 305.6478 Iteration 3: deviance = 305.6457 Iteration 4: deviance = 305.6457 Generalized linear models No. of obs = 340 Optimization : MQL Fisher scoring Residual df = 335 (IRLS EIM) Scale parameter = 1 Deviance = 305.6457012 (1/df) Deviance = .9123752 Pearson = 333.5001091 (1/df) Pearson = .9955227 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1647.051 ------------------------------------------------------------------------------ | EIM hp2work | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- bf15m | .0000806 .000105 0.77 0.443 -.0001252 .0002864 illw3 | -.8957517 .4543388 -1.97 0.049 -1.786239 -.0052639 avgcumdosew3 | -.0042893 .0292684 -0.15 0.883 -.0616544 .0530759 ageXillw3 | .0235238 .0080267 2.93 0.003 .0077918 .0392559 _cons | -1.061944 .0973897 -10.90 0.000 -1.252824 -.871064 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) Iteration 0: log likelihood = -3469.0024 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = 4.29e+07 Deviance = 1.44935e+10 (1/df) Deviance = 4.29e+07 Pearson = 1.44935e+10 (1/df) Pearson = 4.29e+07 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 20.41766 Log likelihood = -3469.002409 BIC = 1.45e+10 ------------------------------------------------------------------------------ | OIM bf17 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | -17.08696 133.2235 -0.13 0.898 -278.2002 244.0263 _cons | 434.0573 390.4791 1.11 0.266 -331.2677 1199.382 ------------------------------------------------------------------------------ Iteration 1: deviance = 306.2652 Iteration 2: deviance = 305.7886 Iteration 3: deviance = 305.7001 Iteration 4: deviance = 305.5515 Iteration 5: deviance = 305.1672 Iteration 6: deviance = 305.0101 Iteration 7: deviance = 304.9255 Iteration 8: deviance = 304.8717 Iteration 9: deviance = 304.8247 Iteration 10: deviance = 304.7365 Iteration 11: deviance = 304.6723 Iteration 12: deviance = 304.6508 Iteration 13: deviance = 304.6429 Iteration 14: deviance = 304.6398 Iteration 15: deviance = 304.6384 Iteration 16: deviance = 304.6377 Iteration 17: deviance = 304.6373 Iteration 18: deviance = 304.637 Iteration 19: deviance = 304.6369 Iteration 20: deviance = 304.6368 Iteration 21: deviance = 304.6367 Iteration 22: deviance = 304.6366 Iteration 23: deviance = 304.6366 Iteration 24: deviance = 304.6365 Iteration 25: deviance = 304.6365 Iteration 26: deviance = 304.6365 Iteration 27: deviance = 304.6364 Iteration 28: deviance = 304.6364 Iteration 29: deviance = 304.6364 Iteration 30: deviance = 304.6364 Iteration 31: deviance = 304.6364 Iteration 32: deviance = 304.6364 Iteration 33: deviance = 304.6364 Iteration 34: deviance = 304.6364 Iteration 35: deviance = 304.6363 Iteration 36: deviance = 304.6363 Iteration 37: deviance = 304.6363 Iteration 38: deviance = 304.6363 Iteration 39: deviance = 304.6363 Iteration 40: deviance = 304.6363 Iteration 41: deviance = 304.6363 Iteration 42: deviance = 304.6363 Iteration 43: deviance = 304.6363 Iteration 44: deviance = 304.6363 Iteration 45: deviance = 304.6363 Iteration 46: deviance = 304.6363 Iteration 47: deviance = 304.6363 Iteration 48: deviance = 304.6363 Iteration 49: deviance = 304.6363 Iteration 50: deviance = 304.6363 Iteration 51: deviance = 304.6363 Iteration 52: deviance = 304.6363 Iteration 53: deviance = 304.6363 Iteration 54: deviance = 304.6363 Iteration 55: deviance = 304.6363 Iteration 56: deviance = 304.6363 Iteration 57: deviance = 304.6363 Iteration 58: deviance = 304.6363 Iteration 59: deviance = 304.6363 Iteration 60: deviance = 304.6363 Iteration 61: deviance = 304.6363 Iteration 62: deviance = 304.6363 Iteration 63: deviance = 304.6363 Iteration 64: deviance = 304.6363 Iteration 65: deviance = 304.6363 Iteration 66: deviance = 304.6363 Iteration 67: deviance = 304.6363 Iteration 68: deviance = 304.6363 Generalized linear models No. of obs = 340 Optimization : MQL Fisher scoring Residual df = 335 (IRLS EIM) Scale parameter = 1 Deviance = 304.636255 (1/df) Deviance = .909362 Pearson = 328.9419784 (1/df) Pearson = .9819164 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1648.061 ------------------------------------------------------------------------------ | EIM hp2work | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- bf17 | -.0061172 .0135397 -0.45 0.651 -.0326545 .0204201 illw3 | -.8919627 .4536997 -1.97 0.049 -1.781198 -.0027277 avgcumdosew3 | -.0045617 .029111 -0.16 0.875 -.0616181 .0524948 ageXillw3 | .023281 .0080101 2.91 0.004 .0075815 .0389804 _cons | -1.03774 .0956856 -10.85 0.000 -1.225281 -.8502001 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) Iteration 0: log likelihood = -1596.6648 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = 706.3908 Deviance = 238760.0795 (1/df) Deviance = 706.3908 Pearson = 238760.0795 (1/df) Pearson = 706.3908 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 9.403911 Log likelihood = -1596.664807 BIC = 236789.9 ------------------------------------------------------------------------------ | OIM bf20 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | -.1398753 .5407236 -0.26 0.796 -1.199674 .9199234 _cons | 70.35574 1.584865 44.39 0.000 67.24947 73.46202 ------------------------------------------------------------------------------ Iteration 1: deviance = 300.1457 Iteration 2: deviance = 299.0235 Iteration 3: deviance = 299.0152 Iteration 4: deviance = 299.0152 Iteration 5: deviance = 299.0152 Generalized linear models No. of obs = 340 Optimization : MQL Fisher scoring Residual df = 335 (IRLS EIM) Scale parameter = 1 Deviance = 299.0152272 (1/df) Deviance = .8925828 Pearson = 330.25436 (1/df) Pearson = .9858339 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1653.682 ------------------------------------------------------------------------------ | EIM hp2work | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- bf20 | .0088228 .003147 2.80 0.005 .0026548 .0149908 illw3 | -.7807362 .4376076 -1.78 0.074 -1.638431 .076959 avgcumdosew3 | -.0015929 .0300016 -0.05 0.958 -.060395 .0572092 ageXillw3 | .0206881 .0077194 2.68 0.007 .0055584 .0358178 _cons | -1.683938 .2508128 -6.71 0.000 -2.175522 -1.192354 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) Iteration 0: log likelihood = -3143.6434 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = 6325138 Deviance = 2137896613 (1/df) Deviance = 6325138 Pearson = 2137896613 (1/df) Pearson = 6325138 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 18.50378 Log likelihood = -3143.643356 BIC = 2.14e+09 ------------------------------------------------------------------------------ | OIM bf22 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | 72.68941 51.16675 1.42 0.155 -27.59557 172.9744 _cons | 2107.73 149.9701 14.05 0.000 1813.794 2401.666 ------------------------------------------------------------------------------ Iteration 1: deviance = 305.3026 Iteration 2: deviance = 304.9396 Iteration 3: deviance = 304.9374 Iteration 4: deviance = 304.9374 Iteration 5: deviance = 304.9374 Generalized linear models No. of obs = 340 Optimization : MQL Fisher scoring Residual df = 335 (IRLS EIM) Scale parameter = 1 Deviance = 304.9374153 (1/df) Deviance = .9102609 Pearson = 331.1091682 (1/df) Pearson = .9883856 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1647.759 ------------------------------------------------------------------------------ | EIM hp2work | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- bf22 | .0000371 .0000318 1.17 0.243 -.0000252 .0000993 illw3 | -.918145 .4518314 -2.03 0.042 -1.803718 -.0325717 avgcumdosew3 | -.006472 .0296204 -0.22 0.827 -.0645268 .0515829 ageXillw3 | .0231361 .0079661 2.90 0.004 .0075229 .0387493 _cons | -1.114315 .1113817 -10.00 0.000 -1.332619 -.8960105 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) Iteration 0: log likelihood = -3683.6189 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = 1.52e+08 Deviance = 5.12210e+10 (1/df) Deviance = 1.52e+08 Pearson = 5.12210e+10 (1/df) Pearson = 1.52e+08 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 21.68011 Log likelihood = -3683.618914 BIC = 5.12e+10 ------------------------------------------------------------------------------ | OIM bf29 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | 72.89759 250.4485 0.29 0.771 -417.9724 563.7676 _cons | 1316.168 734.0664 1.79 0.073 -122.5761 2754.911 ------------------------------------------------------------------------------ Iteration 1: deviance = 306.2986 Iteration 2: deviance = 305.9514 Iteration 3: deviance = 305.9494 Iteration 4: deviance = 305.9494 Generalized linear models No. of obs = 340 Optimization : MQL Fisher scoring Residual df = 335 (IRLS EIM) Scale parameter = 1 Deviance = 305.9493576 (1/df) Deviance = .9132817 Pearson = 332.9706028 (1/df) Pearson = .9939421 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1646.747 ------------------------------------------------------------------------------ | EIM hp2work | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- bf29 | 2.79e-06 5.58e-06 0.50 0.617 -8.15e-06 .0000137 illw3 | -.9120386 .4552478 -2.00 0.045 -1.804308 -.0197692 avgcumdosew3 | -.0047071 .0293276 -0.16 0.872 -.0621882 .052774 ageXillw3 | .0237101 .0080424 2.95 0.003 .0079473 .0394729 _cons | -1.052896 .0959692 -10.97 0.000 -1.240992 -.8647998 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) Iteration 0: log likelihood = -2661.1782 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = 370279 Deviance = 125154318.2 (1/df) Deviance = 370279 Pearson = 125154318.2 (1/df) Pearson = 370279 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 15.66575 Log likelihood = -2661.17822 BIC = 1.25e+08 ------------------------------------------------------------------------------ | OIM bf30 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | -8.740799 12.37991 -0.71 0.480 -33.00497 15.52337 _cons | 499.3279 36.2856 13.76 0.000 428.2095 570.4464 ------------------------------------------------------------------------------ Iteration 1: deviance = 302.7978 Iteration 2: deviance = 302.3054 Iteration 3: deviance = 302.3037 Iteration 4: deviance = 302.3037 Iteration 5: deviance = 302.3037 Generalized linear models No. of obs = 340 Optimization : MQL Fisher scoring Residual df = 335 (IRLS EIM) Scale parameter = 1 Deviance = 302.3036646 (1/df) Deviance = .902399 Pearson = 330.9769023 (1/df) Pearson = .9879908 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1650.393 ------------------------------------------------------------------------------ | EIM hp2work | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- bf30 | .0002605 .0001257 2.07 0.038 .0000141 .000507 illw3 | -.704577 .4520917 -1.56 0.119 -1.590661 .1815065 avgcumdosew3 | -.0017053 .0295427 -0.06 0.954 -.059608 .0561974 ageXillw3 | .0200764 .0079446 2.53 0.012 .0045054 .0356475 _cons | -1.198337 .1213319 -9.88 0.000 -1.436144 -.960531 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) Iteration 0: log likelihood = -658.90158 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = 2.840313 Deviance = 960.025842 (1/df) Deviance = 2.840313 Pearson = 960.025842 (1/df) Pearson = 2.840313 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 3.887656 Log likelihood = -658.9015808 BIC = -1010.158 ------------------------------------------------------------------------------ | OIM bf40 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | .0494693 .0342875 1.44 0.149 -.017733 .1166715 _cons | 2.083835 .1004969 20.74 0.000 1.886864 2.280805 ------------------------------------------------------------------------------ Iteration 1: deviance = 300.0331 Iteration 2: deviance = 299.3058 Iteration 3: deviance = 299.3023 Iteration 4: deviance = 299.3023 Iteration 5: deviance = 299.3023 Generalized linear models No. of obs = 340 Optimization : MQL Fisher scoring Residual df = 335 (IRLS EIM) Scale parameter = 1 Deviance = 299.302286 (1/df) Deviance = .8934397 Pearson = 332.1283637 (1/df) Pearson = .991428 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1653.394 ------------------------------------------------------------------------------ | EIM hp2work | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- bf40 | .1459653 .0519808 2.81 0.005 .0440849 .2478458 illw3 | -.8596898 .4456734 -1.93 0.054 -1.733194 .0138141 avgcumdosew3 | -.004707 .0285947 -0.16 0.869 -.0607516 .0513375 ageXillw3 | .0204911 .0078874 2.60 0.009 .005032 .0359502 _cons | -1.321598 .1388504 -9.52 0.000 -1.593739 -1.049456 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 359 . 360 . **** male mediators of dose paid employment: bf8, age, illw3 ageXillw3 361 . scalar wkMedMw3 = "bf8 age illw3 ageXillw3" 362 . 363 . title4 "Female mediator models for dose-paid employment" ------------------------------------------------------------------------------- Female mediator models for dose-paid employment ------------------------------------------------------------------------------- 364 . glm radhlw3 avgcumdosew3 if gender==2, fam(gaussian) link(identity) Iteration 0: log likelihood = -1798.7074 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = 1185.454 Deviance = 427948.9522 (1/df) Deviance = 1185.454 Pearson = 427948.9522 (1/df) Pearson = 1185.454 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 9.921253 Log likelihood = -1798.707367 BIC = 425821.1 ------------------------------------------------------------------------------ | OIM radhlw3 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | 2.751602 1.03038 2.67 0.008 .7320943 4.77111 _cons | 57.70689 2.190692 26.34 0.000 53.41321 62.00057 ------------------------------------------------------------------------------ 365 . glm hp2work radhlw3 if gender==2, fam(binomial) irls scale(dev) link(probit) Iteration 1: deviance = 395.05 Iteration 2: deviance = 394.6898 Iteration 3: deviance = 394.6898 Iteration 4: deviance = 394.6898 Generalized linear models No. of obs = 363 Optimization : MQL Fisher scoring Residual df = 361 (IRLS EIM) Scale parameter = 1 Deviance = 394.6897802 (1/df) Deviance = 1.093323 Pearson = 364.9268795 (1/df) Pearson = 1.010878 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1733.19 ------------------------------------------------------------------------------ | EIM hp2work | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- radhlw3 | .0091162 .0022772 4.00 0.000 .004653 .0135795 _cons | -1.244306 .1697735 -7.33 0.000 -1.577055 -.9115557 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 366 . glm age avgcumdosew3 if gender==2, fam(gaussian) link(identity) Iteration 0: log likelihood = -1408.064 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = 137.7687 Deviance = 49734.51399 (1/df) Deviance = 137.7687 Pearson = 49734.51399 (1/df) Pearson = 137.7687 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 7.768948 Log likelihood = -1408.06405 BIC = 47606.63 ------------------------------------------------------------------------------ | OIM age | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | 1.058366 .3512614 3.01 0.003 .3699069 1.746826 _cons | 48.94293 .7468173 65.54 0.000 47.47919 50.40666 ------------------------------------------------------------------------------ 367 . glm hp2work age if gender==2, fam(binomial) irls scale(dev) link(probit) Iteration 1: deviance = 372.7391 Iteration 2: deviance = 372.3711 Iteration 3: deviance = 372.3711 Iteration 4: deviance = 372.3711 Generalized linear models No. of obs = 363 Optimization : MQL Fisher scoring Residual df = 361 (IRLS EIM) Scale parameter = 1 Deviance = 372.3710546 (1/df) Deviance = 1.031499 Pearson = 375.1783727 (1/df) Pearson = 1.039275 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1755.508 ------------------------------------------------------------------------------ | EIM hp2work | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0398718 .0066503 6.00 0.000 .0268375 .052906 _cons | -2.722762 .3594297 -7.58 0.000 -3.427231 -2.018292 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 368 . glm illw3 avgcumdosew3 if gender==2, fam(gaussian) link(identity) Iteration 0: log likelihood = -562.81042 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = 1.308042 Deviance = 472.2033151 (1/df) Deviance = 1.308042 Pearson = 472.2033151 (1/df) Pearson = 1.308042 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 3.111903 Log likelihood = -562.8104237 BIC = -1655.676 ------------------------------------------------------------------------------ | OIM illw3 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | .1284565 .0342268 3.75 0.000 .0613733 .1955398 _cons | .5563644 .0727696 7.65 0.000 .4137387 .6989902 ------------------------------------------------------------------------------ 369 . glm hp2work illw3 if gender==2, fam(binomial) irls scale(dev) link(probit) Iteration 1: deviance = 410.7265 Iteration 2: deviance = 410.1776 Iteration 3: deviance = 410.1774 Iteration 4: deviance = 410.1774 Generalized linear models No. of obs = 363 Optimization : MQL Fisher scoring Residual df = 361 (IRLS EIM) Scale parameter = 1 Deviance = 410.1774283 (1/df) Deviance = 1.136226 Pearson = 362.4869354 (1/df) Pearson = 1.004119 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1717.702 ------------------------------------------------------------------------------ | EIM hp2work | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- illw3 | .1024787 .0628325 1.63 0.103 -.0206709 .2256282 _cons | -.7324278 .090138 -8.13 0.000 -.909095 -.5557606 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 370 . 371 . * interaction of ageXillw3 impacts paid employment as mediator and moderator 372 . glm illw3 avgcumdosew3 if gender==2, fam(gaussian) link(identity) Iteration 0: log likelihood = -562.81042 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = 1.308042 Deviance = 472.2033151 (1/df) Deviance = 1.308042 Pearson = 472.2033151 (1/df) Pearson = 1.308042 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 3.111903 Log likelihood = -562.8104237 BIC = -1655.676 ------------------------------------------------------------------------------ | OIM illw3 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | .1284565 .0342268 3.75 0.000 .0613733 .1955398 _cons | .5563644 .0727696 7.65 0.000 .4137387 .6989902 ------------------------------------------------------------------------------ 373 . glm hp2work ageXillw3 illw3 avgcumdosew3 if gender==2, fam(binomial) irls sca > le(dev) link(probit) Iteration 1: deviance = 392.5389 Iteration 2: deviance = 391.8976 Iteration 3: deviance = 391.8969 Iteration 4: deviance = 391.8969 Iteration 5: deviance = 391.8969 Generalized linear models No. of obs = 363 Optimization : MQL Fisher scoring Residual df = 359 (IRLS EIM) Scale parameter = 1 Deviance = 391.8968943 (1/df) Deviance = 1.091635 Pearson = 370.0301694 (1/df) Pearson = 1.030725 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1724.194 ------------------------------------------------------------------------------ | EIM hp2work | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- ageXillw3 | .0187409 .0060019 3.12 0.002 .0069775 .0305044 illw3 | -.9562978 .343609 -2.78 0.005 -1.629759 -.2828366 avgcumdosew3 | .0662197 .0429198 1.54 0.123 -.0179015 .150341 _cons | -.79789 .1001619 -7.97 0.000 -.9942036 -.6015764 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 374 . 375 . 376 . 377 . 378 . 379 . 380 . title4 "bf8 is a male mediator of paid employment" ------------------------------------------------------------------------------- bf8 is a male mediator of paid employment ------------------------------------------------------------------------------- 381 . local w3bf bf1 bf4 bf2 bf4m bf5m bf7m bf8 bf15m bf17 bf20 bf22 bf29 bf30 bf40 382 . foreach var in `w3bf'{ 2. glm `var' avgcumdosew3 if gender==2, family(gaussian) link(identity) 3. glm hp2work `var' illw3 avgcumdosew3 if gender==2, family(binomial) irls > scale(dev) link(probit) 4. 383 . 384 . } Iteration 0: log likelihood = -1647.6213 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = 515.6618 Deviance = 186153.9233 (1/df) Deviance = 515.6618 Pearson = 186153.9233 (1/df) Pearson = 515.6618 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 9.088823 Log likelihood = -1647.621315 BIC = 184026 ------------------------------------------------------------------------------ | OIM bf1 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | 1.403532 .6795752 2.07 0.039 .0715889 2.735475 _cons | 37.53913 1.444846 25.98 0.000 34.70728 40.37097 ------------------------------------------------------------------------------ Iteration 1: deviance = 400.7858 Iteration 2: deviance = 400.3649 Iteration 3: deviance = 400.3647 Iteration 4: deviance = 400.3647 Generalized linear models No. of obs = 363 Optimization : MQL Fisher scoring Residual df = 359 (IRLS EIM) Scale parameter = 1 Deviance = 400.3647141 (1/df) Deviance = 1.115222 Pearson = 362.3414503 (1/df) Pearson = 1.009308 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1715.726 ------------------------------------------------------------------------------ | EIM hp2work | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- bf1 | .0075263 .0035043 2.15 0.032 .0006579 .0143947 illw3 | .0566488 .0651687 0.87 0.385 -.0710796 .1843771 avgcumdosew3 | .0748818 .0422562 1.77 0.076 -.007939 .1577025 _cons | -1.099425 .1680193 -6.54 0.000 -1.428737 -.7701136 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) Iteration 0: log likelihood = -1109.6569 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = 26.6146 Deviance = 9607.869105 (1/df) Deviance = 26.6146 Pearson = 9607.869105 (1/df) Pearson = 26.6146 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 6.124831 Log likelihood = -1109.656873 BIC = 7479.99 ------------------------------------------------------------------------------ | OIM bf4 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | -.4386292 .1543885 -2.84 0.004 -.7412252 -.1360333 _cons | 11.01475 .3282456 33.56 0.000 10.3714 11.6581 ------------------------------------------------------------------------------ Iteration 1: deviance = 368.0458 Iteration 2: deviance = 367.7561 Iteration 3: deviance = 367.7558 Iteration 4: deviance = 367.7558 Generalized linear models No. of obs = 363 Optimization : MQL Fisher scoring Residual df = 359 (IRLS EIM) Scale parameter = 1 Deviance = 367.7557582 (1/df) Deviance = 1.024389 Pearson = 356.2171479 (1/df) Pearson = .9922483 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1748.335 ------------------------------------------------------------------------------ | EIM hp2work | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- bf4 | -.0912403 .015392 -5.93 0.000 -.1214082 -.0610725 illw3 | -.0442384 .0678425 -0.65 0.514 -.1772072 .0887305 avgcumdosew3 | .0676603 .041034 1.65 0.099 -.0127647 .1480854 _cons | .179333 .1922188 0.93 0.351 -.1974089 .5560748 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) Iteration 0: log likelihood = -3335.9695 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = 5652705 Deviance = 2040626644 (1/df) Deviance = 5652705 Pearson = 2040626644 (1/df) Pearson = 5652705 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 18.39102 Log likelihood = -3335.969457 BIC = 2.04e+09 ------------------------------------------------------------------------------ | OIM bf2 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | -14.66006 71.15136 -0.21 0.837 -154.1142 124.794 _cons | 2486.833 151.275 16.44 0.000 2190.34 2783.327 ------------------------------------------------------------------------------ Iteration 1: deviance = 400.7561 Iteration 2: deviance = 400.3769 Iteration 3: deviance = 400.3768 Iteration 4: deviance = 400.3768 Generalized linear models No. of obs = 363 Optimization : MQL Fisher scoring Residual df = 359 (IRLS EIM) Scale parameter = 1 Deviance = 400.3767744 (1/df) Deviance = 1.115256 Pearson = 362.4243987 (1/df) Pearson = 1.009539 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1715.714 ------------------------------------------------------------------------------ | EIM hp2work | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- bf2 | .0000693 .0000321 2.16 0.031 6.50e-06 .0001322 illw3 | .0579184 .0652264 0.89 0.375 -.069923 .1857598 avgcumdosew3 | .0863439 .041937 2.06 0.040 .0041489 .168539 _cons | -.9883744 .1289169 -7.67 0.000 -1.241047 -.7357019 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) Iteration 0: log likelihood = -1141.3116 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = 31.68572 Deviance = 11438.54371 (1/df) Deviance = 31.68572 Pearson = 11438.54371 (1/df) Pearson = 31.68572 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 6.299237 Log likelihood = -1141.311602 BIC = 9310.664 ------------------------------------------------------------------------------ | OIM bf4m | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | -.441173 .1684561 -2.62 0.009 -.771341 -.1110051 _cons | 18.82772 .3581548 52.57 0.000 18.12575 19.52969 ------------------------------------------------------------------------------ Iteration 1: deviance = 376.2521 Iteration 2: deviance = 376.1219 Iteration 3: deviance = 376.1216 Iteration 4: deviance = 376.1216 Iteration 5: deviance = 376.1216 Generalized linear models No. of obs = 363 Optimization : MQL Fisher scoring Residual df = 359 (IRLS EIM) Scale parameter = 1 Deviance = 376.1216056 (1/df) Deviance = 1.047692 Pearson = 352.597962 (1/df) Pearson = .982167 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1739.969 ------------------------------------------------------------------------------ | EIM hp2work | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- bf4m | -.0718043 .0138855 -5.17 0.000 -.0990193 -.0445893 illw3 | -.0199722 .06741 -0.30 0.767 -.1520934 .112149 avgcumdosew3 | .070842 .0412807 1.72 0.086 -.0100667 .1517506 _cons | .5296971 .2777901 1.91 0.057 -.0147615 1.074156 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) Iteration 0: log likelihood = -2474.3315 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = 49036.9 Deviance = 17702319.75 (1/df) Deviance = 49036.9 Pearson = 17702319.75 (1/df) Pearson = 49036.9 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 13.6437 Log likelihood = -2474.331507 BIC = 1.77e+07 ------------------------------------------------------------------------------ | OIM bf5m | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | 11.51759 6.626993 1.74 0.082 -1.471077 24.50626 _cons | 146.1251 14.08966 10.37 0.000 118.5098 173.7403 ------------------------------------------------------------------------------ Iteration 1: deviance = 406.0898 Iteration 2: deviance = 405.5971 Iteration 3: deviance = 405.5969 Iteration 4: deviance = 405.5969 Iteration 5: deviance = 405.5969 Generalized linear models No. of obs = 363 Optimization : MQL Fisher scoring Residual df = 359 (IRLS EIM) Scale parameter = 1 Deviance = 405.5968814 (1/df) Deviance = 1.129796 Pearson = 362.2771278 (1/df) Pearson = 1.009128 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1710.494 ------------------------------------------------------------------------------ | EIM hp2work | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- bf5m | .0000253 .000346 0.07 0.942 -.0006528 .0007034 illw3 | .0757307 .0648804 1.17 0.243 -.0514326 .202894 avgcumdosew3 | .0816456 .0425803 1.92 0.055 -.0018103 .1651014 _cons | -.8200136 .1118444 -7.33 0.000 -1.039225 -.6008026 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) Iteration 0: log likelihood = -2919.8803 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = 570998.8 Deviance = 206130564.2 (1/df) Deviance = 570998.8 Pearson = 206130564.2 (1/df) Pearson = 570998.8 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 16.09851 Log likelihood = -2919.880264 BIC = 2.06e+08 ------------------------------------------------------------------------------ | OIM bf7m | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | -9.882168 22.61375 -0.44 0.662 -54.20431 34.43997 _cons | 1192.342 48.07913 24.80 0.000 1098.109 1286.575 ------------------------------------------------------------------------------ Iteration 1: deviance = 405.7923 Iteration 2: deviance = 405.3032 Iteration 3: deviance = 405.303 Iteration 4: deviance = 405.303 Generalized linear models No. of obs = 363 Optimization : MQL Fisher scoring Residual df = 359 (IRLS EIM) Scale parameter = 1 Deviance = 405.3030164 (1/df) Deviance = 1.128978 Pearson = 362.1616249 (1/df) Pearson = 1.008807 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1710.788 ------------------------------------------------------------------------------ | EIM hp2work | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- bf7m | -.0000542 .0001026 -0.53 0.598 -.0002553 .000147 illw3 | .0715496 .0653324 1.10 0.273 -.0564996 .1995988 avgcumdosew3 | .0819746 .0424018 1.93 0.053 -.0011314 .1650805 _cons | -.7500788 .1604213 -4.68 0.000 -1.064499 -.4356588 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) Iteration 0: log likelihood = -3888.8378 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = 1.19e+08 Deviance = 4.29211e+10 (1/df) Deviance = 1.19e+08 Pearson = 4.29211e+10 (1/df) Pearson = 1.19e+08 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 21.43712 Log likelihood = -3888.83781 BIC = 4.29e+10 ------------------------------------------------------------------------------ | OIM bf8 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | 474.4107 326.3149 1.45 0.146 -165.1547 1113.976 _cons | 5499.472 693.7785 7.93 0.000 4139.691 6859.253 ------------------------------------------------------------------------------ Iteration 1: deviance = 406.001 Iteration 2: deviance = 405.5105 Iteration 3: deviance = 405.5103 Iteration 4: deviance = 405.5103 Generalized linear models No. of obs = 363 Optimization : MQL Fisher scoring Residual df = 359 (IRLS EIM) Scale parameter = 1 Deviance = 405.510287 (1/df) Deviance = 1.129555 Pearson = 362.2128945 (1/df) Pearson = 1.00895 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1710.58 ------------------------------------------------------------------------------ | EIM hp2work | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- bf8 | 2.02e-06 6.97e-06 0.29 0.772 -.0000116 .0000157 illw3 | .0763832 .0648403 1.18 0.239 -.0507015 .2034678 avgcumdosew3 | .0810208 .0425231 1.91 0.057 -.0023229 .1643645 _cons | -.8280872 .1080894 -7.66 0.000 -1.039939 -.6162358 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) Iteration 0: log likelihood = -2865.4294 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = 423004.2 Deviance = 152704509.3 (1/df) Deviance = 423004.2 Pearson = 152704509.3 (1/df) Pearson = 423004.2 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 15.79851 Log likelihood = -2865.42935 BIC = 1.53e+08 ------------------------------------------------------------------------------ | OIM bf15m | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | -16.31159 19.46379 -0.84 0.402 -54.45991 21.83674 _cons | 119.7135 41.38199 2.89 0.004 38.60629 200.8207 ------------------------------------------------------------------------------ Iteration 1: deviance = 403.0022 Iteration 2: deviance = 401.3838 Iteration 3: deviance = 400.8551 Iteration 4: deviance = 400.4877 Iteration 5: deviance = 400.1075 Iteration 6: deviance = 399.7784 Iteration 7: deviance = 399.6168 Iteration 8: deviance = 399.5208 Iteration 9: deviance = 399.4454 Iteration 10: deviance = 399.3984 Iteration 11: deviance = 399.3819 Iteration 12: deviance = 399.3763 Iteration 13: deviance = 399.3744 Iteration 14: deviance = 399.3737 Iteration 15: deviance = 399.3734 Iteration 16: deviance = 399.3733 Iteration 17: deviance = 399.3732 Iteration 18: deviance = 399.3732 Iteration 19: deviance = 399.3732 Iteration 20: deviance = 399.3732 Iteration 21: deviance = 399.3732 Iteration 22: deviance = 399.3732 Iteration 23: deviance = 399.3732 Iteration 24: deviance = 399.3732 Iteration 25: deviance = 399.3732 Iteration 26: deviance = 399.3732 Iteration 27: deviance = 399.3732 Iteration 28: deviance = 399.3732 Iteration 29: deviance = 399.3732 Generalized linear models No. of obs = 363 Optimization : MQL Fisher scoring Residual df = 359 (IRLS EIM) Scale parameter = 1 Deviance = 399.3731679 (1/df) Deviance = 1.11246 Pearson = 350.463985 (1/df) Pearson = .9762228 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1716.717 ------------------------------------------------------------------------------ | EIM hp2work | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- bf15m | -.0185517 .1405693 -0.13 0.895 -.2940624 .2569591 illw3 | .0637593 .064584 0.99 0.324 -.0628231 .1903417 avgcumdosew3 | .0795244 .0419333 1.90 0.058 -.0026634 .1617122 _cons | -.779424 .1009676 -7.72 0.000 -.9773168 -.5815312 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) Iteration 0: log likelihood = -3826.3372 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = 8.43e+07 Deviance = 3.04172e+10 (1/df) Deviance = 8.43e+07 Pearson = 3.04172e+10 (1/df) Pearson = 8.43e+07 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 21.09277 Log likelihood = -3826.337161 BIC = 3.04e+10 ------------------------------------------------------------------------------ | OIM bf17 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | -210.5363 274.7014 -0.77 0.443 -748.9411 327.8686 _cons | 1283.326 584.043 2.20 0.028 138.6227 2428.029 ------------------------------------------------------------------------------ Iteration 1: deviance = 404.4868 Iteration 2: deviance = 403.3612 Iteration 3: deviance = 403.0401 Iteration 4: deviance = 402.7883 Iteration 5: deviance = 402.5042 Iteration 6: deviance = 402.3328 Iteration 7: deviance = 402.2311 Iteration 8: deviance = 402.1401 Iteration 9: deviance = 402.0781 Iteration 10: deviance = 402.0571 Iteration 11: deviance = 402.05 Iteration 12: deviance = 402.0475 Iteration 13: deviance = 402.0467 Iteration 14: deviance = 402.0463 Iteration 15: deviance = 402.0462 Iteration 16: deviance = 402.0462 Iteration 17: deviance = 402.0462 Iteration 18: deviance = 402.0461 Iteration 19: deviance = 402.0461 Iteration 20: deviance = 402.0461 Iteration 21: deviance = 402.0461 Iteration 22: deviance = 402.0461 Iteration 23: deviance = 402.0461 Iteration 24: deviance = 402.0461 Iteration 25: deviance = 402.0461 Generalized linear models No. of obs = 363 Optimization : MQL Fisher scoring Residual df = 359 (IRLS EIM) Scale parameter = 1 Deviance = 402.0461284 (1/df) Deviance = 1.119906 Pearson = 355.4109876 (1/df) Pearson = .9900028 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1714.044 ------------------------------------------------------------------------------ | EIM hp2work | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- bf17 | -.0009418 .0098647 -0.10 0.924 -.0202762 .0183926 illw3 | .0690879 .0646796 1.07 0.285 -.0576818 .1958576 avgcumdosew3 | .0802034 .0421293 1.90 0.057 -.0023685 .1627752 _cons | -.7949403 .1007866 -7.89 0.000 -.9924784 -.5974022 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) Iteration 0: log likelihood = -1708.7675 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = 722.2307 Deviance = 260725.2848 (1/df) Deviance = 722.2307 Pearson = 260725.2848 (1/df) Pearson = 722.2307 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 9.425716 Log likelihood = -1708.767472 BIC = 258597.4 ------------------------------------------------------------------------------ | OIM bf20 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | 1.430073 .8042536 1.78 0.075 -.1462347 3.006382 _cons | 75.65323 1.709925 44.24 0.000 72.30184 79.00463 ------------------------------------------------------------------------------ Iteration 1: deviance = 400.9177 Iteration 2: deviance = 400.4591 Iteration 3: deviance = 400.4589 Iteration 4: deviance = 400.4589 Generalized linear models No. of obs = 363 Optimization : MQL Fisher scoring Residual df = 359 (IRLS EIM) Scale parameter = 1 Deviance = 400.4588662 (1/df) Deviance = 1.115484 Pearson = 362.8847271 (1/df) Pearson = 1.010821 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1715.632 ------------------------------------------------------------------------------ | EIM hp2work | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- bf20 | .0064287 .0030571 2.10 0.035 .0004369 .0124206 illw3 | .0564777 .0651612 0.87 0.386 -.0712358 .1841913 avgcumdosew3 | .0763386 .0422654 1.81 0.071 -.0065001 .1591772 _cons | -1.303581 .2556066 -5.10 0.000 -1.804561 -.8026017 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) Iteration 0: log likelihood = -3441.3735 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = 1.01e+07 Deviance = 3647330298 (1/df) Deviance = 1.01e+07 Pearson = 3647330298 (1/df) Pearson = 1.01e+07 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 18.97175 Log likelihood = -3441.373501 BIC = 3.65e+09 ------------------------------------------------------------------------------ | OIM bf22 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | 198.9575 95.12376 2.09 0.036 12.51832 385.3966 _cons | 3099.215 202.2427 15.32 0.000 2702.826 3495.603 ------------------------------------------------------------------------------ Iteration 1: deviance = 404.7126 Iteration 2: deviance = 404.2497 Iteration 3: deviance = 404.2495 Iteration 4: deviance = 404.2495 Generalized linear models No. of obs = 363 Optimization : MQL Fisher scoring Residual df = 359 (IRLS EIM) Scale parameter = 1 Deviance = 404.2495058 (1/df) Deviance = 1.126043 Pearson = 361.0837357 (1/df) Pearson = 1.005804 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1711.841 ------------------------------------------------------------------------------ | EIM hp2work | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- bf22 | .0000268 .0000236 1.14 0.256 -.0000194 .000073 illw3 | .0662768 .0652813 1.02 0.310 -.0616722 .1942257 avgcumdosew3 | .0787126 .0424878 1.85 0.064 -.004562 .1619871 _cons | -.8976713 .1234173 -7.27 0.000 -1.139565 -.6557778 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) Iteration 0: log likelihood = -3484.9822 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = 1.28e+07 Deviance = 4637909003 (1/df) Deviance = 1.28e+07 Pearson = 4637909003 (1/df) Pearson = 1.28e+07 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 19.21202 Log likelihood = -3484.982169 BIC = 4.64e+09 ------------------------------------------------------------------------------ | OIM bf29 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | 40.03151 107.2661 0.37 0.709 -170.2062 250.2692 _cons | 265.9396 228.0586 1.17 0.244 -181.0471 712.9263 ------------------------------------------------------------------------------ Iteration 1: deviance = 405.4201 Iteration 2: deviance = 404.937 Iteration 3: deviance = 404.9369 Iteration 4: deviance = 404.9369 Generalized linear models No. of obs = 363 Optimization : MQL Fisher scoring Residual df = 359 (IRLS EIM) Scale parameter = 1 Deviance = 404.9368816 (1/df) Deviance = 1.127958 Pearson = 362.1381099 (1/df) Pearson = 1.008741 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1711.154 ------------------------------------------------------------------------------ | EIM hp2work | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- bf29 | .000015 .0000199 0.75 0.452 -.0000241 .000054 illw3 | .0693319 .0654643 1.06 0.290 -.0589757 .1976395 avgcumdosew3 | .0823559 .0423081 1.95 0.052 -.0005665 .1652783 _cons | -.8176021 .1003576 -8.15 0.000 -1.014299 -.6209049 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) Iteration 0: log likelihood = -2855.9026 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = 401373.8 Deviance = 144895947.3 (1/df) Deviance = 401373.8 Pearson = 144895947.3 (1/df) Pearson = 401373.8 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 15.74602 Log likelihood = -2855.902622 BIC = 1.45e+08 ------------------------------------------------------------------------------ | OIM bf30 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | 45.42508 18.95962 2.40 0.017 8.264914 82.58525 _cons | 474.094 40.31007 11.76 0.000 395.0877 553.1003 ------------------------------------------------------------------------------ Iteration 1: deviance = 403.2568 Iteration 2: deviance = 402.8398 Iteration 3: deviance = 402.8396 Iteration 4: deviance = 402.8396 Iteration 5: deviance = 402.8396 Generalized linear models No. of obs = 363 Optimization : MQL Fisher scoring Residual df = 359 (IRLS EIM) Scale parameter = 1 Deviance = 402.8396329 (1/df) Deviance = 1.122116 Pearson = 362.9011676 (1/df) Pearson = 1.010867 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1713.251 ------------------------------------------------------------------------------ | EIM hp2work | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- bf30 | .0001877 .0001196 1.57 0.116 -.0000466 .0004221 illw3 | .0850723 .065274 1.30 0.192 -.0428624 .2130069 avgcumdosew3 | .0727348 .0430132 1.69 0.091 -.0115696 .1570391 _cons | -.9155104 .1202543 -7.61 0.000 -1.151204 -.6798163 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) Iteration 0: log likelihood = -818.14796 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = 5.340664 Deviance = 1927.979854 (1/df) Deviance = 5.340664 Pearson = 1927.979854 (1/df) Pearson = 5.340664 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 4.518722 Log likelihood = -818.1479598 BIC = -199.8996 ------------------------------------------------------------------------------ | OIM bf40 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | .152897 .0691596 2.21 0.027 .0173466 .2884474 _cons | 2.981537 .1470404 20.28 0.000 2.693343 3.269731 ------------------------------------------------------------------------------ Iteration 1: deviance = 401.3653 Iteration 2: deviance = 400.9889 Iteration 3: deviance = 400.9888 Iteration 4: deviance = 400.9888 Generalized linear models No. of obs = 363 Optimization : MQL Fisher scoring Residual df = 359 (IRLS EIM) Scale parameter = 1 Deviance = 400.9887605 (1/df) Deviance = 1.11696 Pearson = 359.9660415 (1/df) Pearson = 1.002691 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1715.102 ------------------------------------------------------------------------------ | EIM hp2work | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- bf40 | .0689094 .0331691 2.08 0.038 .0038992 .1339195 illw3 | .0376887 .0670381 0.56 0.574 -.0937035 .1690809 avgcumdosew3 | .0782343 .0423534 1.85 0.065 -.0047769 .1612455 _cons | -1.010896 .13795 -7.33 0.000 -1.281273 -.7405191 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 385 . * Saving mediators as scalars for Dose=work relationship 386 . **** female mediators of dose-paid employment: radhlw3, age, bf40, bf4m, bf4, > bf1 387 . scalar wkMedFw3 = "radhlw3 age bf40 bf4m bf1" 388 . scalar list VactnMedFw3 = age illw3 radhlw3 VactnMedMw3 = age illw3 VacatnModFw3 = none MainEffVactnFw3 = age radhlw3 deaw3 SigDoseVactnFw3 = no vactnModMw3 = none MainEffVactnMw3 = age bf7m radhlw3 SigDoseVactnMw3 = no sxLifeMedFw3 = age bf4 bf4m sxLifeMedMw3 = age illw3 InthbModFw3 = none MainEffInthbFw3 = age radhlw3 bf4 SigdoseInthbFw3 = no InthbMw3 = none MainEffInthbMw3 = age radhlw3 shfamw3 SigDoseInthbMw3 = no sxlifeMedFw3 = age illw3 radhlw3 bf4 bf4m sxlifeMedMw3 = age illw3 sxlifeModFw3 = none MainEffsxlifeFw3 = age radhlw3 bf4 bf4m shrelaw3 shfamw3 SigDoseSxlifeFw3 = no sxlifeModMw3 = none SigDosesxlifeMw3 = no MainEffsxlifeMw3 = age bf4 illw3 radhlw3 PrbfmhmMedFw3 = age bf4 PrbfmhmMedMw3 = age PrbfmhmModFw3 = none MainEffPrbfmhmFw3 = age bf4 bf40 SigDosePrbfmhmFw3 = no PrbfmhmModw3 = none SigDosePrbfmhmMw3 = no SigDosePrbfhmMw3 = no MainEffPrbfhmMw3 = bf1 bf4 dvcew3 bf7m ProbsocMedFw3 = age radhlw3 ProbsocMedMw3 = age ProbsocModFw3 = none MainEffProbSocFw3 = age radhlw3 illw3 Shrelaw3 avgcumodsew3 SigDoseProbsocFw3 = yes ProbSocModMw3 = none SigDoseProbsocMw3 = no MainEffPrbsocMw3 = age radhlw3 shjobw3 hmcareMedFw3 = age illw3 hmcareMedMw3 = age illw3 hmcareModFw3 = none SigdoseHmcareFw3 = no hmcareModMw3 = none MainEffhmcareMw3 = none SigDoseHmcareMw3 = no wkMedFw3 = radhlw3 age bf40 bf4m bf1 wkMedMw3 = bf8 age illw3 ageXillw3 wkModFw3 = none wkModMw3 = none MainEffwkFw3 = age MainEffwkMw3 = workM: age bf8 illw3 shjobw3 SigDoseWKMw3 = no SigDoseWkFw3 = no medsigFw2 = 1 wkMedMw2 = bf8 age illw2 VactnMedFw2 = age illw2 radhlw2 VactnMedMw2 = age illw2 VacatnModFw2 = none MainEffVactnFw2 = age radhlw2 deaw2 SigDoseVactnFw2 = no vactnModMw2 = none MainEffVactnMw2 = age bf7m radhlw2 SigDoseVactnMw2 = no sxLifeMedFw2 = age bf4 bf4m sxLifeMedMw2 = age illw2 InthbModFw2 = none MainEffInthbFw2 = age radhlw2 bf4 SigdoseInthbFw2 = no InthbMw2 = none MainEffInthbMw2 = age radhlw2 shfamw2 SigDoseInthbMw2 = no sxlifeMedFw2 = age illw2 radhlw2 bf4 bf4m sxlifeMedMw2 = age illw2 sxlifeModFw2 = none MainEffsxlifeFw2 = age radhlw2 bf4 bf4m shrelaw2 shfamw2 SigDoseSxlifeFw2 = no sxlifeModMw2 = none SigDosesxlifeMw2 = no MainEffsxlifeMw2 = age bf4 illw2 radhlw2 PrbfmhmMedFw2 = age bf4 PrbfmhmMedMw2 = age PrbfmhmModFw2 = none MainEffPrbfmhmFw2 = age bf4 bf40 SigDosePrbfmhmFw2 = no PrbfmhmModw2 = none SigDosePrbfmhmMw2 = no SigDosePrbfhmMw2 = no MainEffPrbfhmMw2 = bf1 bf4 dvcew2 bf7m ProbsocMedFw2 = age radhlw2 ProbsocMedMw2 = age ProbsocModFw2 = none MainEffProbSocFw2 = age radhlw2 illw2 Shrelaw2 avgcumodsew2 SigDoseProbsocFw2 = yes ProbSocModMw2 = none SigDoseProbsocMw2 = no MainEffPrbsocMw2 = age radhlw2 shjobw2 hmcareMedFw2 = age illw2 hmcareMedMw2 = age illw2 hmcareModFw2 = none SigDoseWKFw2 = 0 SigdoseHmcareFw2 = no hmcareModMw2 = none MainEffhmcareMw2 = none SigDoseHmcareMw2 = no wkMedFw2 = radhlw2 age bf40 bf4m bf1 wkModFw2 = none wkModMw2 = none MainEffwkFw2 = age MainEffwkMw2 = workM: age bf8 illw2 shjobw2 SigDoseWKMw2 = no SigDoseWkFw2 = no hmcrMedFw1 = age icdxcnt shjobw1 bf4 BSIsoma WHPpain WHPsleep WHPel hmcrMedMw1 = age MainEffhmcrFw1 = illw1 age SigDosehmcrFw1 = no hmcrModMw1 = none MainEffhmcrMw1 = age shjobw1 SigDosehmcrMw1 = no wkMedFw1 = age b4 MainEffwkFw1 = age MainEffwkMw1 = age wkMedMw1 = bf40 WkMedMw1 = none WkModFw1 = none WKModMw1 = none SigDoseWkMw1 = no SigDoseWkFw1 = no SigDoseFw1 = no wkModFw1 = none wkModMw1 = none medsigFw1 = 1 prbsocnumMAsig = 8 389 . 390 . 391 . 392 . 393 . 394 . *xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx > xxx 395 . *------ Chunk 3 Dose=> hp2hmcare impact for males and females 396 . *xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx > xxx 397 . 398 . title "2. Wave 3 part2 H1: dose home care relationship " /// > " Wave 3 Dose - HP2home care Main effects identification" ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** 2. Wave 3 part2 H1: dose home care relationship ***** ***** Wave 3 Dose - HP2home care Main effects identification ***** ***** ***** ***** ***** ***** 1 Jul 2012 20:36:21 ***** ******************************************************************************* ******************************************************************************* 399 . 400 . * review of general model for men and women 401 . 402 . forvalues j=3/3 { 2. set more off 3. 403 . des age educ1-educ7 marrw`j'1-marrw`j'6 inc1w`j'-inc4w`j' /// > bf1 bf4 bf9 bf11 bf4m bf15m bf30 bf40 4. 404 . foreach var in HP2hmcare { 5. 405 . forvalues k=1/2 { 6. local w3bf bf1 bf4 bf2 bf4m bf5m bf7m bf8 bf15m bf17 bf20 bf22 bf29 bf30 > bf40 7. title "chunk 3 H1 test pt 2 :Gender= `k' model Wave = `j' for `e(dep > var)' " 8. di _skip(4) 9. 406 . 407 . xi: logistic `var' age i.educ occ1w`j'-occ8w`j' /// > marrw`j'1- marrw`j'3 marrw`j'5-marrw`j'6 inc1w`j'-inc4w`j' // > / > radhlw`j' havmil avgcumdosew`j' `w`j'bf' /// > deaw`j' dvcew`j' sepaw`j' accdw`j' movew`j' radhlw3 /// > illw`j' shfamw`j' shhlw`j' shjobw`j' shrelaw`j' suprtw`j' suc > hrw`j' /// > havmilsq if gender==`k', coef nolog difficult iterate(50) 10. estat class 11. estat gof 12. fitstat 13. } 14. } 15. } storage display value variable name type format label variable label ------------------------------------------------------------------------------- age double %8.0g * Respondent's age educ1 byte %8.0g educ==1. did not graduate high school educ2 byte %8.0g educ==2. graduated high school educ3 byte %8.0g educ==3. technical degree educ4 byte %8.0g educ==4. did not finish college/bachelor's educ5 byte %8.0g educ==5. graduated college/bachelor's educ6 byte %8.0g educ==6. finished specialist/master's degree educ7 byte %8.0g educ==7. doctor of science/phd marrw31 byte %8.0g marrw3==1. single marrw32 byte %8.0g marrw3==2. cohabitating marrw33 byte %8.0g marrw3==3. married marrw34 byte %8.0g marrw3==4. separated marrw35 byte %8.0g marrw3==5. divorced marrw36 byte %8.0g marrw3==6. widowed inc1w3 double %15.0g LABJ Income is not sufficient for basic neccessities NOW inc2w3 double %15.0g LABJ Income is just sufficient for basic neccessities NOW inc3w3 double %15.0g LABJ Income is sufficient for basics plus extra purchases/savings NOW inc4w3 double %15.0g LABJ Income allows to comfortably afford luxury items NOW bf1 float %9.0g bf1 = max(0, kzchorn - 40) bf4 float %9.0g bf4 = max(0, 24 - BSIsoma) bf9 float %9.0g bf9= max(0, 30 - shhlw1) bf11 float %9.0g bf11= max(0, 20 - sufamw1) bf4m float %9.0g bf4m = max(0, 32 - BSIsoma) bf15m float %9.0g bf15m= max(0, 1 - icdxcnt) * bf2 bf30 float %9.0g bf30 = max(0, neiw1 - 85) * bf20 bf40 float %9.0g bf40 = max(0, icdxcnt - 1.01635E-007) ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** chunk 3 H1 test pt 2 :Gender= 1 model Wave = 3 for hp2work ***** ***** ***** ***** ***** ***** 1 Jul 2012 20:36:21 ***** ******************************************************************************* ******************************************************************************* i.educ _Ieduc_1-8 (naturally coded; _Ieduc_1 omitted) note: _Ieduc_4 != 0 predicts failure perfectly _Ieduc_4 dropped and 14 obs not used note: _Ieduc_8 != 0 predicts failure perfectly _Ieduc_8 dropped and 2 obs not used note: occ6w3 != 0 predicts failure perfectly occ6w3 dropped and 4 obs not used note: bf17 != 0 predicts failure perfectly bf17 dropped and 5 obs not used note: _Ieduc_7 omitted because of collinearity note: occ8w3 omitted because of collinearity note: marrw36 omitted because of collinearity note: radhlw3 omitted because of collinearity Logistic regression Number of obs = 315 LR chi2(48) = 139.93 Prob > chi2 = 0.0000 Log likelihood = -96.893664 Pseudo R2 = 0.4193 ------------------------------------------------------------------------------ HP2hmcare | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0323974 .0293162 1.11 0.269 -.0250612 .089856 _Ieduc_2 | -4.152531 2.287775 -1.82 0.070 -8.636488 .3314257 _Ieduc_3 | -1.864493 1.608696 -1.16 0.246 -5.017479 1.288493 _Ieduc_4 | 0 (omitted) _Ieduc_5 | -1.404302 1.64491 -0.85 0.393 -4.628265 1.819662 _Ieduc_6 | -2.017048 1.54335 -1.31 0.191 -5.041958 1.007861 _Ieduc_7 | 0 (omitted) _Ieduc_8 | 0 (omitted) occ1w3 | -11.82929 1296.263 -0.01 0.993 -2552.458 2528.799 occ2w3 | -11.65702 1296.263 -0.01 0.993 -2552.286 2528.971 occ3w3 | -12.78325 1296.263 -0.01 0.992 -2553.412 2527.846 occ4w3 | -10.84152 1296.263 -0.01 0.993 -2551.47 2529.787 occ5w3 | -10.72665 1296.263 -0.01 0.993 -2551.356 2529.903 occ6w3 | 0 (omitted) occ7w3 | -11.31316 1296.263 -0.01 0.993 -2551.942 2529.316 occ8w3 | 0 (omitted) marrw31 | .3643704 1.429352 0.25 0.799 -2.437107 3.165848 marrw32 | -2.206121 1.844343 -1.20 0.232 -5.820966 1.408725 marrw33 | -.7934545 1.390519 -0.57 0.568 -3.518821 1.931912 marrw35 | -.2775718 1.556356 -0.18 0.858 -3.327973 2.772829 marrw36 | 0 (omitted) inc1w3 | 14.70395 1296.262 0.01 0.991 -2525.924 2555.332 inc2w3 | 14.77269 1296.262 0.01 0.991 -2525.855 2555.4 inc3w3 | 14.57764 1296.262 0.01 0.991 -2526.05 2555.205 inc4w3 | 15.74154 1296.263 0.01 0.990 -2524.886 2556.37 radhlw3 | .0078686 .0080582 0.98 0.329 -.007925 .0236623 havmil | .0027954 .0078952 0.35 0.723 -.0126789 .0182698 avgcumdosew3 | .0057068 .0769937 0.07 0.941 -.1451981 .1566117 bf1 | -.0445389 .0484618 -0.92 0.358 -.1395224 .0504446 bf4 | -.0327423 .2796012 -0.12 0.907 -.5807506 .515266 bf2 | .0000822 .0001677 0.49 0.624 -.0002465 .0004108 bf4m | -.341802 .2609957 -1.31 0.190 -.8533441 .1697402 bf5m | .0012439 .0017995 0.69 0.489 -.0022831 .0047709 bf7m | .0005614 .0005422 1.04 0.300 -.0005013 .0016241 bf8 | -.0000499 .0000448 -1.11 0.265 -.0001376 .0000379 bf15m | -.0000712 .0003918 -0.18 0.856 -.0008391 .0006966 bf17 | 0 (omitted) bf20 | .019063 .0407736 0.47 0.640 -.0608518 .0989778 bf22 | .0000146 .0001733 0.08 0.933 -.0003251 .0003543 bf29 | .0000124 .0000229 0.54 0.589 -.0000325 .0000572 bf30 | -.000416 .0004185 -0.99 0.320 -.0012364 .0004043 bf40 | .1486565 .2411791 0.62 0.538 -.3240459 .6213588 deaw3 | -.6566764 .3112091 -2.11 0.035 -1.266635 -.0467177 dvcew3 | .7731044 1.122755 0.69 0.491 -1.427455 2.973664 sepaw3 | .1659839 1.359372 0.12 0.903 -2.498337 2.830305 accdw3 | .7493757 .6472786 1.16 0.247 -.519267 2.018018 movew3 | .9688514 .5333557 1.82 0.069 -.0765066 2.014209 radhlw3 | 0 (omitted) illw3 | .2806377 .2813528 1.00 0.319 -.2708037 .832079 shfamw3 | .0045809 .0088802 0.52 0.606 -.0128239 .0219857 shhlw3 | -.0144819 .0077 -1.88 0.060 -.0295736 .0006098 shjobw3 | -.0101653 .0077745 -1.31 0.191 -.0254031 .0050725 shrelaw3 | -.0092584 .0083742 -1.11 0.269 -.0256716 .0071547 suprtw3 | -.0009401 .0080071 -0.12 0.907 -.0166337 .0147535 suchrw3 | -.004683 .0069496 -0.67 0.500 -.0183041 .008938 havmilsq | -7.50e-06 .0000145 -0.52 0.604 -.0000359 .0000209 _cons | 3.229911 4.235709 0.76 0.446 -5.071927 11.53175 ------------------------------------------------------------------------------ Note: 3 failures and 0 successes completely determined. Logistic model for HP2hmcare -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 37 14 | 51 - | 33 231 | 264 -----------+--------------------------+----------- Total | 70 245 | 315 Classified + if predicted Pr(D) >= .5 True D defined as HP2hmcare != 0 -------------------------------------------------- Sensitivity Pr( +| D) 52.86% Specificity Pr( -|~D) 94.29% Positive predictive value Pr( D| +) 72.55% Negative predictive value Pr(~D| -) 87.50% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 5.71% False - rate for true D Pr( -| D) 47.14% False + rate for classified + Pr(~D| +) 27.45% False - rate for classified - Pr( D| -) 12.50% -------------------------------------------------- Correctly classified 85.08% -------------------------------------------------- Logistic model for HP2hmcare, goodness-of-fit test number of observations = 315 number of covariate patterns = 315 Pearson chi2(266) = 247.97 Prob > chi2 = 0.7796 Measures of Fit for logistic of HP2hmcare Log-Lik Intercept Only: -166.857 Log-Lik Full Model: -96.894 D(258): 193.787 LR(48): 139.928 Prob > LR: 0.000 McFadden's R2: 0.419 McFadden's Adj R2: 0.078 Maximum Likelihood R2: 0.359 Cragg & Uhler's R2: 0.549 McKelvey and Zavoina's R2: 0.758 Efron's R2: 0.437 Variance of y*: 13.609 Variance of error: 3.290 Count R2: 0.851 Adj Count R2: 0.329 AIC: 0.977 AIC*n: 307.787 BIC: -1290.376 BIC': 136.196 ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** chunk 3 H1 test pt 2 :Gender= 2 model Wave = 3 for HP2hmcare ***** ***** ***** ***** ***** ***** 1 Jul 2012 20:36:23 ***** ******************************************************************************* ******************************************************************************* i.educ _Ieduc_1-8 (naturally coded; _Ieduc_1 omitted) note: occ6w3 != 0 predicts failure perfectly occ6w3 dropped and 4 obs not used note: occ8w3 != 0 predicts failure perfectly occ8w3 dropped and 1 obs not used note: bf29 != 0 predicts success perfectly bf29 dropped and 4 obs not used note: _Ieduc_8 omitted because of collinearity note: radhlw3 omitted because of collinearity convergence not achieved Logistic regression Number of obs = 353 LR chi2(50) = 144.83 Prob > chi2 = 0.0000 Log likelihood = -154.51255 Pseudo R2 = 0.3191 ------------------------------------------------------------------------------ HP2hmcare | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0784128 .0199184 3.94 0.000 .0393735 .1174521 _Ieduc_2 | -16.15888 2.72009 -5.94 0.000 -21.49016 -10.8276 _Ieduc_3 | -16.70929 2.647032 -6.31 0.000 -21.89738 -11.5212 _Ieduc_4 | -15.65932 2.672964 -5.86 0.000 -20.89823 -10.4204 _Ieduc_5 | -16.93546 2.621945 -6.46 0.000 -22.07438 -11.79654 _Ieduc_6 | -17.12993 2.678622 -6.40 0.000 -22.37993 -11.87993 _Ieduc_7 | -16.6826 3.290952 -5.07 0.000 -23.13274 -10.23245 _Ieduc_8 | 0 (omitted) occ1w3 | -17.5089 2870.035 -0.01 0.995 -5642.674 5607.656 occ2w3 | -17.42465 2870.035 -0.01 0.995 -5642.59 5607.741 occ3w3 | -17.38618 2870.035 -0.01 0.995 -5642.551 5607.779 occ4w3 | -17.97919 2870.035 -0.01 0.995 -5643.145 5607.186 occ5w3 | -16.19886 2870.036 -0.01 0.995 -5641.366 5608.968 occ6w3 | 0 (omitted) occ7w3 | -17.37679 2870.035 -0.01 0.995 -5642.542 5607.789 occ8w3 | 0 (omitted) marrw31 | .1254457 1.662878 0.08 0.940 -3.133735 3.384627 marrw32 | .689276 1.963389 0.35 0.726 -3.158896 4.537448 marrw33 | 1.411752 1.537008 0.92 0.358 -1.600728 4.424232 marrw35 | .6824445 1.564972 0.44 0.663 -2.384843 3.749732 marrw36 | .9604788 1.548632 0.62 0.535 -2.074784 3.995742 inc1w3 | 18.76205 2870.035 0.01 0.995 -5606.403 5643.927 inc2w3 | 18.64464 2870.035 0.01 0.995 -5606.521 5643.81 inc3w3 | 18.13548 2870.035 0.01 0.995 -5607.03 5643.301 inc4w3 | 18.63139 2870.035 0.01 0.995 -5606.534 5643.797 radhlw3 | -.0056373 .0071331 -0.79 0.429 -.0196178 .0083433 havmil | .0003358 .0026887 0.12 0.901 -.004934 .0056056 avgcumdosew3 | -.1458757 .0962788 -1.52 0.130 -.3345787 .0428273 bf1 | -.0155333 .0271811 -0.57 0.568 -.0688074 .0377407 bf4 | -.4865728 .1784134 -2.73 0.006 -.8362567 -.136889 bf2 | .0000926 .0001019 0.91 0.364 -.0001072 .0002923 bf4m | .3213367 .1603015 2.00 0.045 .0071516 .6355219 bf5m | -.000883 .0014167 -0.62 0.533 -.0036598 .0018937 bf7m | .0002998 .000443 0.68 0.499 -.0005684 .001168 bf8 | 6.84e-06 .0000322 0.21 0.832 -.0000563 .00007 bf15m | -.0163738 .5454291 -0.03 0.976 -1.085395 1.052648 bf17 | .0008202 .0272715 0.03 0.976 -.0526309 .0542713 bf20 | .00093 .0215397 0.04 0.966 -.041287 .043147 bf22 | -.0000872 .0001081 -0.81 0.420 -.0002991 .0001247 bf29 | 0 (omitted) bf30 | .0000251 .0002916 0.09 0.931 -.0005465 .0005967 bf40 | .130008 .1227916 1.06 0.290 -.1106591 .3706751 deaw3 | .0165154 .1614822 0.10 0.919 -.2999838 .3330147 dvcew3 | .6982802 .7163029 0.97 0.330 -.7056476 2.102208 sepaw3 | -.4992309 .8307882 -0.60 0.548 -2.127546 1.129084 accdw3 | -.1706856 .4639657 -0.37 0.713 -1.080042 .7386705 movew3 | -.4464406 1.157043 -0.39 0.700 -2.714203 1.821322 radhlw3 | 0 (omitted) illw3 | -.0890835 .1513588 -0.59 0.556 -.3857412 .2075743 shfamw3 | -.0035627 .0062149 -0.57 0.566 -.0157436 .0086183 shhlw3 | .0080044 .0056769 1.41 0.159 -.0031221 .0191309 shjobw3 | -.0042351 .0058007 -0.73 0.465 -.0156042 .0071341 shrelaw3 | -.010315 .0062344 -1.65 0.098 -.0225341 .0019041 suprtw3 | -.0017061 .0061593 -0.28 0.782 -.0137782 .010366 suchrw3 | -.0030007 .0044692 -0.67 0.502 -.0117602 .0057587 havmilsq | -1.55e-06 2.58e-06 -0.60 0.549 -6.61e-06 3.52e-06 _cons | 10.07155 . . . . . ------------------------------------------------------------------------------ Note: 4 failures and 0 successes completely determined. Warning: convergence not achieved Logistic model for HP2hmcare -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 76 29 | 105 - | 45 203 | 248 -----------+--------------------------+----------- Total | 121 232 | 353 Classified + if predicted Pr(D) >= .5 True D defined as HP2hmcare != 0 -------------------------------------------------- Sensitivity Pr( +| D) 62.81% Specificity Pr( -|~D) 87.50% Positive predictive value Pr( D| +) 72.38% Negative predictive value Pr(~D| -) 81.85% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 12.50% False - rate for true D Pr( -| D) 37.19% False + rate for classified + Pr(~D| +) 27.62% False - rate for classified - Pr( D| -) 18.15% -------------------------------------------------- Correctly classified 79.04% -------------------------------------------------- Logistic model for HP2hmcare, goodness-of-fit test number of observations = 353 number of covariate patterns = 353 Pearson chi2(301) = 338.41 Prob > chi2 = 0.0677 Measures of Fit for logistic of HP2hmcare Log-Lik Intercept Only: -226.929 Log-Lik Full Model: -154.513 D(296): 309.025 LR(50): 144.834 Prob > LR: 0.000 McFadden's R2: 0.319 McFadden's Adj R2: 0.068 Maximum Likelihood R2: 0.337 Cragg & Uhler's R2: 0.465 McKelvey and Zavoina's R2: 0.954 Efron's R2: 0.369 Variance of y*: 71.429 Variance of error: 3.290 Count R2: 0.790 Adj Count R2: 0.388 AIC: 1.198 AIC*n: 423.025 BIC: -1427.449 BIC': 148.490 408 . 409 . title4 "Male Main effects model for dose=> homcare wave 3" ------------------------------------------------------------------------------- Male Main effects model for dose=> homcare wave 3 ------------------------------------------------------------------------------- 410 . logit hp2hmcare age radhlw3 avgcumdosew3 bf4 bf4m bf40 if gender==1 Iteration 0: log likelihood = -172.87291 Iteration 1: log likelihood = -133.30015 Iteration 2: log likelihood = -130.66001 Iteration 3: log likelihood = -130.56564 Iteration 4: log likelihood = -130.56534 Iteration 5: log likelihood = -130.56534 Logistic regression Number of obs = 340 LR chi2(6) = 84.62 Prob > chi2 = 0.0000 Log likelihood = -130.56534 Pseudo R2 = 0.2447 ------------------------------------------------------------------------------ hp2hmcare | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0212427 .0145356 1.46 0.144 -.0072466 .0497319 radhlw3 | -.0004747 .0052658 -0.09 0.928 -.0107954 .0098461 avgcumdosew3 | .0109468 .049766 0.22 0.826 -.0865928 .1084864 bf4 | -.0254029 .2104548 -0.12 0.904 -.4378867 .3870809 bf4m | -.172073 .19389 -0.89 0.375 -.5520905 .2079444 bf40 | .1415116 .0924687 1.53 0.126 -.0397237 .3227469 _cons | .7537844 1.701465 0.44 0.658 -2.581025 4.088594 ------------------------------------------------------------------------------ 411 . 412 . di as input "Male trimmed model for dose-home care impact in wv 3: dose not s > ignif" Male trimmed model for dose-home care impact in wv 3: dose not signif 413 . di as input " male dose is not signif as main effect in dose - homecare impac > t " male dose is not signif as main effect in dose - homecare impact 414 . di as input " no male moderate interactions for dose-homecare impact" no male moderate interactions for dose-homecare impact 415 . 416 . scalar SigDoseHmcareMw3 = "no" 417 . scalar MainEffhmcareMw3= "none" 418 . scalar list VactnMedFw3 = age illw3 radhlw3 VactnMedMw3 = age illw3 VacatnModFw3 = none MainEffVactnFw3 = age radhlw3 deaw3 SigDoseVactnFw3 = no vactnModMw3 = none MainEffVactnMw3 = age bf7m radhlw3 SigDoseVactnMw3 = no sxLifeMedFw3 = age bf4 bf4m sxLifeMedMw3 = age illw3 InthbModFw3 = none MainEffInthbFw3 = age radhlw3 bf4 SigdoseInthbFw3 = no InthbMw3 = none MainEffInthbMw3 = age radhlw3 shfamw3 SigDoseInthbMw3 = no sxlifeMedFw3 = age illw3 radhlw3 bf4 bf4m sxlifeMedMw3 = age illw3 sxlifeModFw3 = none MainEffsxlifeFw3 = age radhlw3 bf4 bf4m shrelaw3 shfamw3 SigDoseSxlifeFw3 = no sxlifeModMw3 = none SigDosesxlifeMw3 = no MainEffsxlifeMw3 = age bf4 illw3 radhlw3 PrbfmhmMedFw3 = age bf4 PrbfmhmMedMw3 = age PrbfmhmModFw3 = none MainEffPrbfmhmFw3 = age bf4 bf40 SigDosePrbfmhmFw3 = no PrbfmhmModw3 = none SigDosePrbfmhmMw3 = no SigDosePrbfhmMw3 = no MainEffPrbfhmMw3 = bf1 bf4 dvcew3 bf7m ProbsocMedFw3 = age radhlw3 ProbsocMedMw3 = age ProbsocModFw3 = none MainEffProbSocFw3 = age radhlw3 illw3 Shrelaw3 avgcumodsew3 SigDoseProbsocFw3 = yes ProbSocModMw3 = none SigDoseProbsocMw3 = no MainEffPrbsocMw3 = age radhlw3 shjobw3 hmcareMedFw3 = age illw3 hmcareMedMw3 = age illw3 hmcareModFw3 = none SigdoseHmcareFw3 = no hmcareModMw3 = none MainEffhmcareMw3 = none SigDoseHmcareMw3 = no wkMedFw3 = radhlw3 age bf40 bf4m bf1 wkMedMw3 = bf8 age illw3 ageXillw3 wkModFw3 = none wkModMw3 = none MainEffwkFw3 = age MainEffwkMw3 = workM: age bf8 illw3 shjobw3 SigDoseWKMw3 = no SigDoseWkFw3 = no medsigFw2 = 1 wkMedMw2 = bf8 age illw2 VactnMedFw2 = age illw2 radhlw2 VactnMedMw2 = age illw2 VacatnModFw2 = none MainEffVactnFw2 = age radhlw2 deaw2 SigDoseVactnFw2 = no vactnModMw2 = none MainEffVactnMw2 = age bf7m radhlw2 SigDoseVactnMw2 = no sxLifeMedFw2 = age bf4 bf4m sxLifeMedMw2 = age illw2 InthbModFw2 = none MainEffInthbFw2 = age radhlw2 bf4 SigdoseInthbFw2 = no InthbMw2 = none MainEffInthbMw2 = age radhlw2 shfamw2 SigDoseInthbMw2 = no sxlifeMedFw2 = age illw2 radhlw2 bf4 bf4m sxlifeMedMw2 = age illw2 sxlifeModFw2 = none MainEffsxlifeFw2 = age radhlw2 bf4 bf4m shrelaw2 shfamw2 SigDoseSxlifeFw2 = no sxlifeModMw2 = none SigDosesxlifeMw2 = no MainEffsxlifeMw2 = age bf4 illw2 radhlw2 PrbfmhmMedFw2 = age bf4 PrbfmhmMedMw2 = age PrbfmhmModFw2 = none MainEffPrbfmhmFw2 = age bf4 bf40 SigDosePrbfmhmFw2 = no PrbfmhmModw2 = none SigDosePrbfmhmMw2 = no SigDosePrbfhmMw2 = no MainEffPrbfhmMw2 = bf1 bf4 dvcew2 bf7m ProbsocMedFw2 = age radhlw2 ProbsocMedMw2 = age ProbsocModFw2 = none MainEffProbSocFw2 = age radhlw2 illw2 Shrelaw2 avgcumodsew2 SigDoseProbsocFw2 = yes ProbSocModMw2 = none SigDoseProbsocMw2 = no MainEffPrbsocMw2 = age radhlw2 shjobw2 hmcareMedFw2 = age illw2 hmcareMedMw2 = age illw2 hmcareModFw2 = none SigDoseWKFw2 = 0 SigdoseHmcareFw2 = no hmcareModMw2 = none MainEffhmcareMw2 = none SigDoseHmcareMw2 = no wkMedFw2 = radhlw2 age bf40 bf4m bf1 wkModFw2 = none wkModMw2 = none MainEffwkFw2 = age MainEffwkMw2 = workM: age bf8 illw2 shjobw2 SigDoseWKMw2 = no SigDoseWkFw2 = no hmcrMedFw1 = age icdxcnt shjobw1 bf4 BSIsoma WHPpain WHPsleep WHPel hmcrMedMw1 = age MainEffhmcrFw1 = illw1 age SigDosehmcrFw1 = no hmcrModMw1 = none MainEffhmcrMw1 = age shjobw1 SigDosehmcrMw1 = no wkMedFw1 = age b4 MainEffwkFw1 = age MainEffwkMw1 = age wkMedMw1 = bf40 WkMedMw1 = none WkModFw1 = none WKModMw1 = none SigDoseWkMw1 = no SigDoseWkFw1 = no SigDoseFw1 = no wkModFw1 = none wkModMw1 = none medsigFw1 = 1 prbsocnumMAsig = 8 419 . 420 . title4 "male main effect plus interaction model" ------------------------------------------------------------------------------- male main effect plus interaction model ------------------------------------------------------------------------------- 421 . logit hp2hmcare age radhlw3 avgcumdosew3 ageXd3 illw3 if gender==1 Iteration 0: log likelihood = -172.87291 Iteration 1: log likelihood = -149.81879 Iteration 2: log likelihood = -148.25194 Iteration 3: log likelihood = -148.24243 Iteration 4: log likelihood = -148.24243 Logistic regression Number of obs = 340 LR chi2(5) = 49.26 Prob > chi2 = 0.0000 Log likelihood = -148.24243 Pseudo R2 = 0.1425 ------------------------------------------------------------------------------ hp2hmcare | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0437867 .0172121 2.54 0.011 .0100515 .0775219 radhlw3 | .0144867 .0043947 3.30 0.001 .0058733 .0231002 avgcumdosew3 | .3109469 .7827747 0.40 0.691 -1.223263 1.845157 ageXd3 | -.0057849 .0134227 -0.43 0.666 -.0320929 .020523 illw3 | .40549 .1399082 2.90 0.004 .1312749 .679705 _cons | -4.648689 .9666744 -4.81 0.000 -6.543336 -2.754042 ------------------------------------------------------------------------------ 422 . cap gen radhlw3Xillw3 = radhlw3*illw3 423 . cap drop radhlw3Xd1 424 . cap gen radhlw3Xd3 = radhlw3*avgcumdosew3 425 . cap drop illw3Xd1 426 . cap gen illw3Xd3 = illw3*avgcumdosew3 427 . 428 . 429 . * there are no significant moderators for male dose=hmcare relationship 430 . scalar hmcareModMw3 = "none" 431 . 432 . *--------- Male moderator tests for Dose-Hmcare in wave 3: ---------------- > ---- 433 . 434 . title "Dose-home care impact relationship reveals no male moderators" ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Dose-home care impact relationship reveals no male moderators ***** ***** ***** ***** ***** ***** 1 Jul 2012 20:36:27 ***** ******************************************************************************* ******************************************************************************* 435 . logit hp2hmcare radhlw3 avgcumdosew3 illw3 radhlw3Xillw3 radhlw3Xd3 illw3Xd3 > /// > if gender==1 Iteration 0: log likelihood = -172.87291 Iteration 1: log likelihood = -153.71153 Iteration 2: log likelihood = -152.25962 Iteration 3: log likelihood = -152.22817 Iteration 4: log likelihood = -152.22779 Iteration 5: log likelihood = -152.22779 Logistic regression Number of obs = 340 LR chi2(6) = 41.29 Prob > chi2 = 0.0000 Log likelihood = -152.22779 Pseudo R2 = 0.1194 ------------------------------------------------------------------------------- hp2hmcare | Coef. Std. Err. z P>|z| [95% Conf. Interval] --------------+---------------------------------------------------------------- radhlw3 | .0200281 .0064545 3.10 0.002 .0073775 .0326787 avgcumdosew3 | -.1252158 .2932467 -0.43 0.669 -.6999688 .4495372 illw3 | .677266 .2824634 2.40 0.016 .1236479 1.230884 radhlw3Xillw3 | -.0042432 .0039636 -1.07 0.284 -.0120118 .0035254 radhlw3Xd3 | .0007389 .0042983 0.17 0.864 -.0076857 .0091635 illw3Xd3 | .0384326 .0812891 0.47 0.636 -.120891 .1977563 _cons | -2.652783 .4389838 -6.04 0.000 -3.513175 -1.792391 ------------------------------------------------------------------------------- 436 . estat gof Logistic model for hp2hmcare, goodness-of-fit test number of observations = 340 number of covariate patterns = 306 Pearson chi2(299) = 319.87 Prob > chi2 = 0.1945 437 . estat class Logistic model for hp2hmcare -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 8 5 | 13 - | 62 265 | 327 -----------+--------------------------+----------- Total | 70 270 | 340 Classified + if predicted Pr(D) >= .5 True D defined as hp2hmcare != 0 -------------------------------------------------- Sensitivity Pr( +| D) 11.43% Specificity Pr( -|~D) 98.15% Positive predictive value Pr( D| +) 61.54% Negative predictive value Pr(~D| -) 81.04% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 1.85% False - rate for true D Pr( -| D) 88.57% False + rate for classified + Pr(~D| +) 38.46% False - rate for classified - Pr( D| -) 18.96% -------------------------------------------------- Correctly classified 80.29% -------------------------------------------------- 438 . fitstat Measures of Fit for logit of hp2hmcare Log-Lik Intercept Only: -172.873 Log-Lik Full Model: -152.228 D(333): 304.456 LR(6): 41.290 Prob > LR: 0.000 McFadden's R2: 0.119 McFadden's Adj R2: 0.079 Maximum Likelihood R2: 0.114 Cragg & Uhler's R2: 0.179 McKelvey and Zavoina's R2: 0.208 Efron's R2: 0.130 Variance of y*: 4.154 Variance of error: 3.290 Count R2: 0.803 Adj Count R2: 0.043 AIC: 0.937 AIC*n: 318.456 BIC: -1636.583 BIC': -6.317 439 . 440 . 441 . title "trimming female moderators for hp2hmcare" ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** trimming female moderators for hp2hmcare ***** ***** ***** ***** ***** ***** 1 Jul 2012 20:36:29 ***** ******************************************************************************* ******************************************************************************* 442 . 443 . * Dose work relationship for females in wave 3 washes out also 444 . set more off 445 . forvalues j=3/3 { 2. local w3bf bf1 bf4 bf2 bf4m bf5m bf7m bf8 bf15m bf17 bf20 bf22 bf29 bf30 b > f40 3. di _skip(4) 4. di as input "For females hp2hmcare on wave 1 with dose ns" 5. des age avgcumdosew`j' `w3bf' 6. logistic HP2work age radhlw3 /// > avgcumdosew3 shhlw`j' if gender==2, coef nolog 7. 446 . } For females hp2hmcare on wave 1 with dose ns storage display value variable name type format label variable label ------------------------------------------------------------------------------- age double %8.0g * Respondent's age avgcumdosew3 double %8.0g Avg Mean dose of CS137 ending 12/31/2009 bf1 float %9.0g bf1 = max(0, kzchorn - 40) bf4 float %9.0g bf4 = max(0, 24 - BSIsoma) bf2 float %9.0g bf2 = max(0, efradw3 - 1.61252E-006) * bf1 bf4m float %9.0g bf4m = max(0, 32 - BSIsoma) bf5m float %9.0g bf5m = max(0, ecprw3 - 75) * bf4m bf7m float %9.0g bf7m = max(0, radtlw3 - 2.12558E-007) * bf4m bf8 float %9.0g bf8 = max(0, radtlw3 - 40) * bf5m bf15m float %9.0g bf15m= max(0, 1 - icdxcnt) * bf2 bf17 float %9.0g bf17 = max(0, 20 - ecprw3) * bf15m bf20 float %9.0g bf20 = max(0, kzchorn - 2.53946E-006) bf22 float %9.0g bf22 = max(0, icdxcnt - 1.01635E-007) * bf7m bf29 float %9.0g bf29 = max(0, 18 - CSsocspt) * bf8 bf30 float %9.0g bf30 = max(0, neiw1 - 85) * bf20 bf40 float %9.0g bf40 = max(0, icdxcnt - 1.01635E-007) Logistic regression Number of obs = 363 LR chi2(4) = 54.20 Prob > chi2 = 0.0000 Log likelihood = -179.46218 Pseudo R2 = 0.1312 ------------------------------------------------------------------------------ HP2work | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0604261 .0121821 4.96 0.000 .0365495 .0843027 radhlw3 | .0091245 .0041171 2.22 0.027 .0010551 .0171938 avgcumdosew3 | .0744838 .0646958 1.15 0.250 -.0523177 .2012853 shhlw3 | .0068705 .0039339 1.75 0.081 -.0008399 .0145808 _cons | -5.221192 .6904908 -7.56 0.000 -6.574529 -3.867855 ------------------------------------------------------------------------------ 447 . 448 . 449 . 450 . 451 . 452 . 453 . 454 . 455 . scalar SigdoseHmcareFw3="no" 456 . 457 . * capturing significant vars to test as moderators 458 . local cn4: colnames(e(b)) 459 . di "`cn4'" age radhlw3 avgcumdosew3 shhlw3 _cons 460 . local leng4 = length( "`cn4'") 461 . di `leng4' 37 462 . local leng4b `leng4'-6 463 . di `leng3b' 464 . local nuvlist4 = substr("`cn4'",4,`leng4b') 465 . di "`nuvlist4'" radhlw3 avgcumdosew3 shhlw3 _c 466 . local rhsvars4 = "`nuvlist4'" 467 . local nuvlist4= "`nuvlist4'" 468 . local nuvlist4= substr("`cn4'",1,`leng4b') 469 . di "`nuvlist4'" age radhlw3 avgcumdosew3 shhlw3 470 . 471 . cap gen shhlw3Xd3 = shhlw3*avgcumdosew3 472 . 473 . title "No sig female moderators for dose-hmcare impact are found here" ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** No sig female moderators for dose-hmcare impact are found here ***** ***** ***** ***** ***** ***** 1 Jul 2012 20:36:30 ***** ******************************************************************************* ******************************************************************************* 474 . logit hp2hmcare age shhlw3 avgcumdosew3 ageXd3 shhlw3Xd3 if gender==2 Iteration 0: log likelihood = -233.72859 Iteration 1: log likelihood = -194.59265 Iteration 2: log likelihood = -193.8132 Iteration 3: log likelihood = -193.8113 Iteration 4: log likelihood = -193.8113 Logistic regression Number of obs = 363 LR chi2(5) = 79.83 Prob > chi2 = 0.0000 Log likelihood = -193.8113 Pseudo R2 = 0.1708 ------------------------------------------------------------------------------ hp2hmcare | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0869437 .0159483 5.45 0.000 .0556857 .1182017 shhlw3 | .0025983 .0052389 0.50 0.620 -.0076698 .0128663 avgcumdosew3 | -.5753628 .7013698 -0.82 0.412 -1.950022 .7992968 ageXd3 | .0054767 .0110707 0.49 0.621 -.0162215 .0271749 shhlw3Xd3 | .0024363 .0033657 0.72 0.469 -.0041603 .0090329 _cons | -5.058574 .9113937 -5.55 0.000 -6.844872 -3.272275 ------------------------------------------------------------------------------ 475 . 476 . set more off 477 . *---------- Mediator relationships for home care are tested below: ---------- > --- 478 . title "Mediator relationships of Dose - home care impact are tested" ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Mediator relationships of Dose - home care impact are tested ***** ***** ***** ***** ***** ***** 1 Jul 2012 20:36:32 ***** ******************************************************************************* ******************************************************************************* 479 . forvalues k=1/2 { 2. forvalues j=3/3 { 3. local w3bf bf1 bf4 bf2 bf4m bf5m bf7m bf8 bf15m bf17 bf20 bf22 bf29 bf30 b > f40 4. di _skip(2) 5. di as input "Trimmed gender=`k' hp2hmcare impact of dose in wave `j' " 6. des age occ1w`j'-occ8w`j' inc1w`j'-inc4w`j' avgcumdosew`j' `w3bf' 7. sw, pr(.1): logistic hp2hmcare age havmilsq /// > avgcumdosew3 ageXd3 illw`j' shjobw`j' suprtw`j' if gender==`k', coef nolo > g 8. estat gof 9. estat class 10. fitstat 11. } 12. } Trimmed gender=1 hp2hmcare impact of dose in wave 3 storage display value variable name type format label variable label ------------------------------------------------------------------------------- age double %8.0g * Respondent's age occ1w3 double %15.0g LABJ professional executive administration now occ2w3 double %15.0g LABJ technical sales admin support now occ3w3 double %15.0g LABJ service occup protective services now occ4w3 double %15.0g LABJ precision prod mechan craft construction now occ5w3 double %15.0g LABJ factory laborer machinist transp cleaner now occ6w3 double %15.0g LABJ farming agricul forestry fishing trapping logging now occ7w3 double %15.0g LABJ homemaking or caregiving now occ8w3 double %15.0g LABJ student now inc1w3 double %15.0g LABJ Income is not sufficient for basic neccessities NOW inc2w3 double %15.0g LABJ Income is just sufficient for basic neccessities NOW inc3w3 double %15.0g LABJ Income is sufficient for basics plus extra purchases/savings NOW inc4w3 double %15.0g LABJ Income allows to comfortably afford luxury items NOW avgcumdosew3 double %8.0g Avg Mean dose of CS137 ending 12/31/2009 bf1 float %9.0g bf1 = max(0, kzchorn - 40) bf4 float %9.0g bf4 = max(0, 24 - BSIsoma) bf2 float %9.0g bf2 = max(0, efradw3 - 1.61252E-006) * bf1 bf4m float %9.0g bf4m = max(0, 32 - BSIsoma) bf5m float %9.0g bf5m = max(0, ecprw3 - 75) * bf4m bf7m float %9.0g bf7m = max(0, radtlw3 - 2.12558E-007) * bf4m bf8 float %9.0g bf8 = max(0, radtlw3 - 40) * bf5m bf15m float %9.0g bf15m= max(0, 1 - icdxcnt) * bf2 bf17 float %9.0g bf17 = max(0, 20 - ecprw3) * bf15m bf20 float %9.0g bf20 = max(0, kzchorn - 2.53946E-006) bf22 float %9.0g bf22 = max(0, icdxcnt - 1.01635E-007) * bf7m bf29 float %9.0g bf29 = max(0, 18 - CSsocspt) * bf8 bf30 float %9.0g bf30 = max(0, neiw1 - 85) * bf20 bf40 float %9.0g bf40 = max(0, icdxcnt - 1.01635E-007) begin with full model p = 0.8890 >= 0.1000 removing shjobw3 p = 0.7169 >= 0.1000 removing avgcumdosew3 p = 0.6181 >= 0.1000 removing ageXd3 p = 0.3884 >= 0.1000 removing suprtw3 p = 0.3741 >= 0.1000 removing havmilsq Logistic regression Number of obs = 340 LR chi2(2) = 37.81 Prob > chi2 = 0.0000 Log likelihood = -153.96835 Pseudo R2 = 0.1094 ------------------------------------------------------------------------------ hp2hmcare | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .050053 .0120837 4.14 0.000 .0263694 .0737367 illw3 | .450018 .1335457 3.37 0.001 .1882732 .7117629 _cons | -4.209924 .6577161 -6.40 0.000 -5.499024 -2.920824 ------------------------------------------------------------------------------ Logistic model for hp2hmcare, goodness-of-fit test number of observations = 340 number of covariate patterns = 108 Pearson chi2(105) = 123.84 Prob > chi2 = 0.1012 Logistic model for hp2hmcare -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 9 5 | 14 - | 61 265 | 326 -----------+--------------------------+----------- Total | 70 270 | 340 Classified + if predicted Pr(D) >= .5 True D defined as hp2hmcare != 0 -------------------------------------------------- Sensitivity Pr( +| D) 12.86% Specificity Pr( -|~D) 98.15% Positive predictive value Pr( D| +) 64.29% Negative predictive value Pr(~D| -) 81.29% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 1.85% False - rate for true D Pr( -| D) 87.14% False + rate for classified + Pr(~D| +) 35.71% False - rate for classified - Pr( D| -) 18.71% -------------------------------------------------- Correctly classified 80.59% -------------------------------------------------- Measures of Fit for logistic of hp2hmcare Log-Lik Intercept Only: -172.873 Log-Lik Full Model: -153.968 D(337): 307.937 LR(2): 37.809 Prob > LR: 0.000 McFadden's R2: 0.109 McFadden's Adj R2: 0.092 Maximum Likelihood R2: 0.105 Cragg & Uhler's R2: 0.165 McKelvey and Zavoina's R2: 0.170 Efron's R2: 0.126 Variance of y*: 3.965 Variance of error: 3.290 Count R2: 0.806 Adj Count R2: 0.057 AIC: 0.923 AIC*n: 313.937 BIC: -1656.418 BIC': -26.151 Trimmed gender=2 hp2hmcare impact of dose in wave 3 storage display value variable name type format label variable label ------------------------------------------------------------------------------- age double %8.0g * Respondent's age occ1w3 double %15.0g LABJ professional executive administration now occ2w3 double %15.0g LABJ technical sales admin support now occ3w3 double %15.0g LABJ service occup protective services now occ4w3 double %15.0g LABJ precision prod mechan craft construction now occ5w3 double %15.0g LABJ factory laborer machinist transp cleaner now occ6w3 double %15.0g LABJ farming agricul forestry fishing trapping logging now occ7w3 double %15.0g LABJ homemaking or caregiving now occ8w3 double %15.0g LABJ student now inc1w3 double %15.0g LABJ Income is not sufficient for basic neccessities NOW inc2w3 double %15.0g LABJ Income is just sufficient for basic neccessities NOW inc3w3 double %15.0g LABJ Income is sufficient for basics plus extra purchases/savings NOW inc4w3 double %15.0g LABJ Income allows to comfortably afford luxury items NOW avgcumdosew3 double %8.0g Avg Mean dose of CS137 ending 12/31/2009 bf1 float %9.0g bf1 = max(0, kzchorn - 40) bf4 float %9.0g bf4 = max(0, 24 - BSIsoma) bf2 float %9.0g bf2 = max(0, efradw3 - 1.61252E-006) * bf1 bf4m float %9.0g bf4m = max(0, 32 - BSIsoma) bf5m float %9.0g bf5m = max(0, ecprw3 - 75) * bf4m bf7m float %9.0g bf7m = max(0, radtlw3 - 2.12558E-007) * bf4m bf8 float %9.0g bf8 = max(0, radtlw3 - 40) * bf5m bf15m float %9.0g bf15m= max(0, 1 - icdxcnt) * bf2 bf17 float %9.0g bf17 = max(0, 20 - ecprw3) * bf15m bf20 float %9.0g bf20 = max(0, kzchorn - 2.53946E-006) bf22 float %9.0g bf22 = max(0, icdxcnt - 1.01635E-007) * bf7m bf29 float %9.0g bf29 = max(0, 18 - CSsocspt) * bf8 bf30 float %9.0g bf30 = max(0, neiw1 - 85) * bf20 bf40 float %9.0g bf40 = max(0, icdxcnt - 1.01635E-007) begin with full model p = 0.8360 >= 0.1000 removing ageXd3 p = 0.7775 >= 0.1000 removing suprtw3 p = 0.3880 >= 0.1000 removing havmilsq p = 0.3482 >= 0.1000 removing shjobw3 p = 0.2310 >= 0.1000 removing illw3 p = 0.1422 >= 0.1000 removing avgcumdosew3 Logistic regression Number of obs = 362 LR chi2(1) = 75.69 Prob > chi2 = 0.0000 Log likelihood = -195.46039 Pseudo R2 = 0.1622 ------------------------------------------------------------------------------ hp2hmcare | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0916735 .0119861 7.65 0.000 .0681811 .1151659 _cons | -5.391274 .6487 -8.31 0.000 -6.662703 -4.119845 ------------------------------------------------------------------------------ Logistic model for hp2hmcare, goodness-of-fit test number of observations = 362 number of covariate patterns = 49 Pearson chi2(47) = 40.39 Prob > chi2 = 0.7413 Logistic model for hp2hmcare -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 62 32 | 94 - | 63 205 | 268 -----------+--------------------------+----------- Total | 125 237 | 362 Classified + if predicted Pr(D) >= .5 True D defined as hp2hmcare != 0 -------------------------------------------------- Sensitivity Pr( +| D) 49.60% Specificity Pr( -|~D) 86.50% Positive predictive value Pr( D| +) 65.96% Negative predictive value Pr(~D| -) 76.49% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 13.50% False - rate for true D Pr( -| D) 50.40% False + rate for classified + Pr(~D| +) 34.04% False - rate for classified - Pr( D| -) 23.51% -------------------------------------------------- Correctly classified 73.76% -------------------------------------------------- Measures of Fit for logistic of hp2hmcare Log-Lik Intercept Only: -233.306 Log-Lik Full Model: -195.460 D(360): 390.921 LR(1): 75.691 Prob > LR: 0.000 McFadden's R2: 0.162 McFadden's Adj R2: 0.154 Maximum Likelihood R2: 0.189 Cragg & Uhler's R2: 0.260 McKelvey and Zavoina's R2: 0.264 Efron's R2: 0.208 Variance of y*: 4.472 Variance of error: 3.290 Count R2: 0.738 Adj Count R2: 0.240 AIC: 1.091 AIC*n: 394.921 BIC: -1730.071 BIC': -69.799 480 . 481 . scalar hmcareModFw3 = "none" 482 . 483 . 484 . 485 . * age and illw3 are a female mediators of dose - home care impact 486 . 487 . * age is a male and female mediator with impact on home care 488 . glm age avgcumdosew3 if gender==1, fam(gaussian) link(identity) Iteration 0: log likelihood = -1330.6336 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = 147.7142 Deviance = 49927.38549 (1/df) Deviance = 147.7142 Pearson = 49927.38549 (1/df) Pearson = 147.7142 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 7.839021 Log likelihood = -1330.633586 BIC = 47957.2 ------------------------------------------------------------------------------ | OIM age | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | .5433648 .2472657 2.20 0.028 .058733 1.027997 _cons | 48.52021 .7247376 66.95 0.000 47.09975 49.94067 ------------------------------------------------------------------------------ 489 . glm hp2hmcare age if gender==1, fam(binomial) irls scale(dev) link(probit) Iteration 1: deviance = 320.8295 Iteration 2: deviance = 320.0337 Iteration 3: deviance = 320.0328 Iteration 4: deviance = 320.0328 Generalized linear models No. of obs = 340 Optimization : MQL Fisher scoring Residual df = 338 (IRLS EIM) Scale parameter = 1 Deviance = 320.0327771 (1/df) Deviance = .9468425 Pearson = 341.699231 (1/df) Pearson = 1.010944 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1650.151 ------------------------------------------------------------------------------ | EIM hp2hmcare | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .032545 .0064212 5.07 0.000 .0199596 .0451304 _cons | -2.483665 .3435565 -7.23 0.000 -3.157023 -1.810306 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 490 . 491 . glm age avgcumdosew3 if gender==2, fam(gaussian) link(identity) Iteration 0: log likelihood = -1408.064 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = 137.7687 Deviance = 49734.51399 (1/df) Deviance = 137.7687 Pearson = 49734.51399 (1/df) Pearson = 137.7687 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 7.768948 Log likelihood = -1408.06405 BIC = 47606.63 ------------------------------------------------------------------------------ | OIM age | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | 1.058366 .3512614 3.01 0.003 .3699069 1.746826 _cons | 48.94293 .7468173 65.54 0.000 47.47919 50.40666 ------------------------------------------------------------------------------ 492 . glm hp2hmcare age if gender==2 , fam(binomial) irls scale(dev) link(probit) Iteration 1: deviance = 393.7958 Iteration 2: deviance = 393.6955 Iteration 3: deviance = 393.6955 Iteration 4: deviance = 393.6955 Generalized linear models No. of obs = 363 Optimization : MQL Fisher scoring Residual df = 361 (IRLS EIM) Scale parameter = 1 Deviance = 393.6954976 (1/df) Deviance = 1.090569 Pearson = 375.4421438 (1/df) Pearson = 1.040006 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1734.184 ------------------------------------------------------------------------------ | EIM hp2hmcare | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0533501 .0069587 7.67 0.000 .0397113 .0669889 _cons | -3.144653 .3710751 -8.47 0.000 -3.871946 -2.417359 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 493 . 494 . 495 . * illw3 is a male mediator wrt dose home care impact 496 . glm illw3 avgcumdosew3 if gender==1, fam(gaussian) link(identity) Iteration 0: log likelihood = -461.99206 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = .8919217 Deviance = 301.469521 (1/df) Deviance = .8919217 Pearson = 301.469521 (1/df) Pearson = .8919217 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 2.729365 Log likelihood = -461.9920626 BIC = -1668.714 ------------------------------------------------------------------------------ | OIM illw3 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | .038211 .0192139 1.99 0.047 .0005524 .0758696 _cons | .4504952 .0563162 8.00 0.000 .3401176 .5608729 ------------------------------------------------------------------------------ 497 . glm hp2hmcare illw3 if gender==1, fam(binomial) irls scale(dev) link(probit) Iteration 1: deviance = 325.666 Iteration 2: deviance = 325.6236 Iteration 3: deviance = 325.6236 Iteration 4: deviance = 325.6236 Generalized linear models No. of obs = 340 Optimization : MQL Fisher scoring Residual df = 338 (IRLS EIM) Scale parameter = 1 Deviance = 325.6235917 (1/df) Deviance = .9633834 Pearson = 335.97027 (1/df) Pearson = .9939949 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1644.56 ------------------------------------------------------------------------------ | EIM hp2hmcare | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- illw3 | .3422616 .0758391 4.51 0.000 .1936197 .4909035 _cons | -1.024423 .0902165 -11.36 0.000 -1.201244 -.8476019 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 498 . 499 . glm illw3 avgcumdosew3 if gender==2, fam(gaussian) link(identity) Iteration 0: log likelihood = -562.81042 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = 1.308042 Deviance = 472.2033151 (1/df) Deviance = 1.308042 Pearson = 472.2033151 (1/df) Pearson = 1.308042 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 3.111903 Log likelihood = -562.8104237 BIC = -1655.676 ------------------------------------------------------------------------------ | OIM illw3 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | .1284565 .0342268 3.75 0.000 .0613733 .1955398 _cons | .5563644 .0727696 7.65 0.000 .4137387 .6989902 ------------------------------------------------------------------------------ 500 . glm hp2hmcare illw3 if gender==2, fam(binomial) irls scale(dev) link(probit) Iteration 1: deviance = 463.6739 Iteration 2: deviance = 463.093 Iteration 3: deviance = 463.0929 Iteration 4: deviance = 463.0929 Generalized linear models No. of obs = 363 Optimization : MQL Fisher scoring Residual df = 361 (IRLS EIM) Scale parameter = 1 Deviance = 463.0929333 (1/df) Deviance = 1.282806 Pearson = 362.4107813 (1/df) Pearson = 1.003908 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1664.786 ------------------------------------------------------------------------------ | EIM hp2hmcare | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- illw3 | .1203099 .0649774 1.85 0.064 -.0070435 .2476634 _cons | -.4898124 .0909036 -5.39 0.000 -.6679803 -.3116445 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 501 . 502 . 503 . 504 . scalar hmcareMedMw3 = "age illw3" 505 . scalar hmcareMedFw3 = "age illw3" 506 . scalar list VactnMedFw3 = age illw3 radhlw3 VactnMedMw3 = age illw3 VacatnModFw3 = none MainEffVactnFw3 = age radhlw3 deaw3 SigDoseVactnFw3 = no vactnModMw3 = none MainEffVactnMw3 = age bf7m radhlw3 SigDoseVactnMw3 = no sxLifeMedFw3 = age bf4 bf4m sxLifeMedMw3 = age illw3 InthbModFw3 = none MainEffInthbFw3 = age radhlw3 bf4 SigdoseInthbFw3 = no InthbMw3 = none MainEffInthbMw3 = age radhlw3 shfamw3 SigDoseInthbMw3 = no sxlifeMedFw3 = age illw3 radhlw3 bf4 bf4m sxlifeMedMw3 = age illw3 sxlifeModFw3 = none MainEffsxlifeFw3 = age radhlw3 bf4 bf4m shrelaw3 shfamw3 SigDoseSxlifeFw3 = no sxlifeModMw3 = none SigDosesxlifeMw3 = no MainEffsxlifeMw3 = age bf4 illw3 radhlw3 PrbfmhmMedFw3 = age bf4 PrbfmhmMedMw3 = age PrbfmhmModFw3 = none MainEffPrbfmhmFw3 = age bf4 bf40 SigDosePrbfmhmFw3 = no PrbfmhmModw3 = none SigDosePrbfmhmMw3 = no SigDosePrbfhmMw3 = no MainEffPrbfhmMw3 = bf1 bf4 dvcew3 bf7m ProbsocMedFw3 = age radhlw3 ProbsocMedMw3 = age ProbsocModFw3 = none MainEffProbSocFw3 = age radhlw3 illw3 Shrelaw3 avgcumodsew3 SigDoseProbsocFw3 = yes ProbSocModMw3 = none SigDoseProbsocMw3 = no MainEffPrbsocMw3 = age radhlw3 shjobw3 hmcareMedFw3 = age illw3 hmcareMedMw3 = age illw3 hmcareModFw3 = none SigdoseHmcareFw3 = no hmcareModMw3 = none MainEffhmcareMw3 = none SigDoseHmcareMw3 = no wkMedFw3 = radhlw3 age bf40 bf4m bf1 wkMedMw3 = bf8 age illw3 ageXillw3 wkModFw3 = none wkModMw3 = none MainEffwkFw3 = age MainEffwkMw3 = workM: age bf8 illw3 shjobw3 SigDoseWKMw3 = no SigDoseWkFw3 = no medsigFw2 = 1 wkMedMw2 = bf8 age illw2 VactnMedFw2 = age illw2 radhlw2 VactnMedMw2 = age illw2 VacatnModFw2 = none MainEffVactnFw2 = age radhlw2 deaw2 SigDoseVactnFw2 = no vactnModMw2 = none MainEffVactnMw2 = age bf7m radhlw2 SigDoseVactnMw2 = no sxLifeMedFw2 = age bf4 bf4m sxLifeMedMw2 = age illw2 InthbModFw2 = none MainEffInthbFw2 = age radhlw2 bf4 SigdoseInthbFw2 = no InthbMw2 = none MainEffInthbMw2 = age radhlw2 shfamw2 SigDoseInthbMw2 = no sxlifeMedFw2 = age illw2 radhlw2 bf4 bf4m sxlifeMedMw2 = age illw2 sxlifeModFw2 = none MainEffsxlifeFw2 = age radhlw2 bf4 bf4m shrelaw2 shfamw2 SigDoseSxlifeFw2 = no sxlifeModMw2 = none SigDosesxlifeMw2 = no MainEffsxlifeMw2 = age bf4 illw2 radhlw2 PrbfmhmMedFw2 = age bf4 PrbfmhmMedMw2 = age PrbfmhmModFw2 = none MainEffPrbfmhmFw2 = age bf4 bf40 SigDosePrbfmhmFw2 = no PrbfmhmModw2 = none SigDosePrbfmhmMw2 = no SigDosePrbfhmMw2 = no MainEffPrbfhmMw2 = bf1 bf4 dvcew2 bf7m ProbsocMedFw2 = age radhlw2 ProbsocMedMw2 = age ProbsocModFw2 = none MainEffProbSocFw2 = age radhlw2 illw2 Shrelaw2 avgcumodsew2 SigDoseProbsocFw2 = yes ProbSocModMw2 = none SigDoseProbsocMw2 = no MainEffPrbsocMw2 = age radhlw2 shjobw2 hmcareMedFw2 = age illw2 hmcareMedMw2 = age illw2 hmcareModFw2 = none SigDoseWKFw2 = 0 SigdoseHmcareFw2 = no hmcareModMw2 = none MainEffhmcareMw2 = none SigDoseHmcareMw2 = no wkMedFw2 = radhlw2 age bf40 bf4m bf1 wkModFw2 = none wkModMw2 = none MainEffwkFw2 = age MainEffwkMw2 = workM: age bf8 illw2 shjobw2 SigDoseWKMw2 = no SigDoseWkFw2 = no hmcrMedFw1 = age icdxcnt shjobw1 bf4 BSIsoma WHPpain WHPsleep WHPel hmcrMedMw1 = age MainEffhmcrFw1 = illw1 age SigDosehmcrFw1 = no hmcrModMw1 = none MainEffhmcrMw1 = age shjobw1 SigDosehmcrMw1 = no wkMedFw1 = age b4 MainEffwkFw1 = age MainEffwkMw1 = age wkMedMw1 = bf40 WkMedMw1 = none WkModFw1 = none WKModMw1 = none SigDoseWkMw1 = no SigDoseWkFw1 = no SigDoseFw1 = no wkModFw1 = none wkModMw1 = none medsigFw1 = 1 prbsocnumMAsig = 8 507 . 508 . * conclusion "age & illw3 are main effects as possible male & female mediator > s" 509 . * conclusion title "their interaction is not a mediator" 510 . 511 . 512 . 513 . 514 . * Other non-signif test results for mediators of the dose-homecare impact 515 . 516 . glm illw3Xd3 illw3 avgcumdosew3 if gender==1, fam(gaussian) link(identity) Iteration 0: log likelihood = -910.27475 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 337 Scale parameter = 12.49768 Deviance = 4211.718004 (1/df) Deviance = 12.49768 Pearson = 4211.718004 (1/df) Pearson = 12.49768 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 5.372204 Log likelihood = -910.2747528 BIC = 2247.363 ------------------------------------------------------------------------------ | OIM illw3Xd3 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- illw3 | 1.785312 .2036071 8.77 0.000 1.386249 2.184374 avgcumdosew3 | 1.08337 .0723425 14.98 0.000 .9415811 1.225159 _cons | -1.330357 .2298973 -5.79 0.000 -1.780947 -.8797666 ------------------------------------------------------------------------------ 517 . glm hp2hmcare illw3Xd3 illw3 avgcumdosew3 if gender==1, fam(binomial) /// > irls scale(dev) link(probit) Iteration 1: deviance = 324.9852 Iteration 2: deviance = 324.7765 Iteration 3: deviance = 324.755 Iteration 4: deviance = 324.7539 Iteration 5: deviance = 324.7539 Iteration 6: deviance = 324.7539 Generalized linear models No. of obs = 340 Optimization : MQL Fisher scoring Residual df = 336 (IRLS EIM) Scale parameter = 1 Deviance = 324.7538899 (1/df) Deviance = .9665294 Pearson = 334.7330022 (1/df) Pearson = .9962292 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1633.772 ------------------------------------------------------------------------------ | EIM hp2hmcare | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- illw3Xd3 | .0296527 .0383533 0.77 0.439 -.0455184 .1048239 illw3 | .3037802 .0878109 3.46 0.001 .131674 .4758864 avgcumdosew3 | -.0397572 .0621297 -0.64 0.522 -.1615292 .0820148 _cons | -.9819848 .10943 -8.97 0.000 -1.196464 -.767506 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 518 . glm illw3Xd3 illw3 avgcumdosew3 if gender==2, fam(gaussian) link(identity) Iteration 0: log likelihood = -985.70781 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 360 Scale parameter = 13.48151 Deviance = 4853.341842 (1/df) Deviance = 13.48151 Pearson = 4853.341842 (1/df) Pearson = 13.48151 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 5.447426 Log likelihood = -985.7078088 BIC = 2731.357 ------------------------------------------------------------------------------ | OIM illw3Xd3 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- illw3 | 1.708471 .1689681 10.11 0.000 1.377299 2.039642 avgcumdosew3 | 2.232994 .1120046 19.94 0.000 2.013469 2.452519 _cons | -2.648599 .251824 -10.52 0.000 -3.142165 -2.155033 ------------------------------------------------------------------------------ 519 . glm hp2hmcare illw3Xd3 illw3 avgcumdosew3 if gender==2, fam(binomial) /// > irls scale(dev) link(probit) Iteration 1: deviance = 460.104 Iteration 2: deviance = 459.2782 Iteration 3: deviance = 459.2401 Iteration 4: deviance = 459.2395 Iteration 5: deviance = 459.2395 Iteration 6: deviance = 459.2395 Generalized linear models No. of obs = 363 Optimization : MQL Fisher scoring Residual df = 359 (IRLS EIM) Scale parameter = 1 Deviance = 459.2395051 (1/df) Deviance = 1.279219 Pearson = 360.8121049 (1/df) Pearson = 1.005048 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1656.851 ------------------------------------------------------------------------------ | EIM hp2hmcare | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- illw3Xd3 | -.0506129 .0397971 -1.27 0.203 -.1286138 .0273881 illw3 | .1996924 .0831248 2.40 0.016 .0367707 .3626141 avgcumdosew3 | .0648611 .0733042 0.88 0.376 -.0788126 .2085348 _cons | -.5685167 .1207782 -4.71 0.000 -.8052376 -.3317958 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 520 . 521 . 522 . glm havmilsq avgcumdosew3 if gender==1, fam(gaussian) link(identity) Iteration 0: log likelihood = -4357.43 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = 7.98e+09 Deviance = 2.69659e+12 (1/df) Deviance = 7.98e+09 Pearson = 2.69659e+12 (1/df) Pearson = 7.98e+09 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 25.64371 Log likelihood = -4357.430049 BIC = 2.70e+12 ------------------------------------------------------------------------------ | OIM havmilsq | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | -1575.31 1817.197 -0.87 0.386 -5136.952 1986.331 _cons | 18893.16 5326.219 3.55 0.000 8453.963 29332.36 ------------------------------------------------------------------------------ 523 . glm hp2hmcare havmilsq if gender==1, fam(binomial) irls scale(dev) link(probi > t) Iteration 1: deviance = 345.527 Iteration 2: deviance = 345.1721 Iteration 3: deviance = 345.1646 Iteration 4: deviance = 345.1644 Iteration 5: deviance = 345.1644 Iteration 6: deviance = 345.1644 Generalized linear models No. of obs = 340 Optimization : MQL Fisher scoring Residual df = 338 (IRLS EIM) Scale parameter = 1 Deviance = 345.1644251 (1/df) Deviance = 1.021197 Pearson = 339.1838387 (1/df) Pearson = 1.003502 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1625.019 ------------------------------------------------------------------------------ | EIM hp2hmcare | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- havmilsq | -9.19e-07 1.39e-06 -0.66 0.509 -3.65e-06 1.81e-06 _cons | -.8078353 .0797621 -10.13 0.000 -.9641661 -.6515045 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 524 . glm havmilsq avgcumdosew3 if gender==2, fam(gaussian) link(identity) Iteration 0: log likelihood = -5315.4087 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = 3.08e+11 Deviance = 1.11219e+14 (1/df) Deviance = 3.08e+11 Pearson = 1.11219e+14 (1/df) Pearson = 3.08e+11 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 29.29702 Log likelihood = -5315.408686 BIC = 1.11e+14 ------------------------------------------------------------------------------ | OIM havmilsq | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | 8378.635 16610.83 0.50 0.614 -24177.99 40935.26 _cons | 50752.51 35316.31 1.44 0.151 -18466.18 119971.2 ------------------------------------------------------------------------------ 525 . glm hp2hmcare havmilsq if gender==2, fam(binomial) irls scale(dev) link(probi > t) Iteration 1: deviance = 466.1751 Iteration 2: deviance = 465.0334 Iteration 3: deviance = 464.73 Iteration 4: deviance = 464.6076 Iteration 5: deviance = 464.5797 Iteration 6: deviance = 464.5779 Iteration 7: deviance = 464.5779 Iteration 8: deviance = 464.5779 Generalized linear models No. of obs = 363 Optimization : MQL Fisher scoring Residual df = 361 (IRLS EIM) Scale parameter = 1 Deviance = 464.5778963 (1/df) Deviance = 1.286919 Pearson = 360.2475414 (1/df) Pearson = .9979156 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1663.302 ------------------------------------------------------------------------------ | EIM hp2hmcare | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- havmilsq | -7.46e-07 1.04e-06 -0.72 0.475 -2.79e-06 1.30e-06 _cons | -.3815177 .0787742 -4.84 0.000 -.5359124 -.227123 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 526 . 527 . glm radhlw3 avgcumdosew3 if gender==1, fam(gaussian) link(identity) Iteration 0: log likelihood = -1695.1855 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = 1261.052 Deviance = 426235.7205 (1/df) Deviance = 1261.052 Pearson = 426235.7205 (1/df) Pearson = 1261.052 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 9.983444 Log likelihood = -1695.185473 BIC = 424265.5 ------------------------------------------------------------------------------ | OIM radhlw3 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | .9606492 .7224692 1.33 0.184 -.4553645 2.376663 _cons | 46.19995 2.117563 21.82 0.000 42.0496 50.3503 ------------------------------------------------------------------------------ 528 . glm hp2hmcare radhlw3 if gender==1, fam(binomial) irls scale(dev) link(probit > ) Iteration 1: deviance = 319.2576 Iteration 2: deviance = 318.3456 Iteration 3: deviance = 318.3441 Iteration 4: deviance = 318.3441 Generalized linear models No. of obs = 340 Optimization : MQL Fisher scoring Residual df = 338 (IRLS EIM) Scale parameter = 1 Deviance = 318.3440747 (1/df) Deviance = .9418464 Pearson = 342.3257119 (1/df) Pearson = 1.012798 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1651.84 ------------------------------------------------------------------------------ | EIM hp2hmcare | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- radhlw3 | .0115758 .0022053 5.25 0.000 .0072534 .0158982 _cons | -1.437377 .1466803 -9.80 0.000 -1.724866 -1.149889 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 529 . glm radhlw3 avgcumdosew3 if gender==2, fam(gaussian) link(identity) Iteration 0: log likelihood = -1798.7074 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = 1185.454 Deviance = 427948.9522 (1/df) Deviance = 1185.454 Pearson = 427948.9522 (1/df) Pearson = 1185.454 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 9.921253 Log likelihood = -1798.707367 BIC = 425821.1 ------------------------------------------------------------------------------ | OIM radhlw3 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | 2.751602 1.03038 2.67 0.008 .7320943 4.77111 _cons | 57.70689 2.190692 26.34 0.000 53.41321 62.00057 ------------------------------------------------------------------------------ 530 . glm hp2hmcare radhlw3 if gender==2, fam(binomial) irls scale(dev) link(probit > ) Iteration 1: deviance = 466.2486 Iteration 2: deviance = 465.6482 Iteration 3: deviance = 465.6481 Iteration 4: deviance = 465.6481 Generalized linear models No. of obs = 363 Optimization : MQL Fisher scoring Residual df = 361 (IRLS EIM) Scale parameter = 1 Deviance = 465.6481297 (1/df) Deviance = 1.289884 Pearson = 362.9350038 (1/df) Pearson = 1.00536 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1662.231 ------------------------------------------------------------------------------ | EIM hp2hmcare | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- radhlw3 | .0026441 .0022316 1.18 0.236 -.0017297 .0070179 _cons | -.5636837 .1583099 -3.56 0.000 -.8739654 -.2534021 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 531 . 532 . title4 "*------- summary matrix construction for dose home care" ------------------------------------------------------------------------------- *------- summary matrix construction for dose home care ------------------------------------------------------------------------------- 533 . 534 . matrix define HP2hmcrMw3 = J(1,8, 0) 535 . matrix define HP2hmcrFw3 = J(1,8, 0) 536 . matrix colnames HP2hmcrMw3= hypnum ptnum wave gender medsig numMAsig numMods > ig /// > numMed 537 . matrix colnames HP2hmcrFw3= hypnum ptnum wave gender medsig numMAsig numMods > ig /// > numMed 538 . matrix rownames HP2hmcrMw3 = hmcareM 539 . matrix rownames HP2hmcrFw3 = hmcareF 540 . matrix define HP2hmcrFw3= (1, 2, 3, 2, 0 ,2, 0 , 2 ) 541 . matrix define HP2hmcrMw3= (1, 2, 3, 1, 0 , 4, 0 , 2 ) 542 . matrix define H1pt2w3 = (HP2wkMw3 \ HP2wkFw3 \ HP2hmcrMw3 \HP2hmcrFw3 > ) 543 . matrix colnames H1pt2w3 = hypnum ptnum wave gender medsig numMAsig numMo > dsig numMed 544 . matrix colnames H1pt2w3 = hypnum ptnum wave gender medsig numMAsig numMo > dsig numMed 545 . matrix rownames H1pt2w3 = HP2wkMw3 WHP2wkFw3 HP2hmcrMw3 HP2hmcrFw3 546 . matlist H1pt2w3 | hypnum ptnum wave gender medsig numMAsig > -------------+----------------------------------------------------------------- - HP2wkMw3 | 1 2 3 1 0 4 > WHP2wkFw3 | 1 2 3 2 0 1 > HP2hmcrMw3 | 1 2 3 1 0 4 > HP2hmcrFw3 | 1 2 3 2 0 2 > | numModsig numMed -------------+---------------------- HP2wkMw3 | 0 4 WHP2wkFw3 | 0 6 HP2hmcrMw3 | 0 2 HP2hmcrFw3 | 0 2 547 . 548 . * see scalar list for names of variables 549 . scalar list VactnMedFw3 = age illw3 radhlw3 VactnMedMw3 = age illw3 VacatnModFw3 = none MainEffVactnFw3 = age radhlw3 deaw3 SigDoseVactnFw3 = no vactnModMw3 = none MainEffVactnMw3 = age bf7m radhlw3 SigDoseVactnMw3 = no sxLifeMedFw3 = age bf4 bf4m sxLifeMedMw3 = age illw3 InthbModFw3 = none MainEffInthbFw3 = age radhlw3 bf4 SigdoseInthbFw3 = no InthbMw3 = none MainEffInthbMw3 = age radhlw3 shfamw3 SigDoseInthbMw3 = no sxlifeMedFw3 = age illw3 radhlw3 bf4 bf4m sxlifeMedMw3 = age illw3 sxlifeModFw3 = none MainEffsxlifeFw3 = age radhlw3 bf4 bf4m shrelaw3 shfamw3 SigDoseSxlifeFw3 = no sxlifeModMw3 = none SigDosesxlifeMw3 = no MainEffsxlifeMw3 = age bf4 illw3 radhlw3 PrbfmhmMedFw3 = age bf4 PrbfmhmMedMw3 = age PrbfmhmModFw3 = none MainEffPrbfmhmFw3 = age bf4 bf40 SigDosePrbfmhmFw3 = no PrbfmhmModw3 = none SigDosePrbfmhmMw3 = no SigDosePrbfhmMw3 = no MainEffPrbfhmMw3 = bf1 bf4 dvcew3 bf7m ProbsocMedFw3 = age radhlw3 ProbsocMedMw3 = age ProbsocModFw3 = none MainEffProbSocFw3 = age radhlw3 illw3 Shrelaw3 avgcumodsew3 SigDoseProbsocFw3 = yes ProbSocModMw3 = none SigDoseProbsocMw3 = no MainEffPrbsocMw3 = age radhlw3 shjobw3 hmcareMedFw3 = age illw3 hmcareMedMw3 = age illw3 hmcareModFw3 = none SigdoseHmcareFw3 = no hmcareModMw3 = none MainEffhmcareMw3 = none SigDoseHmcareMw3 = no wkMedFw3 = radhlw3 age bf40 bf4m bf1 wkMedMw3 = bf8 age illw3 ageXillw3 wkModFw3 = none wkModMw3 = none MainEffwkFw3 = age MainEffwkMw3 = workM: age bf8 illw3 shjobw3 SigDoseWKMw3 = no SigDoseWkFw3 = no medsigFw2 = 1 wkMedMw2 = bf8 age illw2 VactnMedFw2 = age illw2 radhlw2 VactnMedMw2 = age illw2 VacatnModFw2 = none MainEffVactnFw2 = age radhlw2 deaw2 SigDoseVactnFw2 = no vactnModMw2 = none MainEffVactnMw2 = age bf7m radhlw2 SigDoseVactnMw2 = no sxLifeMedFw2 = age bf4 bf4m sxLifeMedMw2 = age illw2 InthbModFw2 = none MainEffInthbFw2 = age radhlw2 bf4 SigdoseInthbFw2 = no InthbMw2 = none MainEffInthbMw2 = age radhlw2 shfamw2 SigDoseInthbMw2 = no sxlifeMedFw2 = age illw2 radhlw2 bf4 bf4m sxlifeMedMw2 = age illw2 sxlifeModFw2 = none MainEffsxlifeFw2 = age radhlw2 bf4 bf4m shrelaw2 shfamw2 SigDoseSxlifeFw2 = no sxlifeModMw2 = none SigDosesxlifeMw2 = no MainEffsxlifeMw2 = age bf4 illw2 radhlw2 PrbfmhmMedFw2 = age bf4 PrbfmhmMedMw2 = age PrbfmhmModFw2 = none MainEffPrbfmhmFw2 = age bf4 bf40 SigDosePrbfmhmFw2 = no PrbfmhmModw2 = none SigDosePrbfmhmMw2 = no SigDosePrbfhmMw2 = no MainEffPrbfhmMw2 = bf1 bf4 dvcew2 bf7m ProbsocMedFw2 = age radhlw2 ProbsocMedMw2 = age ProbsocModFw2 = none MainEffProbSocFw2 = age radhlw2 illw2 Shrelaw2 avgcumodsew2 SigDoseProbsocFw2 = yes ProbSocModMw2 = none SigDoseProbsocMw2 = no MainEffPrbsocMw2 = age radhlw2 shjobw2 hmcareMedFw2 = age illw2 hmcareMedMw2 = age illw2 hmcareModFw2 = none SigDoseWKFw2 = 0 SigdoseHmcareFw2 = no hmcareModMw2 = none MainEffhmcareMw2 = none SigDoseHmcareMw2 = no wkMedFw2 = radhlw2 age bf40 bf4m bf1 wkModFw2 = none wkModMw2 = none MainEffwkFw2 = age MainEffwkMw2 = workM: age bf8 illw2 shjobw2 SigDoseWKMw2 = no SigDoseWkFw2 = no hmcrMedFw1 = age icdxcnt shjobw1 bf4 BSIsoma WHPpain WHPsleep WHPel hmcrMedMw1 = age MainEffhmcrFw1 = illw1 age SigDosehmcrFw1 = no hmcrModMw1 = none MainEffhmcrMw1 = age shjobw1 SigDosehmcrMw1 = no wkMedFw1 = age b4 MainEffwkFw1 = age MainEffwkMw1 = age wkMedMw1 = bf40 WkMedMw1 = none WkModFw1 = none WKModMw1 = none SigDoseWkMw1 = no SigDoseWkFw1 = no SigDoseFw1 = no wkModFw1 = none wkModMw1 = none medsigFw1 = 1 prbsocnumMAsig = 8 550 . 551 . * X * missing the number of main effects in the trimmed models 552 . 553 . //////////////////////////////////////////////////////////////////////// > *--------- Chunk 4 Dose prob soc impact relationship HP2probsoc 554 . *---------------------------------------------------------------------------- > --- 555 . * General model for all part 2 of Nottingham Health Profile 556 . 557 . title " 3. Wave 3 part2 H1: Test of hypothesis 1 Part 2 " ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** 3. Wave 3 part2 H1: Test of hypothesis 1 Part 2 ***** ***** ***** ***** ***** ***** 1 Jul 2012 20:37:19 ***** ******************************************************************************* ******************************************************************************* 558 . title " Wave 3 Dose - HP2probsoc Main effects identification" ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Wave 3 Dose - HP2probsoc Main effects identification ***** ***** ***** ***** ***** ***** 1 Jul 2012 20:37:19 ***** ******************************************************************************* ******************************************************************************* 559 . forvalues j=3/3 { 2. set more off 3. 560 . des age educ1-educ7 marrw`j'1-marrw`j'6 inc1w`j'-inc4w`j' /// > bf1 bf4 bf9 bf11 bf4m bf15m bf30 bf40 4. 561 . foreach var in HP2probsoc { 5. forvalues k=1/2 { 6. di as input "Full main model for `var' for wave= `j' " 7. di _skip(4) 8. di as input "chunk 4 H1 test:Gender= `k' model Wave = `j' for `e(depvar > )' " 9. di _skip(4) 10. title "Full Nottingham Part 2 subscale models for male and then females" 11. 562 . xi: logistic `var' age i.educ occ1w`j'-occ8w`j' /// > marrw`j'1- marrw`j'3 marrw`j'5-marrw`j'6 inc1w`j'-inc4w`j' // > / > radhlw`j' havmil avgcumdosew`j' `w`j'bf' /// > deaw`j' dvcew`j' sepaw`j' accdw`j' movew`j' /// > illw`j' shfamw`j' shhlw`j' shjobw`j' shrelaw`j' suprtw`j' suc > hrw`j' /// > havmilsq if gender==`k', coef nolog difficult iterate(50) 12. estat class 13. estat gof 14. fitstat 15. } 16. } 17. } storage display value variable name type format label variable label ------------------------------------------------------------------------------- age double %8.0g * Respondent's age educ1 byte %8.0g educ==1. did not graduate high school educ2 byte %8.0g educ==2. graduated high school educ3 byte %8.0g educ==3. technical degree educ4 byte %8.0g educ==4. did not finish college/bachelor's educ5 byte %8.0g educ==5. graduated college/bachelor's educ6 byte %8.0g educ==6. finished specialist/master's degree educ7 byte %8.0g educ==7. doctor of science/phd marrw31 byte %8.0g marrw3==1. single marrw32 byte %8.0g marrw3==2. cohabitating marrw33 byte %8.0g marrw3==3. married marrw34 byte %8.0g marrw3==4. separated marrw35 byte %8.0g marrw3==5. divorced marrw36 byte %8.0g marrw3==6. widowed inc1w3 double %15.0g LABJ Income is not sufficient for basic neccessities NOW inc2w3 double %15.0g LABJ Income is just sufficient for basic neccessities NOW inc3w3 double %15.0g LABJ Income is sufficient for basics plus extra purchases/savings NOW inc4w3 double %15.0g LABJ Income allows to comfortably afford luxury items NOW bf1 float %9.0g bf1 = max(0, kzchorn - 40) bf4 float %9.0g bf4 = max(0, 24 - BSIsoma) bf9 float %9.0g bf9= max(0, 30 - shhlw1) bf11 float %9.0g bf11= max(0, 20 - sufamw1) bf4m float %9.0g bf4m = max(0, 32 - BSIsoma) bf15m float %9.0g bf15m= max(0, 1 - icdxcnt) * bf2 bf30 float %9.0g bf30 = max(0, neiw1 - 85) * bf20 bf40 float %9.0g bf40 = max(0, icdxcnt - 1.01635E-007) Full main model for HP2probsoc for wave= 3 chunk 4 H1 test:Gender= 1 model Wave = 3 for hp2hmcare ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Full Nottingham Part 2 subscale models for male and then females ***** ***** ***** ***** ***** ***** 1 Jul 2012 20:37:19 ***** ******************************************************************************* ******************************************************************************* i.educ _Ieduc_1-8 (naturally coded; _Ieduc_1 omitted) note: _Ieduc_4 != 0 predicts failure perfectly _Ieduc_4 dropped and 14 obs not used note: _Ieduc_7 != 0 predicts failure perfectly _Ieduc_7 dropped and 4 obs not used note: _Ieduc_8 != 0 predicts failure perfectly _Ieduc_8 dropped and 2 obs not used note: occ5w3 != 0 predicts failure perfectly occ5w3 dropped and 15 obs not used note: occ6w3 != 0 predicts failure perfectly occ6w3 dropped and 4 obs not used note: marrw32 != 0 predicts failure perfectly marrw32 dropped and 20 obs not used note: bf15m != 0 predicts failure perfectly bf15m dropped and 15 obs not used note: _Ieduc_6 omitted because of collinearity note: occ8w3 omitted because of collinearity note: marrw36 omitted because of collinearity note: bf17 omitted because of collinearity Logistic regression Number of obs = 266 LR chi2(44) = 125.89 Prob > chi2 = 0.0000 Log likelihood = -51.38371 Pseudo R2 = 0.5506 ------------------------------------------------------------------------------ HP2probsoc | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .1094616 .0479486 2.28 0.022 .015484 .2034392 _Ieduc_2 | .7414425 1.297886 0.57 0.568 -1.802367 3.285252 _Ieduc_3 | -1.614771 .8291042 -1.95 0.051 -3.239785 .0102435 _Ieduc_4 | 0 (omitted) _Ieduc_5 | -1.309884 1.008415 -1.30 0.194 -3.286342 .6665737 _Ieduc_6 | 0 (omitted) _Ieduc_7 | 0 (omitted) _Ieduc_8 | 0 (omitted) occ1w3 | -14.19493 1124.783 -0.01 0.990 -2218.729 2190.339 occ2w3 | -12.80013 1124.783 -0.01 0.991 -2217.335 2191.734 occ3w3 | -14.84881 1124.785 -0.01 0.989 -2219.387 2189.689 occ4w3 | -13.35572 1124.784 -0.01 0.991 -2217.891 2191.18 occ5w3 | 0 (omitted) occ6w3 | 0 (omitted) occ7w3 | -14.19043 1124.784 -0.01 0.990 -2218.726 2190.345 occ8w3 | 0 (omitted) marrw31 | 3.074981 1.891094 1.63 0.104 -.6314958 6.781458 marrw32 | 0 (omitted) marrw33 | 1.087086 1.851071 0.59 0.557 -2.540947 4.715119 marrw35 | 2.144183 1.926965 1.11 0.266 -1.632599 5.920964 marrw36 | 0 (omitted) inc1w3 | 12.66541 1124.784 0.01 0.991 -2191.87 2217.201 inc2w3 | 14.23621 1124.783 0.01 0.990 -2190.299 2218.771 inc3w3 | 11.68224 1124.783 0.01 0.992 -2192.853 2216.217 inc4w3 | 13.15717 1124.785 0.01 0.991 -2191.381 2217.695 radhlw3 | .0116102 .013936 0.83 0.405 -.0157038 .0389242 havmil | .010259 .0190025 0.54 0.589 -.0269853 .0475032 avgcumdosew3 | .013934 .0740721 0.19 0.851 -.1312447 .1591127 bf1 | .0049612 .0648373 0.08 0.939 -.1221176 .1320399 bf4 | .3309901 .3608169 0.92 0.359 -.376198 1.038178 bf2 | .0003753 .0003121 1.20 0.229 -.0002364 .000987 bf4m | -.7073564 .3457629 -2.05 0.041 -1.385039 -.0296735 bf5m | .0055743 .0030295 1.84 0.066 -.0003633 .0115119 bf7m | .0005904 .001055 0.56 0.576 -.0014774 .0026582 bf8 | -.0001253 .0000745 -1.68 0.093 -.0002713 .0000207 bf15m | 0 (omitted) bf17 | 0 (omitted) bf20 | -.0283325 .0488173 -0.58 0.562 -.1240127 .0673477 bf22 | .000352 .0002932 1.20 0.230 -.0002227 .0009267 bf29 | -.0000333 .0000588 -0.57 0.572 -.0001486 .000082 bf30 | -.0013785 .0007131 -1.93 0.053 -.0027761 .0000191 bf40 | -.3600239 .3692219 -0.98 0.330 -1.083686 .3636377 deaw3 | -.5217994 .4891348 -1.07 0.286 -1.480486 .4368872 dvcew3 | -.5047921 1.728469 -0.29 0.770 -3.892529 2.882945 sepaw3 | 1.877558 1.625412 1.16 0.248 -1.308191 5.063307 accdw3 | -1.417017 1.419234 -1.00 0.318 -4.198664 1.364631 movew3 | -1.057894 1.576256 -0.67 0.502 -4.1473 2.031511 illw3 | .0330976 .3751226 0.09 0.930 -.7021292 .7683243 shfamw3 | .012083 .0115403 1.05 0.295 -.0105354 .0347015 shhlw3 | -.0165557 .0125582 -1.32 0.187 -.0411693 .0080578 shjobw3 | .032774 .0134379 2.44 0.015 .0064363 .0591118 shrelaw3 | -.0108059 .0117883 -0.92 0.359 -.0339106 .0122988 suprtw3 | -.014138 .0155065 -0.91 0.362 -.0445303 .0162542 suchrw3 | .0131393 .0111977 1.17 0.241 -.0088078 .0350865 havmilsq | -.000014 .0000386 -0.36 0.717 -.0000896 .0000616 _cons | .4495347 5.049973 0.09 0.929 -9.44823 10.3473 ------------------------------------------------------------------------------ Note: 3 failures and 0 successes completely determined. Logistic model for HP2probsoc -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 27 5 | 32 - | 14 220 | 234 -----------+--------------------------+----------- Total | 41 225 | 266 Classified + if predicted Pr(D) >= .5 True D defined as HP2probsoc != 0 -------------------------------------------------- Sensitivity Pr( +| D) 65.85% Specificity Pr( -|~D) 97.78% Positive predictive value Pr( D| +) 84.38% Negative predictive value Pr(~D| -) 94.02% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 2.22% False - rate for true D Pr( -| D) 34.15% False + rate for classified + Pr(~D| +) 15.62% False - rate for classified - Pr( D| -) 5.98% -------------------------------------------------- Correctly classified 92.86% -------------------------------------------------- Logistic model for HP2probsoc, goodness-of-fit test number of observations = 266 number of covariate patterns = 266 Pearson chi2(221) = 138.28 Prob > chi2 = 1.0000 Measures of Fit for logistic of HP2probsoc Log-Lik Intercept Only: -114.331 Log-Lik Full Model: -51.384 D(210): 102.767 LR(44): 125.895 Prob > LR: 0.000 McFadden's R2: 0.551 McFadden's Adj R2: 0.061 Maximum Likelihood R2: 0.377 Cragg & Uhler's R2: 0.654 McKelvey and Zavoina's R2: 0.833 Efron's R2: 0.549 Variance of y*: 19.713 Variance of error: 3.290 Count R2: 0.929 Adj Count R2: 0.537 AIC: 0.807 AIC*n: 214.767 BIC: -1069.767 BIC': 119.779 Full main model for HP2probsoc for wave= 3 chunk 4 H1 test:Gender= 2 model Wave = 3 for HP2probsoc ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Full Nottingham Part 2 subscale models for male and then females ***** ***** ***** ***** ***** ***** 1 Jul 2012 20:37:20 ***** ******************************************************************************* ******************************************************************************* i.educ _Ieduc_1-8 (naturally coded; _Ieduc_1 omitted) note: occ4w3 != 0 predicts failure perfectly occ4w3 dropped and 8 obs not used note: occ5w3 != 0 predicts failure perfectly occ5w3 dropped and 5 obs not used note: occ6w3 != 0 predicts failure perfectly occ6w3 dropped and 4 obs not used note: occ8w3 != 0 predicts failure perfectly occ8w3 dropped and 1 obs not used note: bf15m != 0 predicts failure perfectly bf15m dropped and 11 obs not used note: _Ieduc_8 omitted because of collinearity note: bf17 omitted because of collinearity Logistic regression Number of obs = 333 LR chi2(48) = 182.65 Prob > chi2 = 0.0000 Log likelihood = -85.065495 Pseudo R2 = 0.5177 ------------------------------------------------------------------------------ HP2probsoc | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .1095324 .0321452 3.41 0.001 .0465289 .1725358 _Ieduc_2 | -13.53237 1231.492 -0.01 0.991 -2427.212 2400.147 _Ieduc_3 | -13.52493 1231.492 -0.01 0.991 -2427.204 2400.154 _Ieduc_4 | -12.60239 1231.492 -0.01 0.992 -2426.282 2401.077 _Ieduc_5 | -12.71374 1231.492 -0.01 0.992 -2426.393 2400.966 _Ieduc_6 | -14.01871 1231.492 -0.01 0.991 -2427.698 2399.66 _Ieduc_7 | -14.42024 1231.563 -0.01 0.991 -2428.239 2399.398 _Ieduc_8 | 0 (omitted) occ1w3 | -1.43031 4.480321 -0.32 0.750 -10.21158 7.350959 occ2w3 | -.9422793 4.54239 -0.21 0.836 -9.8452 7.960641 occ3w3 | -.9893619 4.495549 -0.22 0.826 -9.800476 7.821752 occ4w3 | 0 (omitted) occ5w3 | 0 (omitted) occ6w3 | 0 (omitted) occ7w3 | -.3813499 4.479039 -0.09 0.932 -9.160105 8.397405 occ8w3 | 0 (omitted) marrw31 | -1.356413 4.804963 -0.28 0.778 -10.77397 8.061141 marrw32 | 1.424321 4.907376 0.29 0.772 -8.193959 11.0426 marrw33 | .9014745 4.669929 0.19 0.847 -8.251419 10.05437 marrw35 | .1665893 4.645112 0.04 0.971 -8.937664 9.270842 marrw36 | .3174753 4.648882 0.07 0.946 -8.794166 9.429116 inc1w3 | .8600896 4.513897 0.19 0.849 -7.986987 9.707166 inc2w3 | 1.384829 4.490321 0.31 0.758 -7.416038 10.1857 inc3w3 | .4792744 4.482989 0.11 0.915 -8.307222 9.26577 inc4w3 | 2.266942 4.835774 0.47 0.639 -7.211 11.74488 radhlw3 | .0131788 .0108242 1.22 0.223 -.0080363 .0343939 havmil | .0001731 .0072695 0.02 0.981 -.0140748 .014421 avgcumdosew3 | .4373021 .1594734 2.74 0.006 .12474 .7498642 bf1 | .0565003 .0423978 1.33 0.183 -.0265978 .1395985 bf4 | -.5202783 .2238014 -2.32 0.020 -.9589209 -.0816356 bf2 | .0000421 .0001478 0.28 0.776 -.0002477 .0003318 bf4m | .2426577 .1977977 1.23 0.220 -.1450185 .630334 bf5m | -.0017451 .0026768 -0.65 0.514 -.0069915 .0035013 bf7m | .0007865 .0007919 0.99 0.321 -.0007656 .0023387 bf8 | .0000207 .0000544 0.38 0.704 -.000086 .0001273 bf15m | 0 (omitted) bf17 | 0 (omitted) bf20 | -.0669294 .0330398 -2.03 0.043 -.1316862 -.0021726 bf22 | -.0000944 .0001823 -0.52 0.605 -.0004517 .0002629 bf29 | -.0000309 .000047 -0.66 0.511 -.0001229 .0000611 bf30 | .0003246 .0004246 0.76 0.445 -.0005076 .0011567 bf40 | .0606979 .1844629 0.33 0.742 -.3008427 .4222385 deaw3 | .1696097 .2295421 0.74 0.460 -.2802844 .6195039 dvcew3 | .3810548 1.285314 0.30 0.767 -2.138115 2.900224 sepaw3 | -2.876602 1.529689 -1.88 0.060 -5.874737 .1215322 accdw3 | .1226563 .714668 0.17 0.864 -1.278067 1.52338 movew3 | 1.918652 1.360681 1.41 0.159 -.7482334 4.585538 illw3 | .2671943 .2045213 1.31 0.191 -.1336601 .6680487 shfamw3 | -.0003116 .0095404 -0.03 0.974 -.0190104 .0183873 shhlw3 | -.0026048 .0074647 -0.35 0.727 -.0172353 .0120256 shjobw3 | .006075 .0086284 0.70 0.481 -.0108364 .0229864 shrelaw3 | -.0267274 .010033 -2.66 0.008 -.0463918 -.007063 suprtw3 | -.0065983 .0100162 -0.66 0.510 -.0262297 .0130331 suchrw3 | .0015649 .0064519 0.24 0.808 -.0110806 .0142105 havmilsq | -3.19e-06 .0000124 -0.26 0.797 -.0000275 .0000211 _cons | 6.986764 1231.505 0.01 0.995 -2406.718 2420.692 ------------------------------------------------------------------------------ Note: 1 failure and 0 successes completely determined. Logistic model for HP2probsoc -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 54 13 | 67 - | 20 246 | 266 -----------+--------------------------+----------- Total | 74 259 | 333 Classified + if predicted Pr(D) >= .5 True D defined as HP2probsoc != 0 -------------------------------------------------- Sensitivity Pr( +| D) 72.97% Specificity Pr( -|~D) 94.98% Positive predictive value Pr( D| +) 80.60% Negative predictive value Pr(~D| -) 92.48% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 5.02% False - rate for true D Pr( -| D) 27.03% False + rate for classified + Pr(~D| +) 19.40% False - rate for classified - Pr( D| -) 7.52% -------------------------------------------------- Correctly classified 90.09% -------------------------------------------------- Logistic model for HP2probsoc, goodness-of-fit test number of observations = 333 number of covariate patterns = 333 Pearson chi2(284) = 335.12 Prob > chi2 = 0.0199 Measures of Fit for logistic of HP2probsoc Log-Lik Intercept Only: -176.392 Log-Lik Full Model: -85.065 D(277): 170.131 LR(48): 182.653 Prob > LR: 0.000 McFadden's R2: 0.518 McFadden's Adj R2: 0.200 Maximum Likelihood R2: 0.422 Cragg & Uhler's R2: 0.646 McKelvey and Zavoina's R2: 0.810 Efron's R2: 0.561 Variance of y*: 17.273 Variance of error: 3.290 Count R2: 0.901 Adj Count R2: 0.554 AIC: 0.847 AIC*n: 282.131 BIC: -1438.724 BIC': 96.138 563 . ************************ Possible signifi dose effect*********************** > *** 564 . *-----Chunk 4 dose3 social problem impact---for women in wave three 565 . ***************************************************************************** > ** 566 . title4 "Chunk 4 trimmed models of dose and HP2work relationship in wave 3" ------------------------------------------------------------------------------- Chunk 4 trimmed models of dose and HP2work relationship in wave 3 ------------------------------------------------------------------------------- 567 . * male models 568 . set more off 569 . forvalues j=3/3 { 2. local w3bf bf1 bf4 bf2 bf4m bf5m bf7m bf8 bf15m bf17 bf20 bf22 bf29 bf30 b > f40 3. title3 "trimmed HP2probsoc main effects models wave 3 for H1 part 2 with d > ose ns" 4. title "Wave 3 dose HP2probsoc relationship but avgcumdosew`j': Dose not si > gnif" 5. xi:logit HP2probsoc age i.educ radhlw3 accdw`j' bf8 shjobw`j' suchrw3 hav > milsq /// > avgcumdosew`j' if gender==1 6. estat class 7. estat gof 8. fitstat 9. } ------------------------------------------------------------------------------- title3 : trimmed HP2probsoc main effects models wave 3 for H1 part 2 with dose > ns 1 Jul 2012 20:37:22 computer Macintosh (Intel 64-bit) folder /Users/robertyaffee/Documents/data/research/chwk/phase3/Htests/H1tests/ > h1pt2 Data file chwide1jul2012.dta currrently has 2402 variables and 703 observ > ations ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** *****Wave 3 dose HP2probsoc relationship but avgcumdosew3: Dose not signif***** ***** ***** ***** ***** ***** 1 Jul 2012 20:37:22 ***** ******************************************************************************* ******************************************************************************* i.educ _Ieduc_1-8 (naturally coded; _Ieduc_1 omitted) note: _Ieduc_4 != 0 predicts failure perfectly _Ieduc_4 dropped and 14 obs not used note: _Ieduc_7 != 0 predicts failure perfectly _Ieduc_7 dropped and 4 obs not used note: _Ieduc_8 != 0 predicts failure perfectly _Ieduc_8 dropped and 2 obs not used note: _Ieduc_6 omitted because of collinearity Iteration 0: log likelihood = -122.49818 Iteration 1: log likelihood = -94.094194 Iteration 2: log likelihood = -86.783267 Iteration 3: log likelihood = -86.595645 Iteration 4: log likelihood = -86.595407 Iteration 5: log likelihood = -86.595407 Logistic regression Number of obs = 320 LR chi2(11) = 71.81 Prob > chi2 = 0.0000 Log likelihood = -86.595407 Pseudo R2 = 0.2931 ------------------------------------------------------------------------------ HP2probsoc | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0535719 .0238163 2.25 0.024 .0068928 .100251 _Ieduc_2 | .3605111 .9297636 0.39 0.698 -1.461792 2.182814 _Ieduc_3 | -.6699915 .4771602 -1.40 0.160 -1.605208 .2652253 _Ieduc_4 | 0 (omitted) _Ieduc_5 | -.5495985 .5675642 -0.97 0.333 -1.662004 .5628069 _Ieduc_6 | 0 (omitted) _Ieduc_7 | 0 (omitted) _Ieduc_8 | 0 (omitted) radhlw3 | .0305161 .0070656 4.32 0.000 .0166678 .0443643 accdw3 | -1.646048 .8717553 -1.89 0.059 -3.354657 .0625614 bf8 | -.0000366 .0000261 -1.40 0.161 -.0000877 .0000146 shjobw3 | .0159184 .0057194 2.78 0.005 .0047085 .0271283 suchrw3 | .0135001 .0055103 2.45 0.014 .0027001 .0243001 havmilsq | -1.21e-06 4.50e-06 -0.27 0.788 -.00001 7.61e-06 avgcumdosew3 | .0300057 .0490462 0.61 0.541 -.0661232 .1261345 _cons | -7.526129 1.376102 -5.47 0.000 -10.22324 -4.829018 ------------------------------------------------------------------------------ Logistic model for HP2probsoc -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 13 6 | 19 - | 28 273 | 301 -----------+--------------------------+----------- Total | 41 279 | 320 Classified + if predicted Pr(D) >= .5 True D defined as HP2probsoc != 0 -------------------------------------------------- Sensitivity Pr( +| D) 31.71% Specificity Pr( -|~D) 97.85% Positive predictive value Pr( D| +) 68.42% Negative predictive value Pr(~D| -) 90.70% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 2.15% False - rate for true D Pr( -| D) 68.29% False + rate for classified + Pr(~D| +) 31.58% False - rate for classified - Pr( D| -) 9.30% -------------------------------------------------- Correctly classified 89.38% -------------------------------------------------- Logistic model for HP2probsoc, goodness-of-fit test number of observations = 320 number of covariate patterns = 319 Pearson chi2(307) = 262.97 Prob > chi2 = 0.9673 Measures of Fit for logit of HP2probsoc Log-Lik Intercept Only: -122.498 Log-Lik Full Model: -86.595 D(304): 173.191 LR(11): 71.806 Prob > LR: 0.000 McFadden's R2: 0.293 McFadden's Adj R2: 0.162 Maximum Likelihood R2: 0.201 Cragg & Uhler's R2: 0.376 McKelvey and Zavoina's R2: 0.500 Efron's R2: 0.271 Variance of y*: 6.583 Variance of error: 3.290 Count R2: 0.894 Adj Count R2: 0.171 AIC: 0.641 AIC*n: 205.191 BIC: -1580.379 BIC': -8.354 570 . 571 . 572 . forvalues j=3/3 { 2. title "trimmed HP2probsoc main effects models wave `j'" " for H1 part 2 wi > th dose ns" 3. title2 "Wave `j dose HP2work relationship but avgcumdosew`j': Dose not sig > nif" 4. } ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** trimmed HP2probsoc main effects models wave 3 ***** ***** for H1 part 2 with dose ns ***** ***** ***** ***** ***** ***** 1 Jul 2012 20:37:24 ***** ******************************************************************************* ******************************************************************************* ------------------------------------------------------------------------------- title2: Wave `j dose HP2work relationship but avgcumdosew3: Dose not signif Date and time: 1 Jul 2012 20:37:24 Working directory: /Users/robertyaffee/ > Documents/data/research/chwk/phase3/Htests/H1tests/h1pt2 Stata data file: chwide1jul2012.dta ha > s 2402 variables and 703 observations Wave `j dose HP2work relationship but avgcumdosew3: Dose not signif ------------------------------------------------------------------------------- 573 . 574 . foreach var in suchrw3 radhlw3 shjobw3 { 2. cap gen `var'Xd3= `var'*avgcumdosew3 3. } 575 . 576 . forvalues j=3/3 { 2. title "Main effects Dose ProbSoc model for males" 3. logit HP2probsoc age avgcumdosew3 radhlw3 shjobw`j' if gender==1 4. estat class 5. estat gof 6. fitstat 7. } ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Main effects Dose ProbSoc model for males ***** ***** ***** ***** ***** ***** 1 Jul 2012 20:37:24 ***** ******************************************************************************* ******************************************************************************* Iteration 0: log likelihood = -125.15243 Iteration 1: log likelihood = -102.23967 Iteration 2: log likelihood = -97.397123 Iteration 3: log likelihood = -97.305516 Iteration 4: log likelihood = -97.305496 Iteration 5: log likelihood = -97.305496 Logistic regression Number of obs = 340 LR chi2(4) = 55.69 Prob > chi2 = 0.0000 Log likelihood = -97.305496 Pseudo R2 = 0.2225 ------------------------------------------------------------------------------ HP2probsoc | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0793863 .0196172 4.05 0.000 .0409372 .1178353 avgcumdosew3 | .0349899 .0473999 0.74 0.460 -.0579122 .1278919 radhlw3 | .0232266 .0060628 3.83 0.000 .0113437 .0351094 shjobw3 | .0140642 .0050535 2.78 0.005 .0041595 .0239689 _cons | -8.338983 1.267447 -6.58 0.000 -10.82313 -5.854832 ------------------------------------------------------------------------------ Logistic model for HP2probsoc -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 5 3 | 8 - | 36 296 | 332 -----------+--------------------------+----------- Total | 41 299 | 340 Classified + if predicted Pr(D) >= .5 True D defined as HP2probsoc != 0 -------------------------------------------------- Sensitivity Pr( +| D) 12.20% Specificity Pr( -|~D) 99.00% Positive predictive value Pr( D| +) 62.50% Negative predictive value Pr(~D| -) 89.16% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 1.00% False - rate for true D Pr( -| D) 87.80% False + rate for classified + Pr(~D| +) 37.50% False - rate for classified - Pr( D| -) 10.84% -------------------------------------------------- Correctly classified 88.53% -------------------------------------------------- Logistic model for HP2probsoc, goodness-of-fit test number of observations = 340 number of covariate patterns = 328 Pearson chi2(323) = 293.19 Prob > chi2 = 0.8819 Measures of Fit for logit of HP2probsoc Log-Lik Intercept Only: -125.152 Log-Lik Full Model: -97.305 D(335): 194.611 LR(4): 55.694 Prob > LR: 0.000 McFadden's R2: 0.223 McFadden's Adj R2: 0.183 Maximum Likelihood R2: 0.151 Cragg & Uhler's R2: 0.290 McKelvey and Zavoina's R2: 0.409 Efron's R2: 0.189 Variance of y*: 5.568 Variance of error: 3.290 Count R2: 0.885 Adj Count R2: 0.049 AIC: 0.602 AIC*n: 204.611 BIC: -1758.086 BIC': -32.378 577 . 578 . scalar MainEffPrbsocMw3 = "age radhlw3 shjobw3" 579 . 580 . 581 . forvalues j=3/3 { 2. logit HP2probsoc age radhlw3 shjobw`j' /// > avgcumdosew`j' /// > shjobw3Xd3 if gender==1 3. estat class 4. estat gof 5. fitstat 6. } Iteration 0: log likelihood = -125.15243 Iteration 1: log likelihood = -99.524419 Iteration 2: log likelihood = -94.068605 Iteration 3: log likelihood = -93.949644 Iteration 4: log likelihood = -93.948748 Iteration 5: log likelihood = -93.948746 Logistic regression Number of obs = 340 LR chi2(5) = 62.41 Prob > chi2 = 0.0000 Log likelihood = -93.948746 Pseudo R2 = 0.2493 ------------------------------------------------------------------------------ HP2probsoc | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0751262 .0195236 3.85 0.000 .0368608 .1133917 radhlw3 | .0251104 .0062707 4.00 0.000 .0128201 .0374008 shjobw3 | -.0001631 .0088177 -0.02 0.985 -.0174456 .0171193 avgcumdosew3 | -.2525242 .2724481 -0.93 0.354 -.7865126 .2814642 shjobw3Xd3 | .0124767 .0071063 1.76 0.079 -.0014514 .0264049 _cons | -7.860581 1.288837 -6.10 0.000 -10.38665 -5.334508 ------------------------------------------------------------------------------ Note: 0 failures and 1 success completely determined. Logistic model for HP2probsoc -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 6 3 | 9 - | 35 296 | 331 -----------+--------------------------+----------- Total | 41 299 | 340 Classified + if predicted Pr(D) >= .5 True D defined as HP2probsoc != 0 -------------------------------------------------- Sensitivity Pr( +| D) 14.63% Specificity Pr( -|~D) 99.00% Positive predictive value Pr( D| +) 66.67% Negative predictive value Pr(~D| -) 89.43% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 1.00% False - rate for true D Pr( -| D) 85.37% False + rate for classified + Pr(~D| +) 33.33% False - rate for classified - Pr( D| -) 10.57% -------------------------------------------------- Correctly classified 88.82% -------------------------------------------------- Logistic model for HP2probsoc, goodness-of-fit test number of observations = 340 number of covariate patterns = 328 Pearson chi2(322) = 318.24 Prob > chi2 = 0.5488 Measures of Fit for logit of HP2probsoc Log-Lik Intercept Only: -125.152 Log-Lik Full Model: -93.949 D(334): 187.897 LR(5): 62.407 Prob > LR: 0.000 McFadden's R2: 0.249 McFadden's Adj R2: 0.201 Maximum Likelihood R2: 0.168 Cragg & Uhler's R2: 0.322 McKelvey and Zavoina's R2: 0.615 Efron's R2: 0.228 Variance of y*: 8.541 Variance of error: 3.290 Count R2: 0.888 Adj Count R2: 0.073 AIC: 0.588 AIC*n: 199.897 BIC: -1758.970 BIC': -33.263 582 . scalar SigDoseProbsocMw3 = "no" 583 . * xx no signific radhwl3 by dose effect 584 . * xx for males no signif dose social problem effect 585 . * xx for males no significant moderator in dose social problem effect 586 . scalar ProbSocModMw3 = "none" 587 . 588 . 589 . ************ Female social problems model possible significant dose relations > hip 590 . 591 . * female models 592 . 593 . forvalues j=3/3 { 2. set more off 3. local w3bf bf1 bf4 bf2 bf4m bf5m bf7m bf8 bf15m bf17 bf20 bf22 bf29 bf30 b > f40 4. title3 "trimmed HP2probsoc main effects models wave 3 for H1 part 2 with d > ose ns" 5. title "Wave 3 dose HP2probsoc relationship but avgcumdosew`j': Dose not si > gnif" 6. logit HP2probsoc age radhlw3 accdw`j' sepaw`j' illw`j' shjobw`j' //// > shrelaw`j' suchrw3 havmilsq avgcumdosew`j' if gender==2 7. estat class 8. estat gof 9. fitstat 10. } ------------------------------------------------------------------------------- title3 : trimmed HP2probsoc main effects models wave 3 for H1 part 2 with dose > ns 1 Jul 2012 20:37:26 computer Macintosh (Intel 64-bit) folder /Users/robertyaffee/Documents/data/research/chwk/phase3/Htests/H1tests/ > h1pt2 Data file chwide1jul2012.dta currrently has 2402 variables and 703 observ > ations ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** *****Wave 3 dose HP2probsoc relationship but avgcumdosew3: Dose not signif***** ***** ***** ***** ***** ***** 1 Jul 2012 20:37:26 ***** ******************************************************************************* ******************************************************************************* Iteration 0: log likelihood = -183.34177 Iteration 1: log likelihood = -123.45484 Iteration 2: log likelihood = -113.79263 Iteration 3: log likelihood = -112.73 Iteration 4: log likelihood = -112.14405 Iteration 5: log likelihood = -112.0764 Iteration 6: log likelihood = -112.07463 Iteration 7: log likelihood = -112.07462 Logistic regression Number of obs = 362 LR chi2(10) = 142.53 Prob > chi2 = 0.0000 Log likelihood = -112.07462 Pseudo R2 = 0.3887 ------------------------------------------------------------------------------ HP2probsoc | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .1199451 .020794 5.77 0.000 .0791897 .1607005 radhlw3 | .0211303 .0055776 3.79 0.000 .0101983 .0320622 accdw3 | -.0504717 .5021919 -0.10 0.920 -1.03475 .9338064 sepaw3 | -1.843435 1.040782 -1.77 0.077 -3.883329 .1964598 illw3 | .3907454 .1531736 2.55 0.011 .0905306 .6909602 shjobw3 | -.0025249 .005367 -0.47 0.638 -.0130441 .0079943 shrelaw3 | -.0165931 .0059102 -2.81 0.005 -.028177 -.0050093 suchrw3 | .0025861 .0039833 0.65 0.516 -.0052211 .0103933 havmilsq | -7.39e-06 6.74e-06 -1.10 0.273 -.0000206 5.82e-06 avgcumdosew3 | .360538 .119122 3.03 0.002 .1270632 .5940128 _cons | -9.607496 1.314552 -7.31 0.000 -12.18397 -7.031022 ------------------------------------------------------------------------------ Note: 3 failures and 0 successes completely determined. Logistic model for HP2probsoc -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 39 12 | 51 - | 35 276 | 311 -----------+--------------------------+----------- Total | 74 288 | 362 Classified + if predicted Pr(D) >= .5 True D defined as HP2probsoc != 0 -------------------------------------------------- Sensitivity Pr( +| D) 52.70% Specificity Pr( -|~D) 95.83% Positive predictive value Pr( D| +) 76.47% Negative predictive value Pr(~D| -) 88.75% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 4.17% False - rate for true D Pr( -| D) 47.30% False + rate for classified + Pr(~D| +) 23.53% False - rate for classified - Pr( D| -) 11.25% -------------------------------------------------- Correctly classified 87.02% -------------------------------------------------- Logistic model for HP2probsoc, goodness-of-fit test number of observations = 362 number of covariate patterns = 362 Pearson chi2(351) = 411.55 Prob > chi2 = 0.0142 Measures of Fit for logit of HP2probsoc Log-Lik Intercept Only: -183.342 Log-Lik Full Model: -112.075 D(351): 224.149 LR(10): 142.534 Prob > LR: 0.000 McFadden's R2: 0.389 McFadden's Adj R2: 0.329 Maximum Likelihood R2: 0.325 Cragg & Uhler's R2: 0.511 McKelvey and Zavoina's R2: 0.867 Efron's R2: 0.431 Variance of y*: 24.799 Variance of error: 3.290 Count R2: 0.870 Adj Count R2: 0.365 AIC: 0.680 AIC*n: 246.149 BIC: -1843.818 BIC': -83.618 594 . 595 . scalar SigDoseProbsocFw3 = "yes" 596 . scalar MainEffProbSocFw3 = "age radhlw3 illw3 Shrelaw3 avgcumodsew3" 597 . 598 . * trimmed female model with basis functions 599 . forvalues j=3/3 { 2. set more off 3. local w3bf bf1 bf4 bf2 bf4m bf5m bf7m bf8 bf15m bf17 bf20 bf22 bf29 bf30 b > f40 4. title "trimmed HP2probsoc main effects models wave 3 for H1 part 2 " "Dose > is signif Females" 5. title "Wave 3 dose HP2probsoc relationship but avgcumdosew`j': Dose signif > " 6. title "Possible agorithmic artifact needs checking" 7. logit HP2probsoc age radhlw3 illw`j' `w3bf' //// > shrelaw`j' avgcumdosew`j' if gender==2 8. estat class 9. estat gof 10. fitstat 11. } ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** trimmed HP2probsoc main effects models wave 3 for H1 part 2 ***** ***** Dose is signif Females ***** ***** ***** ***** ***** ***** 1 Jul 2012 20:37:28 ***** ******************************************************************************* ******************************************************************************* ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Wave 3 dose HP2probsoc relationship but avgcumdosew3: Dose signif ***** ***** ***** ***** ***** ***** 1 Jul 2012 20:37:28 ***** ******************************************************************************* ******************************************************************************* ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Possible agorithmic artifact needs checking ***** ***** ***** ***** ***** ***** 1 Jul 2012 20:37:28 ***** ******************************************************************************* ******************************************************************************* note: bf15m != 0 predicts failure perfectly bf15m dropped and 12 obs not used note: bf17 omitted because of collinearity Iteration 0: log likelihood = -180.7823 Iteration 1: log likelihood = -112.88537 Iteration 2: log likelihood = -100.94644 Iteration 3: log likelihood = -100.42263 Iteration 4: log likelihood = -100.42122 Iteration 5: log likelihood = -100.42122 Logistic regression Number of obs = 351 LR chi2(17) = 160.72 Prob > chi2 = 0.0000 Log likelihood = -100.42122 Pseudo R2 = 0.4445 ------------------------------------------------------------------------------ HP2probsoc | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .1073124 .0208977 5.14 0.000 .0663537 .1482711 radhlw3 | .0186595 .0090599 2.06 0.039 .0009026 .0364165 illw3 | .2164694 .1656953 1.31 0.191 -.1082875 .5412263 bf1 | .0336012 .0334153 1.01 0.315 -.0318916 .0990939 bf4 | -.3133546 .1907491 -1.64 0.100 -.687216 .0605068 bf2 | -4.52e-07 .0001044 -0.00 0.997 -.0002052 .0002043 bf4m | .1185749 .1733569 0.68 0.494 -.2211983 .4583481 bf5m | -.0032317 .0024163 -1.34 0.181 -.0079675 .0015042 bf7m | .0003788 .000645 0.59 0.557 -.0008853 .0016429 bf8 | .0000426 .0000472 0.90 0.367 -.0000499 .000135 bf15m | 0 (omitted) bf17 | 0 (omitted) bf20 | -.0379984 .0263966 -1.44 0.150 -.0897347 .0137379 bf22 | -.0000771 .0001567 -0.49 0.623 -.0003841 .00023 bf29 | -3.07e-06 .0000388 -0.08 0.937 -.0000791 .0000729 bf30 | .0001674 .0003328 0.50 0.615 -.0004848 .0008196 bf40 | .0213847 .1643559 0.13 0.896 -.300747 .3435164 shrelaw3 | -.0189004 .0066211 -2.85 0.004 -.0318775 -.0059234 avgcumdosew3 | .393852 .138802 2.84 0.005 .121805 .665899 _cons | -6.458746 2.119349 -3.05 0.002 -10.61259 -2.304899 ------------------------------------------------------------------------------ Logistic model for HP2probsoc -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 49 11 | 60 - | 25 266 | 291 -----------+--------------------------+----------- Total | 74 277 | 351 Classified + if predicted Pr(D) >= .5 True D defined as HP2probsoc != 0 -------------------------------------------------- Sensitivity Pr( +| D) 66.22% Specificity Pr( -|~D) 96.03% Positive predictive value Pr( D| +) 81.67% Negative predictive value Pr(~D| -) 91.41% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 3.97% False - rate for true D Pr( -| D) 33.78% False + rate for classified + Pr(~D| +) 18.33% False - rate for classified - Pr( D| -) 8.59% -------------------------------------------------- Correctly classified 89.74% -------------------------------------------------- Logistic model for HP2probsoc, goodness-of-fit test number of observations = 351 number of covariate patterns = 351 Pearson chi2(333) = 457.28 Prob > chi2 = 0.0000 Measures of Fit for logit of HP2probsoc Log-Lik Intercept Only: -180.782 Log-Lik Full Model: -100.421 D(331): 200.842 LR(17): 160.722 Prob > LR: 0.000 McFadden's R2: 0.445 McFadden's Adj R2: 0.334 Maximum Likelihood R2: 0.367 Cragg & Uhler's R2: 0.571 McKelvey and Zavoina's R2: 0.662 Efron's R2: 0.488 Variance of y*: 9.746 Variance of error: 3.290 Count R2: 0.897 Adj Count R2: 0.514 AIC: 0.686 AIC*n: 240.842 BIC: -1739.078 BIC': -61.089 600 . 601 . foreach var in bf4 shrelaw3 { 2. cap gen `var'Xd3 = `var'*avgcumdosew3 3. } 602 . 603 . * testing the female moderator model with basis functions 604 . 605 . set more off 606 . local w3bf bf1 bf4 bf2 bf4m bf5m bf7m bf8 bf15m bf17 bf20 bf22 bf29 bf30 bf40 > 607 . title "trimmed HP2socprob main effects wv 3 for Hyp1 pt 2" "dose is signif f > or females" ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** trimmed HP2socprob main effects wv 3 for Hyp1 pt 2 ***** ***** dose is signif for females ***** ***** ***** ***** ***** ***** 1 Jul 2012 20:37:29 ***** ******************************************************************************* ******************************************************************************* 608 . title "Wave 3 dose HP2socprob relationship but avgcumdosew`j'" " Dose is sign > if for females" ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Wave 3 dose HP2socprob relationship but avgcumdosew ***** ***** Dose is signif for females ***** ***** ***** ***** ***** ***** 1 Jul 2012 20:37:29 ***** ******************************************************************************* ******************************************************************************* 609 . title "But this signif may be false positive due to backward stepwise algorit > hm" ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** *****But this signif may be false positive due to backward stepwise algorithm** > *** ***** ***** ***** ***** ***** 1 Jul 2012 20:37:29 ***** ******************************************************************************* ******************************************************************************* 610 . 611 . 612 . logit HP2probsoc age radhlw3 illw3 bf4 //// > shrelaw3 avgcumdosew3 bf4Xd3 shrelaw3Xd3 /// > if gender==2 Iteration 0: log likelihood = -183.5701 Iteration 1: log likelihood = -115.57598 Iteration 2: log likelihood = -104.01427 Iteration 3: log likelihood = -103.59509 Iteration 4: log likelihood = -103.59367 Iteration 5: log likelihood = -103.59367 Logistic regression Number of obs = 363 LR chi2(8) = 159.95 Prob > chi2 = 0.0000 Log likelihood = -103.59367 Pseudo R2 = 0.4357 ------------------------------------------------------------------------------ HP2probsoc | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .1028004 .0196031 5.24 0.000 .064379 .1412218 radhlw3 | .0177202 .0060309 2.94 0.003 .0058999 .0295405 illw3 | .1431181 .1461189 0.98 0.327 -.1432697 .4295058 bf4 | -.1143471 .0744815 -1.54 0.125 -.2603281 .031634 shrelaw3 | -.0144139 .0099309 -1.45 0.147 -.0338781 .0050504 avgcumdosew3 | 1.092776 .6493144 1.68 0.092 -.1798569 2.365409 bf4Xd3 | -.0638129 .0641358 -0.99 0.320 -.1895167 .0618909 shrelaw3Xd3 | -.0059117 .0071313 -0.83 0.407 -.0198889 .0080654 _cons | -7.465103 1.452311 -5.14 0.000 -10.31158 -4.618627 ------------------------------------------------------------------------------ 613 . estat class Logistic model for HP2probsoc -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 46 10 | 56 - | 28 279 | 307 -----------+--------------------------+----------- Total | 74 289 | 363 Classified + if predicted Pr(D) >= .5 True D defined as HP2probsoc != 0 -------------------------------------------------- Sensitivity Pr( +| D) 62.16% Specificity Pr( -|~D) 96.54% Positive predictive value Pr( D| +) 82.14% Negative predictive value Pr(~D| -) 90.88% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 3.46% False - rate for true D Pr( -| D) 37.84% False + rate for classified + Pr(~D| +) 17.86% False - rate for classified - Pr( D| -) 9.12% -------------------------------------------------- Correctly classified 89.53% -------------------------------------------------- 614 . estat gof Logistic model for HP2probsoc, goodness-of-fit test number of observations = 363 number of covariate patterns = 361 Pearson chi2(352) = 427.83 Prob > chi2 = 0.0035 615 . fitstat Measures of Fit for logit of HP2probsoc Log-Lik Intercept Only: -183.570 Log-Lik Full Model: -103.594 D(354): 207.187 LR(8): 159.953 Prob > LR: 0.000 McFadden's R2: 0.436 McFadden's Adj R2: 0.387 Maximum Likelihood R2: 0.356 Cragg & Uhler's R2: 0.560 McKelvey and Zavoina's R2: 0.677 Efron's R2: 0.482 Variance of y*: 10.184 Variance of error: 3.290 Count R2: 0.895 Adj Count R2: 0.486 AIC: 0.620 AIC*n: 225.187 BIC: -1879.431 BIC': -112.798 616 . 617 . scalar ProbsocModFw3 = "none" 618 . 619 . title4 " testing for male and female dose probsoc mediators" ------------------------------------------------------------------------------- testing for male and female dose probsoc mediators ------------------------------------------------------------------------------- 620 . * Male mediator dose social problem response models 621 . 622 . 623 . 624 . // age is a male mediator 625 . glm age avgcumdosew3 if gender==1, fam(gaus) link(identity) Iteration 0: log likelihood = -1330.6336 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = 147.7142 Deviance = 49927.38549 (1/df) Deviance = 147.7142 Pearson = 49927.38549 (1/df) Pearson = 147.7142 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 7.839021 Log likelihood = -1330.633586 BIC = 47957.2 ------------------------------------------------------------------------------ | OIM age | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | .5433648 .2472657 2.20 0.028 .058733 1.027997 _cons | 48.52021 .7247376 66.95 0.000 47.09975 49.94067 ------------------------------------------------------------------------------ 626 . glm HP2probsoc age if gender==1, fam(bin) irls link(probit) scale(dev) Iteration 1: deviance = 230.0069 Iteration 2: deviance = 223.5454 Iteration 3: deviance = 223.2469 Iteration 4: deviance = 223.2456 Iteration 5: deviance = 223.2456 Generalized linear models No. of obs = 340 Optimization : MQL Fisher scoring Residual df = 338 (IRLS EIM) Scale parameter = 1 Deviance = 223.2456447 (1/df) Deviance = .6604901 Pearson = 331.0340472 (1/df) Pearson = .9793907 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1746.938 ------------------------------------------------------------------------------ | EIM HP2probsoc | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0392343 .0064286 6.10 0.000 .0266344 .0518342 _cons | -3.234772 .3587306 -9.02 0.000 -3.937871 -2.531673 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 627 . 628 . glm radhlw3 avgcumdosew3 if gender==1, fam(gaus) link(identity) Iteration 0: log likelihood = -1695.1855 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = 1261.052 Deviance = 426235.7205 (1/df) Deviance = 1261.052 Pearson = 426235.7205 (1/df) Pearson = 1261.052 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 9.983444 Log likelihood = -1695.185473 BIC = 424265.5 ------------------------------------------------------------------------------ | OIM radhlw3 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | .9606492 .7224692 1.33 0.184 -.4553645 2.376663 _cons | 46.19995 2.117563 21.82 0.000 42.0496 50.3503 ------------------------------------------------------------------------------ 629 . glm HP2probsoc radhlw3 if gender==1,fam(bin) irls link(probit) scale(dev) Iteration 1: deviance = 224.6665 Iteration 2: deviance = 216.1679 Iteration 3: deviance = 215.5978 Iteration 4: deviance = 215.5929 Iteration 5: deviance = 215.5929 Generalized linear models No. of obs = 340 Optimization : MQL Fisher scoring Residual df = 338 (IRLS EIM) Scale parameter = 1 Deviance = 215.5929138 (1/df) Deviance = .6378489 Pearson = 333.7963451 (1/df) Pearson = .9875632 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1754.591 ------------------------------------------------------------------------------ | EIM HP2probsoc | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- radhlw3 | .0156818 .0022898 6.85 0.000 .0111939 .0201697 _cons | -2.095692 .1691863 -12.39 0.000 -2.427291 -1.764093 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 630 . 631 . glm shjobw3 avgcumdosew3 if gender==1, fam(gaus) link(identity) Iteration 0: log likelihood = -1720.6013 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = 1464.409 Deviance = 494970.193 (1/df) Deviance = 1464.409 Pearson = 494970.193 (1/df) Pearson = 1464.409 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 10.13295 Log likelihood = -1720.601326 BIC = 493000 ------------------------------------------------------------------------------ | OIM shjobw3 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | -.2000973 .7785454 -0.26 0.797 -1.726018 1.325824 _cons | 41.22913 2.281923 18.07 0.000 36.75664 45.70162 ------------------------------------------------------------------------------ 632 . glm HP2probsoc shjobw3 if gender==1,fam(bin) irls link(probit) scale(dev) Iteration 1: deviance = 249.6649 Iteration 2: deviance = 248.8792 Iteration 3: deviance = 248.8773 Iteration 4: deviance = 248.8773 Generalized linear models No. of obs = 340 Optimization : MQL Fisher scoring Residual df = 338 (IRLS EIM) Scale parameter = 1 Deviance = 248.8773343 (1/df) Deviance = .7363235 Pearson = 340.8400768 (1/df) Pearson = 1.008403 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1721.306 ------------------------------------------------------------------------------ | EIM HP2probsoc | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- shjobw3 | .0026922 .0019572 1.38 0.169 -.0011439 .0065284 _cons | -1.288564 .1154816 -11.16 0.000 -1.514904 -1.062225 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 633 . 634 . // shjobw3Xd3 is almost significant but not quite 635 . glm radhlw3 shjobw3 avgcumdosew3 if gender==1, fam(gaus) link(identity) Iteration 0: log likelihood = -1694.063 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 337 Scale parameter = 1256.471 Deviance = 423430.6999 (1/df) Deviance = 1256.471 Pearson = 423430.6999 (1/df) Pearson = 1256.471 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 9.982724 Log likelihood = -1694.063021 BIC = 421466.3 ------------------------------------------------------------------------------ | OIM radhlw3 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- shjobw3 | .0752798 .0503833 1.49 0.135 -.0234697 .1740293 avgcumdosew3 | .9757125 .7212261 1.35 0.176 -.4378647 2.38929 _cons | 43.09623 2.963577 14.54 0.000 37.28772 48.90473 ------------------------------------------------------------------------------ 636 . glm HP2probsoc shjobw3 avgcumdosew3 shjobw3Xd3 if gender==1,fam(bin) /// > irls scale(dev) link(probit) Iteration 1: deviance = 244.6055 Iteration 2: deviance = 243.0617 Iteration 3: deviance = 241.3069 Iteration 4: deviance = 240.868 Iteration 5: deviance = 240.8657 Iteration 6: deviance = 240.8656 Iteration 7: deviance = 240.8656 Iteration 8: deviance = 240.8656 Generalized linear models No. of obs = 340 Optimization : MQL Fisher scoring Residual df = 336 (IRLS EIM) Scale parameter = 1 Deviance = 240.8656032 (1/df) Deviance = .7168619 Pearson = 340.9255101 (1/df) Pearson = 1.014659 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1717.66 ------------------------------------------------------------------------------ | EIM HP2probsoc | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- shjobw3 | -.0045194 .0035953 -1.26 0.209 -.0115661 .0025273 avgcumdosew3 | -.0918458 .0746098 -1.23 0.218 -.2380783 .0543867 shjobw3Xd3 | .0066355 .002922 2.27 0.023 .0009086 .0123624 _cons | -1.180909 .1352851 -8.73 0.000 -1.446063 -.9157549 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 637 . 638 . scalar ProbsocMedMw3 = "age" 639 . 640 . * female mediator tests: age radhlw3 bf4 641 . 642 . // age is a female mediator 643 . glm age avgcumdosew3 if gender==2, fam(gaus) link(identity) Iteration 0: log likelihood = -1408.064 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = 137.7687 Deviance = 49734.51399 (1/df) Deviance = 137.7687 Pearson = 49734.51399 (1/df) Pearson = 137.7687 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 7.768948 Log likelihood = -1408.06405 BIC = 47606.63 ------------------------------------------------------------------------------ | OIM age | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | 1.058366 .3512614 3.01 0.003 .3699069 1.746826 _cons | 48.94293 .7468173 65.54 0.000 47.47919 50.40666 ------------------------------------------------------------------------------ 644 . glm HP2probsoc age if gender==2, fam(bin) irls scale(dev) link(probit) Iteration 1: deviance = 289.3253 Iteration 2: deviance = 280.9528 Iteration 3: deviance = 280.5176 Iteration 4: deviance = 280.5162 Iteration 5: deviance = 280.5162 Generalized linear models No. of obs = 363 Optimization : MQL Fisher scoring Residual df = 361 (IRLS EIM) Scale parameter = 1 Deviance = 280.5161869 (1/df) Deviance = .7770531 Pearson = 406.2926804 (1/df) Pearson = 1.125464 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1847.363 ------------------------------------------------------------------------------ | EIM HP2probsoc | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0683554 .007474 9.15 0.000 .0537067 .083004 _cons | -4.505136 .424587 -10.61 0.000 -5.337311 -3.672961 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 645 . 646 . // radhlw3 is a female mediator 647 . glm radhlw3 avgcumdosew3 if gender==2, fam(gaus) link(identity) Iteration 0: log likelihood = -1798.7074 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = 1185.454 Deviance = 427948.9522 (1/df) Deviance = 1185.454 Pearson = 427948.9522 (1/df) Pearson = 1185.454 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 9.921253 Log likelihood = -1798.707367 BIC = 425821.1 ------------------------------------------------------------------------------ | OIM radhlw3 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | 2.751602 1.03038 2.67 0.008 .7320943 4.77111 _cons | 57.70689 2.190692 26.34 0.000 53.41321 62.00057 ------------------------------------------------------------------------------ 648 . glm HP2probsoc radhlw3 if gender==2,fam(bin) irls scale(dev) link(probit) Iteration 1: deviance = 332.0999 Iteration 2: deviance = 329.376 Iteration 3: deviance = 329.3467 Iteration 4: deviance = 329.3467 Iteration 5: deviance = 329.3467 Generalized linear models No. of obs = 363 Optimization : MQL Fisher scoring Residual df = 361 (IRLS EIM) Scale parameter = 1 Deviance = 329.3467003 (1/df) Deviance = .9123177 Pearson = 374.561784 (1/df) Pearson = 1.037567 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1798.533 ------------------------------------------------------------------------------ | EIM HP2probsoc | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- radhlw3 | .0145154 .0024198 6.00 0.000 .0097727 .0192582 _cons | -1.818717 .1912579 -9.51 0.000 -2.193576 -1.443859 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 649 . 650 . 651 . // bf4 is a mediator 652 . glm bf4 avgcumdosew3 if gender==2, fam(gaus) link(identity) Iteration 0: log likelihood = -1109.6569 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = 26.6146 Deviance = 9607.869105 (1/df) Deviance = 26.6146 Pearson = 9607.869105 (1/df) Pearson = 26.6146 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 6.124831 Log likelihood = -1109.656873 BIC = 7479.99 ------------------------------------------------------------------------------ | OIM bf4 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | -.4386292 .1543885 -2.84 0.004 -.7412252 -.1360333 _cons | 11.01475 .3282456 33.56 0.000 10.3714 11.6581 ------------------------------------------------------------------------------ 653 . glm HP2probsoc bf4 if gender==2,fam(bin) irls scale(dev) link(probit) Iteration 1: deviance = 295.3213 Iteration 2: deviance = 289.8751 Iteration 3: deviance = 289.6607 Iteration 4: deviance = 289.6591 Iteration 5: deviance = 289.6591 Iteration 6: deviance = 289.6591 Generalized linear models No. of obs = 363 Optimization : MQL Fisher scoring Residual df = 361 (IRLS EIM) Scale parameter = 1 Deviance = 289.6591069 (1/df) Deviance = .8023798 Pearson = 306.7680355 (1/df) Pearson = .849773 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1838.22 ------------------------------------------------------------------------------ | EIM HP2probsoc | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- bf4 | -.1364145 .0148745 -9.17 0.000 -.165568 -.107261 _cons | .3956217 .1443369 2.74 0.006 .1127267 .6785167 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 654 . 655 . glm shjobw3 avgcumdosew3 if gender==2, fam(gaus) link(identity) Iteration 0: log likelihood = -1782.2022 Generalized linear models No. of obs = 362 Optimization : ML Residual df = 360 Scale parameter = 1112.187 Deviance = 400387.4607 (1/df) Deviance = 1112.187 Pearson = 400387.4607 (1/df) Pearson = 1112.187 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 9.857471 Log likelihood = -1782.202176 BIC = 398266.5 ------------------------------------------------------------------------------ | OIM shjobw3 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | -1.527977 .9981622 -1.53 0.126 -3.484339 .4283847 _cons | 32.25021 2.12484 15.18 0.000 28.0856 36.41482 ------------------------------------------------------------------------------ 656 . glm HP2probsoc shjobw3 avgcumdosew3 if gender==2,fam(bin) /// > irls scale(dev) link(probit) Iteration 1: deviance = 329.6578 Iteration 2: deviance = 328.2396 Iteration 3: deviance = 328.227 Iteration 4: deviance = 328.2269 Iteration 5: deviance = 328.2269 Generalized linear models No. of obs = 362 Optimization : MQL Fisher scoring Residual df = 359 (IRLS EIM) Scale parameter = 1 Deviance = 328.2269272 (1/df) Deviance = .9142811 Pearson = 364.4863603 (1/df) Pearson = 1.015282 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1786.873 ------------------------------------------------------------------------------ | EIM HP2probsoc | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- shjobw3 | -.0088534 .0025178 -3.52 0.000 -.0137883 -.0039185 avgcumdosew3 | .2194295 .054413 4.03 0.000 .112782 .3260771 _cons | -.8734121 .1155844 -7.56 0.000 -1.099953 -.6468708 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 657 . 658 . scalar ProbsocMedFw3 = "age radhlw3 bf4" 659 . 660 . title4 "summary matrix for dose Hp2probsoc impact in wave 3" ------------------------------------------------------------------------------- summary matrix for dose Hp2probsoc impact in wave 3 ------------------------------------------------------------------------------- 661 . * male hp2spM w3 mediators: age 662 . * dose is not significant main effect for males 663 . * female hp2spF w3 mediators: age radhlw3 bf4 664 . * dose is not sig main effect for males 665 . 666 . scalar SigDoseProbsocMw3 = "no" 667 . 668 . matrix define HP2spMw3 = J(1,8, 0) 669 . matrix define HP2spFw3 = J(1,8, 0) 670 . matrix colnames HP2spMw3= hypnum ptnum wave gender medsig numMAsig numModsig > numMed 671 . matrix colnames HP2spFw3= hypnum ptnum wave gender medsig numMAsig numModsig > numMed 672 . matrix define HP2spFw3= (1, 2, 3, 2, 1, 5, 5, 3 ) 673 . matrix define HP2spMw3= (1, 2, 3, 1, 0, 2, 0, 1 ) 674 . matrix rowname HP2spMw3 = HP2spMw3 675 . matrix rowname HP2spFw3 = HP2spFw3 676 . matlist HP2spMw3 | c1 c2 c3 c4 c5 c6 > -------------+----------------------------------------------------------------- - HP2spMw3 | 1 2 3 1 0 2 > | c7 c8 -------------+---------------------- HP2spMw3 | 0 1 677 . matlist HP2spFw3 | c1 c2 c3 c4 c5 c6 > -------------+----------------------------------------------------------------- - HP2spFw3 | 1 2 3 2 1 5 > | c7 c8 -------------+---------------------- HP2spFw3 | 5 3 678 . matrix define H1pt2w3 = ( HP2wkMw3 \ HP2wkFw3 \ HP2hmcrMw3 \ HP2hmcrF > w3 \ HP2spMw3 \ HP2spFw3 ) 679 . 680 . matlist H1pt2w3 | c1 c2 c3 c4 c5 c6 > -------------+----------------------------------------------------------------- - r1 | 1 2 3 1 0 4 > r1 | 1 2 3 2 0 1 > r1 | 1 2 3 1 0 4 > r1 | 1 2 3 2 0 2 > HP2spMw3 | 1 2 3 1 0 2 > HP2spFw3 | 1 2 3 2 1 5 > | c7 c8 -------------+---------------------- r1 | 0 4 r1 | 0 6 r1 | 0 2 r1 | 0 2 HP2spMw3 | 0 1 HP2spFw3 | 5 3 681 . matrix colnames H1pt2w3 = hypnum ptnum wave gender medsig numMAsig numMo > dsig numMed 682 . matrix rownames H1pt2w3 = HP2wkMw3 HP2wkFw3 HP2hmcrMw3 HP2hmcrFw3 HP2so > cprbMw3 HP2socprbFw3 683 . matlist H1pt2w3 | hypnum ptnum wave gender medsig numMAsig > -------------+----------------------------------------------------------------- - HP2wkMw3 | 1 2 3 1 0 4 > HP2wkFw3 | 1 2 3 2 0 1 > HP2hmcrMw3 | 1 2 3 1 0 4 > HP2hmcrFw3 | 1 2 3 2 0 2 > HP2socprbMw3 | 1 2 3 1 0 2 > HP2socprbFw3 | 1 2 3 2 1 5 > | numModsig numMed -------------+---------------------- HP2wkMw3 | 0 4 HP2wkFw3 | 0 6 HP2hmcrMw3 | 0 2 HP2hmcrFw3 | 0 2 HP2socprbMw3 | 0 1 HP2socprbFw3 | 5 3 684 . 685 . 686 . *xx significant dose effect for females 687 . scalar ProbsocModFw3 = "none" 688 . *xx no female moderators for Dose Social problem impact relationship 689 . scalar list ProbsocMedFw3 = age radhlw3 bf4 VactnMedFw3 = age illw3 radhlw3 VactnMedMw3 = age illw3 VacatnModFw3 = none MainEffVactnFw3 = age radhlw3 deaw3 SigDoseVactnFw3 = no vactnModMw3 = none MainEffVactnMw3 = age bf7m radhlw3 SigDoseVactnMw3 = no sxLifeMedFw3 = age bf4 bf4m sxLifeMedMw3 = age illw3 InthbModFw3 = none MainEffInthbFw3 = age radhlw3 bf4 SigdoseInthbFw3 = no InthbMw3 = none MainEffInthbMw3 = age radhlw3 shfamw3 SigDoseInthbMw3 = no sxlifeMedFw3 = age illw3 radhlw3 bf4 bf4m sxlifeMedMw3 = age illw3 sxlifeModFw3 = none MainEffsxlifeFw3 = age radhlw3 bf4 bf4m shrelaw3 shfamw3 SigDoseSxlifeFw3 = no sxlifeModMw3 = none SigDosesxlifeMw3 = no MainEffsxlifeMw3 = age bf4 illw3 radhlw3 PrbfmhmMedFw3 = age bf4 PrbfmhmMedMw3 = age PrbfmhmModFw3 = none MainEffPrbfmhmFw3 = age bf4 bf40 SigDosePrbfmhmFw3 = no PrbfmhmModw3 = none SigDosePrbfmhmMw3 = no SigDosePrbfhmMw3 = no MainEffPrbfhmMw3 = bf1 bf4 dvcew3 bf7m ProbsocMedMw3 = age ProbsocModFw3 = none MainEffProbSocFw3 = age radhlw3 illw3 Shrelaw3 avgcumodsew3 SigDoseProbsocFw3 = yes ProbSocModMw3 = none SigDoseProbsocMw3 = no MainEffPrbsocMw3 = age radhlw3 shjobw3 hmcareMedFw3 = age illw3 hmcareMedMw3 = age illw3 hmcareModFw3 = none SigdoseHmcareFw3 = no hmcareModMw3 = none MainEffhmcareMw3 = none SigDoseHmcareMw3 = no wkMedFw3 = radhlw3 age bf40 bf4m bf1 wkMedMw3 = bf8 age illw3 ageXillw3 wkModFw3 = none wkModMw3 = none MainEffwkFw3 = age MainEffwkMw3 = workM: age bf8 illw3 shjobw3 SigDoseWKMw3 = no SigDoseWkFw3 = no medsigFw2 = 1 wkMedMw2 = bf8 age illw2 VactnMedFw2 = age illw2 radhlw2 VactnMedMw2 = age illw2 VacatnModFw2 = none MainEffVactnFw2 = age radhlw2 deaw2 SigDoseVactnFw2 = no vactnModMw2 = none MainEffVactnMw2 = age bf7m radhlw2 SigDoseVactnMw2 = no sxLifeMedFw2 = age bf4 bf4m sxLifeMedMw2 = age illw2 InthbModFw2 = none MainEffInthbFw2 = age radhlw2 bf4 SigdoseInthbFw2 = no InthbMw2 = none MainEffInthbMw2 = age radhlw2 shfamw2 SigDoseInthbMw2 = no sxlifeMedFw2 = age illw2 radhlw2 bf4 bf4m sxlifeMedMw2 = age illw2 sxlifeModFw2 = none MainEffsxlifeFw2 = age radhlw2 bf4 bf4m shrelaw2 shfamw2 SigDoseSxlifeFw2 = no sxlifeModMw2 = none SigDosesxlifeMw2 = no MainEffsxlifeMw2 = age bf4 illw2 radhlw2 PrbfmhmMedFw2 = age bf4 PrbfmhmMedMw2 = age PrbfmhmModFw2 = none MainEffPrbfmhmFw2 = age bf4 bf40 SigDosePrbfmhmFw2 = no PrbfmhmModw2 = none SigDosePrbfmhmMw2 = no SigDosePrbfhmMw2 = no MainEffPrbfhmMw2 = bf1 bf4 dvcew2 bf7m ProbsocMedFw2 = age radhlw2 ProbsocMedMw2 = age ProbsocModFw2 = none MainEffProbSocFw2 = age radhlw2 illw2 Shrelaw2 avgcumodsew2 SigDoseProbsocFw2 = yes ProbSocModMw2 = none SigDoseProbsocMw2 = no MainEffPrbsocMw2 = age radhlw2 shjobw2 hmcareMedFw2 = age illw2 hmcareMedMw2 = age illw2 hmcareModFw2 = none SigDoseWKFw2 = 0 SigdoseHmcareFw2 = no hmcareModMw2 = none MainEffhmcareMw2 = none SigDoseHmcareMw2 = no wkMedFw2 = radhlw2 age bf40 bf4m bf1 wkModFw2 = none wkModMw2 = none MainEffwkFw2 = age MainEffwkMw2 = workM: age bf8 illw2 shjobw2 SigDoseWKMw2 = no SigDoseWkFw2 = no hmcrMedFw1 = age icdxcnt shjobw1 bf4 BSIsoma WHPpain WHPsleep WHPel hmcrMedMw1 = age MainEffhmcrFw1 = illw1 age SigDosehmcrFw1 = no hmcrModMw1 = none MainEffhmcrMw1 = age shjobw1 SigDosehmcrMw1 = no wkMedFw1 = age b4 MainEffwkFw1 = age MainEffwkMw1 = age wkMedMw1 = bf40 WkMedMw1 = none WkModFw1 = none WKModMw1 = none SigDoseWkMw1 = no SigDoseWkFw1 = no SigDoseFw1 = no wkModFw1 = none wkModMw1 = none medsigFw1 = 1 prbsocnumMAsig = 8 690 . 691 . *----------- Chunk 5 Dose => Problems with the Family at home Impact 692 . 693 . 694 . 695 . title "4. Wave 3 part2 hypothesis 1 Pt2 Probs with Fam at home" ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** 4. Wave 3 part2 hypothesis 1 Pt2 Probs with Fam at home ***** ***** ***** ***** ***** ***** 1 Jul 2012 20:37:53 ***** ******************************************************************************* ******************************************************************************* 696 . forvalues j=3/3 { 2. set more off 3. 697 . des age educ1-educ7 marrw`j'1-marrw`j'6 inc1w`j'-inc4w`j' /// > bf1 bf4 bf9 bf11 bf4m bf15m bf30 bf40 4. 698 . foreach var in HP2pbfhm { 5. forvalues k=1/2 { 6. local w3bf bf1 bf4 bf2 bf4m bf5m bf7m bf8 bf15m bf17 bf20 bf22 bf29 bf30 b > f40 7. 699 . di as input "Full main model for `var' for wave= `j' " 8. di _skip(4) 9. di as input "chunk 5 H1 test:Gender= `k' model Wave = `j' for `e(depvar > )' " 10. di _skip(4) 11. title "Full Nottingham Part 2 subscale models for male and then females" 12. 700 . xi: logistic `var' age i.educ occ1w`j'-occ8w`j' /// > marrw`j'1- marrw`j'3 marrw`j'5-marrw`j'6 inc1w`j'-inc4w`j' // > / > radhlw`j' havmil avgcumdosew`j' `w`j'bf' /// > deaw`j' dvcew`j' sepaw`j' accdw`j' movew`j' /// > illw`j' shfamw`j' shhlw`j' shjobw`j' shrelaw`j' suprtw`j' suc > hrw`j' /// > havmilsq if gender==`k', coef nolog difficult iterate(50) 13. estat class 14. estat gof 15. fitstat 16. } 17. } 18. } storage display value variable name type format label variable label ------------------------------------------------------------------------------- age double %8.0g * Respondent's age educ1 byte %8.0g educ==1. did not graduate high school educ2 byte %8.0g educ==2. graduated high school educ3 byte %8.0g educ==3. technical degree educ4 byte %8.0g educ==4. did not finish college/bachelor's educ5 byte %8.0g educ==5. graduated college/bachelor's educ6 byte %8.0g educ==6. finished specialist/master's degree educ7 byte %8.0g educ==7. doctor of science/phd marrw31 byte %8.0g marrw3==1. single marrw32 byte %8.0g marrw3==2. cohabitating marrw33 byte %8.0g marrw3==3. married marrw34 byte %8.0g marrw3==4. separated marrw35 byte %8.0g marrw3==5. divorced marrw36 byte %8.0g marrw3==6. widowed inc1w3 double %15.0g LABJ Income is not sufficient for basic neccessities NOW inc2w3 double %15.0g LABJ Income is just sufficient for basic neccessities NOW inc3w3 double %15.0g LABJ Income is sufficient for basics plus extra purchases/savings NOW inc4w3 double %15.0g LABJ Income allows to comfortably afford luxury items NOW bf1 float %9.0g bf1 = max(0, kzchorn - 40) bf4 float %9.0g bf4 = max(0, 24 - BSIsoma) bf9 float %9.0g bf9= max(0, 30 - shhlw1) bf11 float %9.0g bf11= max(0, 20 - sufamw1) bf4m float %9.0g bf4m = max(0, 32 - BSIsoma) bf15m float %9.0g bf15m= max(0, 1 - icdxcnt) * bf2 bf30 float %9.0g bf30 = max(0, neiw1 - 85) * bf20 bf40 float %9.0g bf40 = max(0, icdxcnt - 1.01635E-007) Full main model for HP2pbfhm for wave= 3 chunk 5 H1 test:Gender= 1 model Wave = 3 for HP2probsoc ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Full Nottingham Part 2 subscale models for male and then females ***** ***** ***** ***** ***** ***** 1 Jul 2012 20:37:53 ***** ******************************************************************************* ******************************************************************************* i.educ _Ieduc_1-8 (naturally coded; _Ieduc_1 omitted) note: _Ieduc_2 != 0 predicts failure perfectly _Ieduc_2 dropped and 10 obs not used note: _Ieduc_4 != 0 predicts failure perfectly _Ieduc_4 dropped and 14 obs not used note: _Ieduc_7 != 0 predicts failure perfectly _Ieduc_7 dropped and 4 obs not used note: _Ieduc_8 != 0 predicts failure perfectly _Ieduc_8 dropped and 2 obs not used note: occ5w3 != 0 predicts failure perfectly occ5w3 dropped and 13 obs not used note: occ6w3 != 0 predicts failure perfectly occ6w3 dropped and 4 obs not used note: bf15m != 0 predicts failure perfectly bf15m dropped and 17 obs not used note: bf29 != 0 predicts failure perfectly bf29 dropped and 6 obs not used note: movew3 != 0 predicts failure perfectly movew3 dropped and 22 obs not used note: _Ieduc_6 omitted because of collinearity note: occ8w3 omitted because of collinearity note: marrw36 omitted because of collinearity note: bf17 omitted because of collinearity Logistic regression Number of obs = 248 LR chi2(42) = 61.10 Prob > chi2 = 0.0286 Log likelihood = -43.736999 Pseudo R2 = 0.4112 ------------------------------------------------------------------------------ HP2pbfhm | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0762859 .0508028 1.50 0.133 -.0232857 .1758575 _Ieduc_2 | 0 (omitted) _Ieduc_3 | -.1477637 .8109786 -0.18 0.855 -1.737253 1.441725 _Ieduc_4 | 0 (omitted) _Ieduc_5 | -.7596947 1.090598 -0.70 0.486 -2.897227 1.377837 _Ieduc_6 | 0 (omitted) _Ieduc_7 | 0 (omitted) _Ieduc_8 | 0 (omitted) occ1w3 | -10.90364 2018.344 -0.01 0.996 -3966.785 3944.977 occ2w3 | -10.89538 2018.344 -0.01 0.996 -3966.777 3944.986 occ3w3 | -9.963313 2018.344 -0.00 0.996 -3965.846 3945.919 occ4w3 | -10.3499 2018.344 -0.01 0.996 -3966.232 3945.532 occ5w3 | 0 (omitted) occ6w3 | 0 (omitted) occ7w3 | -10.56369 2018.344 -0.01 0.996 -3966.445 3945.318 occ8w3 | 0 (omitted) marrw31 | 1.938945 1.834088 1.06 0.290 -1.655802 5.533692 marrw32 | 2.869349 2.03424 1.41 0.158 -1.117687 6.856385 marrw33 | -2.070881 2.007923 -1.03 0.302 -6.006338 1.864576 marrw35 | 3.548252 2.186549 1.62 0.105 -.7373048 7.833809 marrw36 | 0 (omitted) inc1w3 | 12.37597 2018.344 0.01 0.995 -3943.505 3968.257 inc2w3 | 12.75723 2018.343 0.01 0.995 -3943.123 3968.637 inc3w3 | 11.01982 2018.344 0.01 0.996 -3944.861 3966.9 inc4w3 | 11.952 2018.345 0.01 0.995 -3943.931 3967.835 radhlw3 | .032589 .0182947 1.78 0.075 -.0032679 .0684459 havmil | .0129536 .013774 0.94 0.347 -.0140429 .0399501 avgcumdosew3 | -.3791136 .3273992 -1.16 0.247 -1.020804 .2625771 bf1 | -.1029605 .0825755 -1.25 0.212 -.2648056 .0588846 bf4 | -.1906164 .3464978 -0.55 0.582 -.8697396 .4885069 bf2 | .0004772 .0003548 1.35 0.179 -.0002181 .0011725 bf4m | .0772469 .2972932 0.26 0.795 -.505437 .6599308 bf5m | -.0019382 .0047879 -0.40 0.686 -.0113224 .007446 bf7m | .0012129 .001013 1.20 0.231 -.0007725 .0031983 bf8 | -3.27e-06 .0000957 -0.03 0.973 -.0001909 .0001843 bf15m | 0 (omitted) bf17 | 0 (omitted) bf20 | .0430617 .0653802 0.66 0.510 -.0850811 .1712045 bf22 | -4.46e-06 .0002995 -0.01 0.988 -.0005915 .0005826 bf29 | 0 (omitted) bf30 | .000126 .0007197 0.18 0.861 -.0012845 .0015365 bf40 | .071783 .4795976 0.15 0.881 -.8682111 1.011777 deaw3 | .3272315 .4280065 0.76 0.445 -.5116458 1.166109 dvcew3 | 1.631036 1.568401 1.04 0.298 -1.442973 4.705045 sepaw3 | .2595898 1.605075 0.16 0.872 -2.886299 3.405479 accdw3 | -.9114258 2.076173 -0.44 0.661 -4.980649 3.157798 movew3 | 0 (omitted) illw3 | -.5480408 .5150453 -1.06 0.287 -1.557511 .4614294 shfamw3 | .0143257 .0164517 0.87 0.384 -.017919 .0465703 shhlw3 | -.0109085 .0129224 -0.84 0.399 -.0362359 .014419 shjobw3 | -.0129256 .0143995 -0.90 0.369 -.0411481 .0152969 shrelaw3 | -.0047884 .012683 -0.38 0.706 -.0296466 .0200697 suprtw3 | .025454 .0177967 1.43 0.153 -.0094269 .0603349 suchrw3 | .0037567 .0120299 0.31 0.755 -.0198214 .0273349 havmilsq | -.0000259 .0000249 -1.04 0.299 -.0000746 .0000229 _cons | -12.84498 6.147159 -2.09 0.037 -24.89319 -.79677 ------------------------------------------------------------------------------ Note: 5 failures and 0 successes completely determined. Logistic model for HP2pbfhm -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 9 4 | 13 - | 13 222 | 235 -----------+--------------------------+----------- Total | 22 226 | 248 Classified + if predicted Pr(D) >= .5 True D defined as HP2pbfhm != 0 -------------------------------------------------- Sensitivity Pr( +| D) 40.91% Specificity Pr( -|~D) 98.23% Positive predictive value Pr( D| +) 69.23% Negative predictive value Pr(~D| -) 94.47% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 1.77% False - rate for true D Pr( -| D) 59.09% False + rate for classified + Pr(~D| +) 30.77% False - rate for classified - Pr( D| -) 5.53% -------------------------------------------------- Correctly classified 93.15% -------------------------------------------------- Logistic model for HP2pbfhm, goodness-of-fit test number of observations = 248 number of covariate patterns = 248 Pearson chi2(205) = 151.48 Prob > chi2 = 0.9980 Measures of Fit for logistic of HP2pbfhm Log-Lik Intercept Only: -74.286 Log-Lik Full Model: -43.737 D(192): 87.474 LR(42): 61.099 Prob > LR: 0.029 McFadden's R2: 0.411 McFadden's Adj R2: -0.343 Maximum Likelihood R2: 0.218 Cragg & Uhler's R2: 0.485 McKelvey and Zavoina's R2: 0.816 Efron's R2: 0.329 Variance of y*: 17.878 Variance of error: 3.290 Count R2: 0.931 Adj Count R2: 0.227 AIC: 0.804 AIC*n: 199.474 BIC: -971.104 BIC': 170.465 Full main model for HP2pbfhm for wave= 3 chunk 5 H1 test:Gender= 2 model Wave = 3 for HP2pbfhm ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Full Nottingham Part 2 subscale models for male and then females ***** ***** ***** ***** ***** ***** 1 Jul 2012 20:37:54 ***** ******************************************************************************* ******************************************************************************* i.educ _Ieduc_1-8 (naturally coded; _Ieduc_1 omitted) note: occ2w3 != 0 predicts failure perfectly occ2w3 dropped and 37 obs not used note: occ4w3 != 0 predicts failure perfectly occ4w3 dropped and 8 obs not used note: occ6w3 != 0 predicts failure perfectly occ6w3 dropped and 4 obs not used note: occ8w3 != 0 predicts failure perfectly occ8w3 dropped and 1 obs not used note: marrw32 != 0 predicts failure perfectly marrw32 dropped and 7 obs not used note: inc4w3 != 0 predicts failure perfectly inc4w3 dropped and 8 obs not used note: bf15m != 0 predicts failure perfectly bf15m dropped and 11 obs not used note: movew3 != 0 predicts failure perfectly movew3 dropped and 9 obs not used note: _Ieduc_8 omitted because of collinearity note: bf17 omitted because of collinearity Logistic regression Number of obs = 277 LR chi2(45) = 88.17 Prob > chi2 = 0.0001 Log likelihood = -80.45257 Pseudo R2 = 0.3540 ------------------------------------------------------------------------------ HP2pbfhm | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0605232 .0301499 2.01 0.045 .0014305 .1196159 _Ieduc_2 | 14.33097 3050.48 0.00 0.996 -5964.5 5993.162 _Ieduc_3 | 14.57814 3050.48 0.00 0.996 -5964.253 5993.409 _Ieduc_4 | 14.71229 3050.48 0.00 0.996 -5964.118 5993.543 _Ieduc_5 | 14.46503 3050.48 0.00 0.996 -5964.366 5993.296 _Ieduc_6 | 14.13284 3050.48 0.00 0.996 -5964.698 5992.963 _Ieduc_7 | 16.45371 3050.482 0.01 0.996 -5962.381 5995.289 _Ieduc_8 | 0 (omitted) occ1w3 | -.9142061 3.466224 -0.26 0.792 -7.70788 5.879468 occ2w3 | 0 (omitted) occ3w3 | -.2867411 3.495557 -0.08 0.935 -7.137908 6.564426 occ4w3 | 0 (omitted) occ5w3 | 2.578209 4.53518 0.57 0.570 -6.310581 11.467 occ6w3 | 0 (omitted) occ7w3 | -.5244179 3.46458 -0.15 0.880 -7.31487 6.266034 occ8w3 | 0 (omitted) marrw31 | 13.57521 900.684 0.02 0.988 -1751.733 1778.884 marrw32 | 0 (omitted) marrw33 | 15.5368 900.6835 0.02 0.986 -1749.77 1780.844 marrw35 | 15.43053 900.6834 0.02 0.986 -1749.877 1780.738 marrw36 | 15.00571 900.6833 0.02 0.987 -1750.301 1780.313 inc1w3 | 2.006505 3.516446 0.57 0.568 -4.885601 8.898612 inc2w3 | 2.111761 3.483985 0.61 0.544 -4.716724 8.940246 inc3w3 | 1.911831 3.463507 0.55 0.581 -4.876519 8.70018 inc4w3 | 0 (omitted) radhlw3 | .0113673 .0123354 0.92 0.357 -.0128096 .0355442 havmil | -.0010166 .0142076 -0.07 0.943 -.0288629 .0268297 avgcumdosew3 | -.0338506 .1440343 -0.24 0.814 -.3161526 .2484513 bf1 | -.0040962 .0453653 -0.09 0.928 -.0930105 .0848181 bf4 | -.3790747 .2483688 -1.53 0.127 -.8658686 .1077192 bf2 | .0000525 .0001469 0.36 0.721 -.0002354 .0003404 bf4m | .1263528 .2275811 0.56 0.579 -.3196979 .5724036 bf5m | -.0049342 .0041169 -1.20 0.231 -.0130031 .0031348 bf7m | -.0004133 .0008454 -0.49 0.625 -.0020703 .0012437 bf8 | .0001156 .0000755 1.53 0.125 -.0000323 .0002635 bf15m | 0 (omitted) bf17 | 0 (omitted) bf20 | -.0078983 .0366468 -0.22 0.829 -.0797248 .0639282 bf22 | .000158 .0001863 0.85 0.396 -.0002071 .0005231 bf29 | 9.34e-06 .0000425 0.22 0.826 -.000074 .0000927 bf30 | -.0000869 .0004483 -0.19 0.846 -.0009655 .0007917 bf40 | -.2779981 .1983152 -1.40 0.161 -.6666887 .1106924 deaw3 | -.0223131 .2253092 -0.10 0.921 -.4639109 .4192848 dvcew3 | 1.571998 1.037736 1.51 0.130 -.4619271 3.605923 sepaw3 | -1.894764 1.527486 -1.24 0.215 -4.888582 1.099055 accdw3 | -.2729555 .6926052 -0.39 0.694 -1.630437 1.084526 movew3 | 0 (omitted) illw3 | -.1949663 .2468671 -0.79 0.430 -.6788169 .2888842 shfamw3 | -.0082258 .0094908 -0.87 0.386 -.0268274 .0103758 shhlw3 | .0062899 .0080613 0.78 0.435 -.00951 .0220898 shjobw3 | -.0009012 .0093159 -0.10 0.923 -.0191601 .0173576 shrelaw3 | -.0126452 .0092607 -1.37 0.172 -.0307958 .0055054 suprtw3 | -.004099 .0105306 -0.39 0.697 -.0247385 .0165405 suchrw3 | -.0078922 .0065901 -1.20 0.231 -.0208085 .0050241 havmilsq | -4.43e-06 .000039 -0.11 0.909 -.0000808 .000072 _cons | -32.88256 3180.671 -0.01 0.992 -6266.884 6201.119 ------------------------------------------------------------------------------ Note: 5 failures and 0 successes completely determined. Logistic model for HP2pbfhm -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 22 9 | 31 - | 24 222 | 246 -----------+--------------------------+----------- Total | 46 231 | 277 Classified + if predicted Pr(D) >= .5 True D defined as HP2pbfhm != 0 -------------------------------------------------- Sensitivity Pr( +| D) 47.83% Specificity Pr( -|~D) 96.10% Positive predictive value Pr( D| +) 70.97% Negative predictive value Pr(~D| -) 90.24% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 3.90% False - rate for true D Pr( -| D) 52.17% False + rate for classified + Pr(~D| +) 29.03% False - rate for classified - Pr( D| -) 9.76% -------------------------------------------------- Correctly classified 88.09% -------------------------------------------------- Logistic model for HP2pbfhm, goodness-of-fit test number of observations = 277 number of covariate patterns = 277 Pearson chi2(231) = 439.38 Prob > chi2 = 0.0000 Measures of Fit for logistic of HP2pbfhm Log-Lik Intercept Only: -124.537 Log-Lik Full Model: -80.453 D(221): 160.905 LR(45): 88.169 Prob > LR: 0.000 McFadden's R2: 0.354 McFadden's Adj R2: -0.096 Maximum Likelihood R2: 0.273 Cragg & Uhler's R2: 0.460 McKelvey and Zavoina's R2: 0.796 Efron's R2: 0.384 Variance of y*: 16.128 Variance of error: 3.290 Count R2: 0.881 Adj Count R2: 0.283 AIC: 0.985 AIC*n: 272.905 BIC: -1082.003 BIC': 164.912 701 . 702 . 703 . title "Partly Trimmed male wave 3 Dose => Problems with Family at home model > s" ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** *****Partly Trimmed male wave 3 Dose => Problems with Family at home models*** > ** ***** ***** ***** ***** ***** 1 Jul 2012 20:37:56 ***** ******************************************************************************* ******************************************************************************* 704 . local w3bf bf1 bf4 bf2 bf4m bf5m bf7m bf8 bf15m bf17 bf20 bf22 bf29 bf30 bf40 705 . logit HP2pbfhm age sepaw3 dvcew3 radhlw3 avgcumdosew3 suprtw3 /// > havmilsq illw3 `w3bf' if gender==1, iterate(50) note: bf15m != 0 predicts failure perfectly bf15m dropped and 21 obs not used note: bf29 != 0 predicts failure perfectly bf29 dropped and 8 obs not used note: bf17 omitted because of collinearity Iteration 0: log likelihood = -79.475349 Iteration 1: log likelihood = -67.02422 Iteration 2: log likelihood = -60.135828 Iteration 3: log likelihood = -59.852788 Iteration 4: log likelihood = -59.850816 Iteration 5: log likelihood = -59.850815 Logistic regression Number of obs = 311 LR chi2(19) = 39.25 Prob > chi2 = 0.0041 Log likelihood = -59.850815 Pseudo R2 = 0.2469 ------------------------------------------------------------------------------ HP2pbfhm | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .043687 .0250852 1.74 0.082 -.0054791 .092853 sepaw3 | 1.382077 1.196445 1.16 0.248 -.9629124 3.727067 dvcew3 | 1.720325 1.049833 1.64 0.101 -.3373098 3.77796 radhlw3 | .0111639 .0118036 0.95 0.344 -.0119707 .0342986 avgcumdosew3 | -.0948486 .2407308 -0.39 0.694 -.5666722 .376975 suprtw3 | -.0049975 .0064124 -0.78 0.436 -.0175656 .0075705 havmilsq | -1.41e-06 6.40e-06 -0.22 0.826 -.000014 .0000111 illw3 | -.190415 .3387342 -0.56 0.574 -.8543217 .4734918 bf1 | -.0587243 .0691016 -0.85 0.395 -.194161 .0767123 bf4 | -.2551053 .2251582 -1.13 0.257 -.6964073 .1861967 bf2 | .0004205 .0002504 1.68 0.093 -.0000704 .0009113 bf4m | .0336013 .2032952 0.17 0.869 -.3648499 .4320525 bf5m | .0012898 .0029269 0.44 0.659 -.0044468 .0070264 bf7m | .0016168 .0007794 2.07 0.038 .0000891 .0031445 bf8 | -.0000436 .0000621 -0.70 0.483 -.0001653 .0000781 bf15m | 0 (omitted) bf17 | 0 (omitted) bf20 | .0203096 .0573578 0.35 0.723 -.0921097 .1327289 bf22 | -.0000858 .0002375 -0.36 0.718 -.0005514 .0003797 bf29 | 0 (omitted) bf30 | -.000487 .0004957 -0.98 0.326 -.0014586 .0004845 bf40 | -.0932224 .3574103 -0.26 0.794 -.7937336 .6072889 _cons | -4.855589 3.519856 -1.38 0.168 -11.75438 2.043202 ------------------------------------------------------------------------------ 706 . 707 . estat class Logistic model for HP2pbfhm -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 1 3 | 4 - | 21 286 | 307 -----------+--------------------------+----------- Total | 22 289 | 311 Classified + if predicted Pr(D) >= .5 True D defined as HP2pbfhm != 0 -------------------------------------------------- Sensitivity Pr( +| D) 4.55% Specificity Pr( -|~D) 98.96% Positive predictive value Pr( D| +) 25.00% Negative predictive value Pr(~D| -) 93.16% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 1.04% False - rate for true D Pr( -| D) 95.45% False + rate for classified + Pr(~D| +) 75.00% False - rate for classified - Pr( D| -) 6.84% -------------------------------------------------- Correctly classified 92.28% -------------------------------------------------- 708 . estat gof Logistic model for HP2pbfhm, goodness-of-fit test number of observations = 311 number of covariate patterns = 310 Pearson chi2(290) = 253.04 Prob > chi2 = 0.9426 709 . fitstat Measures of Fit for logit of HP2pbfhm Log-Lik Intercept Only: -79.475 Log-Lik Full Model: -59.851 D(288): 119.702 LR(19): 39.249 Prob > LR: 0.004 McFadden's R2: 0.247 McFadden's Adj R2: -0.042 Maximum Likelihood R2: 0.119 Cragg & Uhler's R2: 0.296 McKelvey and Zavoina's R2: 0.486 Efron's R2: 0.165 Variance of y*: 6.405 Variance of error: 3.290 Count R2: 0.923 Adj Count R2: -0.091 AIC: 0.533 AIC*n: 165.702 BIC: -1533.359 BIC': 69.807 710 . 711 . title "fully Trimmed male main effects wv 3" " Dose => Problems with Family a > t home models" ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** fully Trimmed male main effects wv 3 ***** ***** Dose => Problems with Family at home models ***** ***** ***** ***** ***** ***** 1 Jul 2012 20:37:58 ***** ******************************************************************************* ******************************************************************************* 712 . local w3bf bf1 bf4 bf2 bf4m bf5m bf7m bf8 bf15m bf17 bf20 bf22 bf29 bf30 bf40 713 . sw, pr(.1):logit HP2pbfhm age sepaw3 dvcew3 radhlw3 avgcumdosew3 suprtw3 /// > havmilsq illw3 `w3bf' if gender==1, iterate(50) note: bf15m dropped because of estimability note: bf17 dropped because of estimability note: bf29 dropped because of estimability note: o.bf15m dropped because of estimability note: o.bf17 dropped because of estimability note: o.bf29 dropped because of estimability note: 29 obs. dropped because of estimability begin with full model p = 0.8687 >= 0.1000 removing bf4m p = 0.8320 >= 0.1000 removing havmilsq p = 0.7873 >= 0.1000 removing bf40 p = 0.7202 >= 0.1000 removing bf20 p = 0.6874 >= 0.1000 removing avgcumdosew3 p = 0.6350 >= 0.1000 removing bf5m p = 0.5258 >= 0.1000 removing bf8 p = 0.4782 >= 0.1000 removing illw3 p = 0.4550 >= 0.1000 removing radhlw3 p = 0.4439 >= 0.1000 removing bf30 p = 0.3545 >= 0.1000 removing suprtw3 p = 0.2500 >= 0.1000 removing bf22 p = 0.3169 >= 0.1000 removing sepaw3 p = 0.1709 >= 0.1000 removing age Logistic regression Number of obs = 311 LR chi2(5) = 31.19 Prob > chi2 = 0.0000 Log likelihood = -63.878677 Pseudo R2 = 0.1962 ------------------------------------------------------------------------------ HP2pbfhm | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- bf1 | -.0373492 .0219622 -1.70 0.089 -.0803943 .0056959 bf4 | -.2457605 .0676591 -3.63 0.000 -.37837 -.1131511 dvcew3 | 2.001697 .80438 2.49 0.013 .4251407 3.578253 bf2 | .0003872 .000212 1.83 0.068 -.0000283 .0008027 bf7m | .0014478 .0004687 3.09 0.002 .0005292 .0023664 _cons | -1.533868 .7653632 -2.00 0.045 -3.033953 -.0337839 ------------------------------------------------------------------------------ 714 . 715 . estat class Logistic model for HP2pbfhm -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 0 0 | 0 - | 22 289 | 311 -----------+--------------------------+----------- Total | 22 289 | 311 Classified + if predicted Pr(D) >= .5 True D defined as HP2pbfhm != 0 -------------------------------------------------- Sensitivity Pr( +| D) 0.00% Specificity Pr( -|~D) 100.00% Positive predictive value Pr( D| +) .% Negative predictive value Pr(~D| -) 92.93% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 0.00% False - rate for true D Pr( -| D) 100.00% False + rate for classified + Pr(~D| +) .% False - rate for classified - Pr( D| -) 7.07% -------------------------------------------------- Correctly classified 92.93% -------------------------------------------------- 716 . estat gof Logistic model for HP2pbfhm, goodness-of-fit test number of observations = 311 number of covariate patterns = 263 Pearson chi2(257) = 376.88 Prob > chi2 = 0.0000 717 . fitstat Measures of Fit for logit of HP2pbfhm Log-Lik Intercept Only: -79.475 Log-Lik Full Model: -63.879 D(305): 127.757 LR(5): 31.193 Prob > LR: 0.000 McFadden's R2: 0.196 McFadden's Adj R2: 0.121 Maximum Likelihood R2: 0.095 Cragg & Uhler's R2: 0.238 McKelvey and Zavoina's R2: 0.411 Efron's R2: 0.128 Variance of y*: 5.587 Variance of error: 3.290 Count R2: 0.929 Adj Count R2: 0.000 AIC: 0.449 AIC*n: 139.757 BIC: -1622.879 BIC': -2.494 718 . 719 . scalar MainEffPrbfhmMw3 = "bf1 bf4 dvcew3 bf7m" 720 . scalar SigDosePrbfhmMw3 = "no" 721 . // construction of moderators for male model 722 . 723 . foreach var in bf1 bf4 dvcew3 bf2 bf7m { 2. cap gen `var'Xd3 = `var'*avgcumdosew3 3. } 724 . 725 . 726 . 727 . 728 . ***************************************************************************** > * 729 . *-------chunk 6 continued -testing moderators and none found for males 730 . local w3bf bf1 bf4 bf2 bf4m bf5m bf7m bf8 bf15m bf17 bf20 bf22 bf29 bf30 bf40 731 . 732 . 733 . title "fully Trimmed male main effects wv 3" /// > "Dose => Problems with Family at home models" ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** fully Trimmed male main effects wv 3 ***** ***** Dose => Problems with Family at home models ***** ***** ***** ***** ***** ***** 1 Jul 2012 20:38:20 ***** ******************************************************************************* ******************************************************************************* 734 . local w3bf bf1 bf4 bf2 bf4m bf5m bf7m bf8 bf15m bf17 bf20 bf22 bf29 bf30 bf40 735 . sw, pr(.1):logit HP2pbfhm age sepaw3 dvcew3 radhlw3 avgcumdosew3 suprtw3 /// > havmilsq illw3 `w3bf' bf1Xd3 bf4Xd3 bf2Xd3 bf7mXd3 dvcew3Xd3 if /// > gender==1, iterate(50) note: bf15m dropped because of estimability note: bf17 dropped because of estimability note: bf29 dropped because of estimability note: o.bf15m dropped because of estimability note: o.bf17 dropped because of estimability note: o.bf29 dropped because of estimability note: 29 obs. dropped because of estimability begin with full model p = 0.9832 >= 0.1000 removing bf2Xd3 p = 0.8995 >= 0.1000 removing bf4m p = 0.8784 >= 0.1000 removing havmilsq p = 0.8427 >= 0.1000 removing bf7mXd3 p = 0.8108 >= 0.1000 removing bf1Xd3 p = 0.7829 >= 0.1000 removing dvcew3Xd3 p = 0.7779 >= 0.1000 removing bf40 p = 0.6983 >= 0.1000 removing bf20 p = 0.6391 >= 0.1000 removing bf4Xd3 p = 0.6874 >= 0.1000 removing avgcumdosew3 p = 0.6350 >= 0.1000 removing bf5m p = 0.5258 >= 0.1000 removing bf8 p = 0.4782 >= 0.1000 removing illw3 p = 0.4550 >= 0.1000 removing radhlw3 p = 0.4439 >= 0.1000 removing bf30 p = 0.3545 >= 0.1000 removing suprtw3 p = 0.2500 >= 0.1000 removing bf22 p = 0.3169 >= 0.1000 removing sepaw3 p = 0.1709 >= 0.1000 removing age Logistic regression Number of obs = 311 LR chi2(5) = 31.19 Prob > chi2 = 0.0000 Log likelihood = -63.878677 Pseudo R2 = 0.1962 ------------------------------------------------------------------------------ HP2pbfhm | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- bf1 | -.0373492 .0219622 -1.70 0.089 -.0803943 .0056959 bf4 | -.2457605 .0676591 -3.63 0.000 -.37837 -.1131511 dvcew3 | 2.001697 .80438 2.49 0.013 .4251407 3.578253 bf2 | .0003872 .000212 1.83 0.068 -.0000283 .0008027 bf7m | .0014478 .0004687 3.09 0.002 .0005292 .0023664 _cons | -1.533868 .7653632 -2.00 0.045 -3.033953 -.0337839 ------------------------------------------------------------------------------ 736 . 737 . estat class Logistic model for HP2pbfhm -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 0 0 | 0 - | 22 289 | 311 -----------+--------------------------+----------- Total | 22 289 | 311 Classified + if predicted Pr(D) >= .5 True D defined as HP2pbfhm != 0 -------------------------------------------------- Sensitivity Pr( +| D) 0.00% Specificity Pr( -|~D) 100.00% Positive predictive value Pr( D| +) .% Negative predictive value Pr(~D| -) 92.93% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 0.00% False - rate for true D Pr( -| D) 100.00% False + rate for classified + Pr(~D| +) .% False - rate for classified - Pr( D| -) 7.07% -------------------------------------------------- Correctly classified 92.93% -------------------------------------------------- 738 . estat gof Logistic model for HP2pbfhm, goodness-of-fit test number of observations = 311 number of covariate patterns = 263 Pearson chi2(257) = 376.88 Prob > chi2 = 0.0000 739 . fitstat Measures of Fit for logit of HP2pbfhm Log-Lik Intercept Only: -79.475 Log-Lik Full Model: -63.879 D(305): 127.757 LR(5): 31.193 Prob > LR: 0.000 McFadden's R2: 0.196 McFadden's Adj R2: 0.121 Maximum Likelihood R2: 0.095 Cragg & Uhler's R2: 0.238 McKelvey and Zavoina's R2: 0.411 Efron's R2: 0.128 Variance of y*: 5.587 Variance of error: 3.290 Count R2: 0.929 Adj Count R2: 0.000 AIC: 0.449 AIC*n: 139.757 BIC: -1622.879 BIC': -2.494 740 . 741 . scalar SigDosePrbfmhmMw3 = "no" 742 . scalar PrbfmhmModw3 = "none" 743 . 744 . * 3 main effects signif no main effect for dose for males 745 . 746 . 747 . ***************************************************************************** > *** 748 . title4 "Chunk 6 continued -testing meditors for females" ------------------------------------------------------------------------------- Chunk 6 continued -testing meditors for females ------------------------------------------------------------------------------- 749 . title4 Simultaneous trimming to .1 female wave 3" "Dose => Problems with Fam > ily at home models" ------------------------------------------------------------------------------- Simultaneous trimming to ------------------------------------------------------------------------------- 750 . local w3bf bf1 bf4 bf2 bf4m bf5m bf7m bf8 bf15m bf17 bf20 bf22 bf29 bf30 bf40 751 . logit HP2pbfhm age dvcew3 avgcumdosew3 bf4 /// > if gender==2, iterate(50) Iteration 0: log likelihood = -139.89675 Iteration 1: log likelihood = -113.53198 Iteration 2: log likelihood = -107.97258 Iteration 3: log likelihood = -107.87574 Iteration 4: log likelihood = -107.87549 Iteration 5: log likelihood = -107.87549 Logistic regression Number of obs = 363 LR chi2(4) = 64.04 Prob > chi2 = 0.0000 Log likelihood = -107.87549 Pseudo R2 = 0.2289 ------------------------------------------------------------------------------ HP2pbfhm | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0645234 .0172238 3.75 0.000 .0307654 .0982813 dvcew3 | .8311533 .6285086 1.32 0.186 -.4007009 2.063007 avgcumdosew3 | -.0017344 .0768006 -0.02 0.982 -.1522607 .148792 bf4 | -.175564 .0365808 -4.80 0.000 -.2472611 -.1038669 _cons | -4.048039 1.095505 -3.70 0.000 -6.195189 -1.900889 ------------------------------------------------------------------------------ 752 . 753 . estat class Logistic model for HP2pbfhm -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 8 5 | 13 - | 39 311 | 350 -----------+--------------------------+----------- Total | 47 316 | 363 Classified + if predicted Pr(D) >= .5 True D defined as HP2pbfhm != 0 -------------------------------------------------- Sensitivity Pr( +| D) 17.02% Specificity Pr( -|~D) 98.42% Positive predictive value Pr( D| +) 61.54% Negative predictive value Pr(~D| -) 88.86% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 1.58% False - rate for true D Pr( -| D) 82.98% False + rate for classified + Pr(~D| +) 38.46% False - rate for classified - Pr( D| -) 11.14% -------------------------------------------------- Correctly classified 87.88% -------------------------------------------------- 754 . estat gof Logistic model for HP2pbfhm, goodness-of-fit test number of observations = 363 number of covariate patterns = 357 Pearson chi2(352) = 307.66 Prob > chi2 = 0.9574 755 . fitstat Measures of Fit for logit of HP2pbfhm Log-Lik Intercept Only: -139.897 Log-Lik Full Model: -107.875 D(358): 215.751 LR(4): 64.043 Prob > LR: 0.000 McFadden's R2: 0.229 McFadden's Adj R2: 0.193 Maximum Likelihood R2: 0.162 Cragg & Uhler's R2: 0.301 McKelvey and Zavoina's R2: 0.381 Efron's R2: 0.194 Variance of y*: 5.316 Variance of error: 3.290 Count R2: 0.879 Adj Count R2: 0.064 AIC: 0.622 AIC*n: 225.751 BIC: -1894.445 BIC': -40.465 756 . 757 . 758 . title "Dose effect not significant when simultaneously trimmed for females" ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** *****Dose effect not significant when simultaneously trimmed for females ***** ***** ***** ***** ***** ***** 1 Jul 2012 20:38:50 ***** ******************************************************************************* ******************************************************************************* 759 . 760 . *-------Chunk 6 continued -testing meditors for females 761 . title "More partly female Trimmed wave 3" "Dose => Problems with Family at h > ome models" ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** More partly female Trimmed wave 3 ***** ***** Dose => Problems with Family at home models ***** ***** ***** ***** ***** ***** 1 Jul 2012 20:38:50 ***** ******************************************************************************* ******************************************************************************* 762 . local w3bf bf1 bf4 bf2 bf8 bf15m bf17 bf20 bf22 bf29 bf30 bf40 763 . logit HP2pbfhm age bf4 bf40 if gender==2, iterate(50) Iteration 0: log likelihood = -139.89675 Iteration 1: log likelihood = -112.36921 Iteration 2: log likelihood = -106.24923 Iteration 3: log likelihood = -106.12137 Iteration 4: log likelihood = -106.12091 Iteration 5: log likelihood = -106.12091 Logistic regression Number of obs = 363 LR chi2(3) = 67.55 Prob > chi2 = 0.0000 Log likelihood = -106.12091 Pseudo R2 = 0.2414 ------------------------------------------------------------------------------ HP2pbfhm | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0636233 .017269 3.68 0.000 .0297767 .0974699 bf4 | -.2029758 .0392585 -5.17 0.000 -.2799211 -.1260305 bf40 | -.1942568 .091411 -2.13 0.034 -.373419 -.0150946 _cons | -3.085643 1.113267 -2.77 0.006 -5.267607 -.9036792 ------------------------------------------------------------------------------ 764 . 765 . estat class Logistic model for HP2pbfhm -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 12 3 | 15 - | 35 313 | 348 -----------+--------------------------+----------- Total | 47 316 | 363 Classified + if predicted Pr(D) >= .5 True D defined as HP2pbfhm != 0 -------------------------------------------------- Sensitivity Pr( +| D) 25.53% Specificity Pr( -|~D) 99.05% Positive predictive value Pr( D| +) 80.00% Negative predictive value Pr(~D| -) 89.94% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 0.95% False - rate for true D Pr( -| D) 74.47% False + rate for classified + Pr(~D| +) 20.00% False - rate for classified - Pr( D| -) 10.06% -------------------------------------------------- Correctly classified 89.53% -------------------------------------------------- 766 . estat gof Logistic model for HP2pbfhm, goodness-of-fit test number of observations = 363 number of covariate patterns = 341 Pearson chi2(337) = 366.00 Prob > chi2 = 0.1331 767 . fitstat Measures of Fit for logit of HP2pbfhm Log-Lik Intercept Only: -139.897 Log-Lik Full Model: -106.121 D(359): 212.242 LR(3): 67.552 Prob > LR: 0.000 McFadden's R2: 0.241 McFadden's Adj R2: 0.213 Maximum Likelihood R2: 0.170 Cragg & Uhler's R2: 0.316 McKelvey and Zavoina's R2: 0.399 Efron's R2: 0.224 Variance of y*: 5.470 Variance of error: 3.290 Count R2: 0.895 Adj Count R2: 0.191 AIC: 0.607 AIC*n: 220.242 BIC: -1903.849 BIC': -49.868 768 . 769 . scalar SigDosePrbfmhmFw3 = "no" 770 . scalar MainEffPrbfmhmFw3 = "age bf4 bf40" 771 . * 3 significant main effects for females 772 . * no significant main effect for dose 773 . 774 . * constructing moderators 775 . 776 . foreach var in bf4 bf40 { 2. cap gen `var'Xd3 = `var'*avgcumdosew3 3. } 777 . 778 . 779 . *- testing female moderator effects: no moderator effects for females 780 . 781 . sw, pr(.1): logit HP2pbfhm age bf4 bf40 ageXd3 bf4Xd3 bf40Xd3 if gender==2, i > terate(50) begin with full model p = 0.7256 >= 0.1000 removing bf4Xd3 p = 0.5514 >= 0.1000 removing bf40 Logistic regression Number of obs = 363 LR chi2(4) = 69.05 Prob > chi2 = 0.0000 Log likelihood = -105.37103 Pseudo R2 = 0.2468 ------------------------------------------------------------------------------ HP2pbfhm | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0553962 .0175151 3.16 0.002 .0210671 .0897253 bf4 | -.1901097 .0380586 -5.00 0.000 -.2647032 -.1155163 bf40Xd3 | -.1318421 .0668537 -1.97 0.049 -.262873 -.0008113 ageXd3 | .0078148 .0040047 1.95 0.051 -.0000342 .0156639 _cons | -3.363212 1.084085 -3.10 0.002 -5.487979 -1.238446 ------------------------------------------------------------------------------ 782 . estat gof Logistic model for HP2pbfhm, goodness-of-fit test number of observations = 363 number of covariate patterns = 359 Pearson chi2(354) = 358.75 Prob > chi2 = 0.4197 783 . estat class Logistic model for HP2pbfhm -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 12 4 | 16 - | 35 312 | 347 -----------+--------------------------+----------- Total | 47 316 | 363 Classified + if predicted Pr(D) >= .5 True D defined as HP2pbfhm != 0 -------------------------------------------------- Sensitivity Pr( +| D) 25.53% Specificity Pr( -|~D) 98.73% Positive predictive value Pr( D| +) 75.00% Negative predictive value Pr(~D| -) 89.91% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 1.27% False - rate for true D Pr( -| D) 74.47% False + rate for classified + Pr(~D| +) 25.00% False - rate for classified - Pr( D| -) 10.09% -------------------------------------------------- Correctly classified 89.26% -------------------------------------------------- 784 . fitstat Measures of Fit for logit of HP2pbfhm Log-Lik Intercept Only: -139.897 Log-Lik Full Model: -105.371 D(358): 210.742 LR(4): 69.051 Prob > LR: 0.000 McFadden's R2: 0.247 McFadden's Adj R2: 0.211 Maximum Likelihood R2: 0.173 Cragg & Uhler's R2: 0.322 McKelvey and Zavoina's R2: 0.417 Efron's R2: 0.228 Variance of y*: 5.645 Variance of error: 3.290 Count R2: 0.893 Adj Count R2: 0.170 AIC: 0.608 AIC*n: 220.742 BIC: -1899.454 BIC': -45.474 785 . 786 . scalar PrbfmhmModFw3="none" 787 . 788 . ***************************************************************************** > *** 789 . *---------Chunk 6 continued testing mediating effects for Problems with famil > y 790 . * at home 791 . 792 . * age is a mediating effect for males for Dose=> problems with family at home 793 . des bf4 bf40 storage display value variable name type format label variable label ------------------------------------------------------------------------------- bf4 float %9.0g bf4 = max(0, 24 - BSIsoma) bf40 float %9.0g bf40 = max(0, icdxcnt - 1.01635E-007) 794 . glm age avgcumdosew3 if gender==1, fam(gaus) link(identity) Iteration 0: log likelihood = -1330.6336 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = 147.7142 Deviance = 49927.38549 (1/df) Deviance = 147.7142 Pearson = 49927.38549 (1/df) Pearson = 147.7142 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 7.839021 Log likelihood = -1330.633586 BIC = 47957.2 ------------------------------------------------------------------------------ | OIM age | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | .5433648 .2472657 2.20 0.028 .058733 1.027997 _cons | 48.52021 .7247376 66.95 0.000 47.09975 49.94067 ------------------------------------------------------------------------------ 795 . glm HP2pbfhm age if gender==1, fam(bin) irls scale(dev) link(probit) Iteration 1: deviance = 163.1004 Iteration 2: deviance = 152.8997 Iteration 3: deviance = 151.9532 Iteration 4: deviance = 151.9347 Iteration 5: deviance = 151.9347 Iteration 6: deviance = 151.9347 Generalized linear models No. of obs = 340 Optimization : MQL Fisher scoring Residual df = 338 (IRLS EIM) Scale parameter = 1 Deviance = 151.9346518 (1/df) Deviance = .4495108 Pearson = 324.8005072 (1/df) Pearson = .9609482 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1818.249 ------------------------------------------------------------------------------ | EIM HP2pbfhm | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0296385 .0061334 4.83 0.000 .0176173 .0416597 _cons | -3.073816 .3430721 -8.96 0.000 -3.746225 -2.401407 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 796 . glm bf4 avgcumdosew3 if gender==1, fam(gaus) link(identity) Iteration 0: log likelihood = -1027.1072 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = 24.77487 Deviance = 8373.906252 (1/df) Deviance = 24.77487 Pearson = 8373.906252 (1/df) Pearson = 24.77487 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 6.053572 Log likelihood = -1027.107224 BIC = 6403.723 ------------------------------------------------------------------------------ | OIM bf4 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | -.0357675 .1012648 -0.35 0.724 -.2342429 .1627078 _cons | 12.54064 .2968079 42.25 0.000 11.95891 13.12238 ------------------------------------------------------------------------------ 797 . glm HP2pbfhm bf4 if gender==1, fam(bin) irls scale(dev) link(probit) Iteration 1: deviance = 160.0024 Iteration 2: deviance = 148.9095 Iteration 3: deviance = 148.0472 Iteration 4: deviance = 148.0358 Iteration 5: deviance = 148.0358 Iteration 6: deviance = 148.0358 Generalized linear models No. of obs = 340 Optimization : MQL Fisher scoring Residual df = 338 (IRLS EIM) Scale parameter = 1 Deviance = 148.0358223 (1/df) Deviance = .4379758 Pearson = 318.8927909 (1/df) Pearson = .9434698 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1822.148 ------------------------------------------------------------------------------ | EIM HP2pbfhm | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- bf4 | -.0752171 .0127773 -5.89 0.000 -.1002602 -.0501741 _cons | -.6910419 .1483563 -4.66 0.000 -.9818149 -.400269 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 798 . 799 . * age is a mediating effect for females for Dose=> Problems with family at ho > me 800 . glm age avgcumdosew3 if gender==2, fam(gaus) link(identity) Iteration 0: log likelihood = -1408.064 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = 137.7687 Deviance = 49734.51399 (1/df) Deviance = 137.7687 Pearson = 49734.51399 (1/df) Pearson = 137.7687 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 7.768948 Log likelihood = -1408.06405 BIC = 47606.63 ------------------------------------------------------------------------------ | OIM age | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | 1.058366 .3512614 3.01 0.003 .3699069 1.746826 _cons | 48.94293 .7468173 65.54 0.000 47.47919 50.40666 ------------------------------------------------------------------------------ 801 . glm HP2pbfhm age if gender==2, fam(bin) irls scale(dev) link(probit) Iteration 1: deviance = 252.4902 Iteration 2: deviance = 245.4181 Iteration 3: deviance = 245.1325 Iteration 4: deviance = 245.1321 Iteration 5: deviance = 245.1321 Generalized linear models No. of obs = 363 Optimization : MQL Fisher scoring Residual df = 361 (IRLS EIM) Scale parameter = 1 Deviance = 245.1320769 (1/df) Deviance = .6790362 Pearson = 382.7456824 (1/df) Pearson = 1.060237 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1882.747 ------------------------------------------------------------------------------ | EIM HP2pbfhm | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .043836 .0066445 6.60 0.000 .030813 .056859 _cons | -3.477625 .3761287 -9.25 0.000 -4.214824 -2.740426 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 802 . 803 . * bf4 is a mediting effect for females for Dose=> Problems with family at hom > e 804 . glm bf4 avgcumdosew3 if gender==2, fam(gaus) link(identity) Iteration 0: log likelihood = -1109.6569 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = 26.6146 Deviance = 9607.869105 (1/df) Deviance = 26.6146 Pearson = 9607.869105 (1/df) Pearson = 26.6146 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 6.124831 Log likelihood = -1109.656873 BIC = 7479.99 ------------------------------------------------------------------------------ | OIM bf4 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | -.4386292 .1543885 -2.84 0.004 -.7412252 -.1360333 _cons | 11.01475 .3282456 33.56 0.000 10.3714 11.6581 ------------------------------------------------------------------------------ 805 . glm HP2pbfhm bf4 if gender==2, fam(bin) irls scale(dev) link(probit) Iteration 1: deviance = 240.0481 Iteration 2: deviance = 229.4916 Iteration 3: deviance = 228.6166 Iteration 4: deviance = 228.5986 Iteration 5: deviance = 228.5985 Iteration 6: deviance = 228.5985 Generalized linear models No. of obs = 363 Optimization : MQL Fisher scoring Residual df = 361 (IRLS EIM) Scale parameter = 1 Deviance = 228.5985175 (1/df) Deviance = .6332369 Pearson = 299.6186696 (1/df) Pearson = .8299686 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1899.281 ------------------------------------------------------------------------------ | EIM HP2pbfhm | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- bf4 | -.1229375 .0145262 -8.46 0.000 -.1514083 -.0944667 _cons | -.0739521 .1322299 -0.56 0.576 -.3331179 .1852138 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 806 . 807 . 808 . glm bf40 avgcumdosew3 if gender==2, fam(gaus) link(identity) Iteration 0: log likelihood = -818.14796 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = 5.340664 Deviance = 1927.979854 (1/df) Deviance = 5.340664 Pearson = 1927.979854 (1/df) Pearson = 5.340664 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 4.518722 Log likelihood = -818.1479598 BIC = -199.8996 ------------------------------------------------------------------------------ | OIM bf40 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | .152897 .0691596 2.21 0.027 .0173466 .2884474 _cons | 2.981537 .1470404 20.28 0.000 2.693343 3.269731 ------------------------------------------------------------------------------ 809 . glm HP2pbfhm bf40 if gender==2, fam(bin) irls scale(dev) link(probit) Iteration 1: deviance = 280.0603 Iteration 2: deviance = 279.7443 Iteration 3: deviance = 279.7441 Iteration 4: deviance = 279.7441 Generalized linear models No. of obs = 363 Optimization : MQL Fisher scoring Residual df = 361 (IRLS EIM) Scale parameter = 1 Deviance = 279.7440687 (1/df) Deviance = .7749143 Pearson = 362.9453702 (1/df) Pearson = 1.005389 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1848.135 ------------------------------------------------------------------------------ | EIM HP2pbfhm | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- bf40 | .0081494 .0313367 0.26 0.795 -.0532693 .0695682 _cons | -1.154869 .1244365 -9.28 0.000 -1.398761 -.9109783 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 810 . 811 . scalar PrbfmhmMedMw3 = "age" 812 . scalar PrbfmhmMedFw3 = "age bf4" 813 . 814 . title4 " Summary of dose=problems with family at home mediating effects " ------------------------------------------------------------------------------- Summary of dose=problems with family at home mediating effects ------------------------------------------------------------------------------- 815 . * males mediators age 1 816 . * females mediators age and BSIsoma rescaled (bf4) 2 817 . 818 . matrix define HP2prbfamMw3 = J(1,8, 0) 819 . matrix define HP2prbfamFw3 = J(1,8, 0) 820 . matrix colnames HP2prbfamMw3 = hypnum ptnum wave gender medsig numMAsig numM > odsig numMed 821 . matrix colnames HP2prbfamFw3= hypnum ptnum wave gender medsig numMAs > ig numModsig numMed 822 . matrix define HP2prbfamMw3= (1, 2, 3, 1, 0, 5, 0, 1 ) 823 . matrix define HP2prbfamFw3= (1, 2, 3, 2, 0, 2, 2, 2) 824 . matrix rowname HP2prbfamMw3 = HP2prbfamM 825 . matrix rowname HP2prbfamFw3 = HP2prbfamF 826 . matlist HP2prbfamMw3 | c1 c2 c3 c4 c5 c6 > -------------+----------------------------------------------------------------- - HP2prbfamM | 1 2 3 1 0 5 > | c7 c8 -------------+---------------------- HP2prbfamM | 0 1 827 . matlist HP2prbfamFw3 | c1 c2 c3 c4 c5 c6 > -------------+----------------------------------------------------------------- - HP2prbfamF | 1 2 3 2 0 2 > | c7 c8 -------------+---------------------- HP2prbfamF | 2 2 828 . matrix define H1pt2w3 = ( HP2wkMw3 \ HP2wkFw3 \ HP2hmcrMw3 \ HP2hmcrF > w3 \HP2spMw3 \HP2spFw3 \ HP2prbfamMw3 \ HP2prbfamFw3 ) 829 . 830 . matlist H1pt2w3 | c1 c2 c3 c4 c5 c6 > -------------+----------------------------------------------------------------- - r1 | 1 2 3 1 0 4 > r1 | 1 2 3 2 0 1 > r1 | 1 2 3 1 0 4 > r1 | 1 2 3 2 0 2 > HP2spMw3 | 1 2 3 1 0 2 > HP2spFw3 | 1 2 3 2 1 5 > HP2prbfamM | 1 2 3 1 0 5 > HP2prbfamF | 1 2 3 2 0 2 > | c7 c8 -------------+---------------------- r1 | 0 4 r1 | 0 6 r1 | 0 2 r1 | 0 2 HP2spMw3 | 0 1 HP2spFw3 | 5 3 HP2prbfamM | 0 1 HP2prbfamF | 2 2 831 . matrix colnames H1pt2w3 = hypnum ptnum wave gender medsig numMAsig numMo > dsig numMed 832 . matrix rownames H1pt2w3 = HP2wkMw3 HP2wkFw3 HP2hmcrMw3 HP2hmcrFw3 HP2pr > bfhmMw3 HP2prbfhmFw3 833 . matlist H1pt2w3 | hypnum ptnum wave gender medsig numMAsig > -------------+----------------------------------------------------------------- - HP2wkMw3 | 1 2 3 1 0 4 > HP2wkFw3 | 1 2 3 2 0 1 > HP2hmcrMw3 | 1 2 3 1 0 4 > HP2hmcrFw3 | 1 2 3 2 0 2 > HP2prbfhmMw3 | 1 2 3 1 0 2 > HP2prbfhmFw3 | 1 2 3 2 1 5 > HP2prbfhmFw3 | 1 2 3 1 0 5 > HP2prbfhmFw3 | 1 2 3 2 0 2 > | numModsig numMed -------------+---------------------- HP2wkMw3 | 0 4 HP2wkFw3 | 0 6 HP2hmcrMw3 | 0 2 HP2hmcrFw3 | 0 2 HP2prbfhmMw3 | 0 1 HP2prbfhmFw3 | 5 3 HP2prbfhmFw3 | 0 1 HP2prbfhmFw3 | 2 2 834 . 835 . 836 . *---------------------------------------------------------------------------- > --- 837 . ***************************************************************************** > *** 838 . *-------Chunk 7 Dose==> problems with sex life impact 839 . * Chunk 7 General model for all part 2 of Nottingham Health Profile 840 . 841 . title "5. Wave 3 part2 H1: Test of hypothesis 1 with Male and Female Respond > ents" /// > " Wave 3 Main effects Dose=> sexlife impact identification" ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** *****5. Wave 3 part2 H1: Test of hypothesis 1 with Male and Female Respondents > ***** ***** Wave 3 Main effects Dose=> sexlife impact identification ***** ***** ***** ***** ***** ***** 1 Jul 2012 20:39:11 ***** ******************************************************************************* ******************************************************************************* 842 . forvalues j=3/3 { 2. set more off 3. 843 . des age educ1-educ7 marrw`j'1-marrw`j'6 inc1w`j'-inc4w`j' /// > bf1 bf4 bf9 bf11 bf4m bf15m bf30 bf40 4. 844 . foreach var in HP2sxlife { 5. forvalues k=1/2 { 6. local w3bf bf1 bf4 bf2 bf4m bf5m bf7m bf8 bf15m bf17 bf20 bf22 bf29 bf30 b > f40 7. title "Full Nottingham Part 2 subscale models for male & females" /// > "Full main model for `var' for wave= `j' " /// > "chunk 7 H1 test:Gender= `k' model Wave = `j' for `e(depvar)' " 8. di _skip(4) 9. 845 . di _skip(4) 10. 846 . 847 . xi: logistic `var' age i.educ occ1w`j'-occ8w`j' /// > marrw`j'1- marrw`j'3 marrw`j'5-marrw`j'6 inc1w`j'-inc4w`j' // > / > radhlw`j' havmil avgcumdosew`j' `w`j'bf' /// > deaw`j' dvcew`j' sepaw`j' accdw`j' movew`j' /// > illw`j' shfamw`j' shhlw`j' shjobw`j' shrelaw`j' suprtw`j' suc > hrw`j' /// > havmilsq radhlw3 if gender==`k', coef nolog difficult itera > te(50) 11. estat class 12. estat gof 13. fitstat 14. } 15. } 16. } storage display value variable name type format label variable label ------------------------------------------------------------------------------- age double %8.0g * Respondent's age educ1 byte %8.0g educ==1. did not graduate high school educ2 byte %8.0g educ==2. graduated high school educ3 byte %8.0g educ==3. technical degree educ4 byte %8.0g educ==4. did not finish college/bachelor's educ5 byte %8.0g educ==5. graduated college/bachelor's educ6 byte %8.0g educ==6. finished specialist/master's degree educ7 byte %8.0g educ==7. doctor of science/phd marrw31 byte %8.0g marrw3==1. single marrw32 byte %8.0g marrw3==2. cohabitating marrw33 byte %8.0g marrw3==3. married marrw34 byte %8.0g marrw3==4. separated marrw35 byte %8.0g marrw3==5. divorced marrw36 byte %8.0g marrw3==6. widowed inc1w3 double %15.0g LABJ Income is not sufficient for basic neccessities NOW inc2w3 double %15.0g LABJ Income is just sufficient for basic neccessities NOW inc3w3 double %15.0g LABJ Income is sufficient for basics plus extra purchases/savings NOW inc4w3 double %15.0g LABJ Income allows to comfortably afford luxury items NOW bf1 float %9.0g bf1 = max(0, kzchorn - 40) bf4 float %9.0g bf4 = max(0, 24 - BSIsoma) bf9 float %9.0g bf9= max(0, 30 - shhlw1) bf11 float %9.0g bf11= max(0, 20 - sufamw1) bf4m float %9.0g bf4m = max(0, 32 - BSIsoma) bf15m float %9.0g bf15m= max(0, 1 - icdxcnt) * bf2 bf30 float %9.0g bf30 = max(0, neiw1 - 85) * bf20 bf40 float %9.0g bf40 = max(0, icdxcnt - 1.01635E-007) ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Full Nottingham Part 2 subscale models for male & females ***** ***** Full main model for HP2sxlife for wave= 3 ***** ***** chunk 7 H1 test:Gender= 1 model Wave = 3 for HP2pbfhm ***** ***** ***** ***** ***** ***** 1 Jul 2012 20:39:11 ***** ******************************************************************************* ******************************************************************************* i.educ _Ieduc_1-8 (naturally coded; _Ieduc_1 omitted) note: _Ieduc_7 != 0 predicts failure perfectly _Ieduc_7 dropped and 4 obs not used note: occ6w3 != 0 predicts failure perfectly occ6w3 dropped and 4 obs not used note: bf15m != 0 predicts failure perfectly bf15m dropped and 20 obs not used note: bf29 != 0 predicts failure perfectly bf29 dropped and 8 obs not used note: _Ieduc_8 omitted because of collinearity note: occ8w3 omitted because of collinearity note: marrw36 omitted because of collinearity note: bf17 omitted because of collinearity note: radhlw3 omitted because of collinearity Logistic regression Number of obs = 304 LR chi2(47) = 153.48 Prob > chi2 = 0.0000 Log likelihood = -86.082561 Pseudo R2 = 0.4713 ------------------------------------------------------------------------------ HP2sxlife | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .1069256 .0319906 3.34 0.001 .0442252 .169626 _Ieduc_2 | -.7455102 2.711615 -0.27 0.783 -6.060177 4.569157 _Ieduc_3 | -1.187035 2.60622 -0.46 0.649 -6.295133 3.921063 _Ieduc_4 | -2.546669 2.819292 -0.90 0.366 -8.072379 2.979041 _Ieduc_5 | -.9083698 2.596245 -0.35 0.726 -5.996916 4.180177 _Ieduc_6 | -.821989 2.54798 -0.32 0.747 -5.815938 4.17196 _Ieduc_7 | 0 (omitted) _Ieduc_8 | 0 (omitted) occ1w3 | -13.83588 1847.337 -0.01 0.994 -3634.551 3606.879 occ2w3 | -14.1177 1847.337 -0.01 0.994 -3634.833 3606.597 occ3w3 | -15.12911 1847.338 -0.01 0.993 -3635.845 3605.586 occ4w3 | -14.04877 1847.338 -0.01 0.994 -3634.764 3606.666 occ5w3 | -13.39243 1847.338 -0.01 0.994 -3634.108 3607.323 occ6w3 | 0 (omitted) occ7w3 | -14.25779 1847.337 -0.01 0.994 -3634.973 3606.457 occ8w3 | 0 (omitted) marrw31 | 1.917986 1.336919 1.43 0.151 -.7023282 4.538299 marrw32 | -.8798595 1.841469 -0.48 0.633 -4.489073 2.729354 marrw33 | .8814069 1.275273 0.69 0.489 -1.618082 3.380896 marrw35 | 1.398611 1.615954 0.87 0.387 -1.768602 4.565823 marrw36 | 0 (omitted) inc1w3 | 16.59262 1847.337 0.01 0.993 -3604.122 3637.307 inc2w3 | 16.41393 1847.337 0.01 0.993 -3604.3 3637.128 inc3w3 | 14.9931 1847.337 0.01 0.994 -3605.721 3635.708 inc4w3 | 13.76529 1847.339 0.01 0.994 -3606.952 3634.482 radhlw3 | .0155883 .0090158 1.73 0.084 -.0020824 .0332591 havmil | .0032884 .0119659 0.27 0.783 -.0201643 .0267412 avgcumdosew3 | .0366781 .0541231 0.68 0.498 -.0694012 .1427574 bf1 | .0224773 .0438725 0.51 0.608 -.0635113 .108466 bf4 | -.3119601 .2453847 -1.27 0.204 -.7929052 .168985 bf2 | .0000786 .0001745 0.45 0.652 -.0002634 .0004207 bf4m | .0103662 .2174828 0.05 0.962 -.4158923 .4366247 bf5m | .0028825 .0019867 1.45 0.147 -.0010113 .0067763 bf7m | .0013372 .0006507 2.05 0.040 .0000618 .0026126 bf8 | -.0000698 .0000479 -1.46 0.145 -.0001638 .0000241 bf15m | 0 (omitted) bf17 | 0 (omitted) bf20 | -.0288329 .0347084 -0.83 0.406 -.09686 .0391943 bf22 | -.0000907 .0001888 -0.48 0.631 -.0004608 .0002793 bf29 | 0 (omitted) bf30 | -5.44e-06 .0004196 -0.01 0.990 -.0008279 .0008171 bf40 | .3549975 .2522025 1.41 0.159 -.1393104 .8493054 deaw3 | -.1446966 .2515866 -0.58 0.565 -.6377974 .3484041 dvcew3 | .2312151 1.685819 0.14 0.891 -3.07293 3.535361 sepaw3 | 1.563211 1.973158 0.79 0.428 -2.304108 5.430529 accdw3 | -1.029126 .9986452 -1.03 0.303 -2.986435 .9281827 movew3 | -.3161441 .7920977 -0.40 0.690 -1.868627 1.236339 illw3 | .2509498 .2730406 0.92 0.358 -.2841998 .7860995 shfamw3 | -.0049114 .0092237 -0.53 0.594 -.0229895 .0131668 shhlw3 | -.0135671 .0078785 -1.72 0.085 -.0290087 .0018746 shjobw3 | .0090088 .0079953 1.13 0.260 -.0066617 .0246793 shrelaw3 | -.0052844 .0083104 -0.64 0.525 -.0215726 .0110037 suprtw3 | .0083949 .0090554 0.93 0.354 -.0093533 .0261431 suchrw3 | -.0115343 .0079215 -1.46 0.145 -.0270603 .0039916 havmilsq | -.0000122 .0000253 -0.48 0.630 -.0000618 .0000374 radhlw3 | 0 (omitted) _cons | -6.912277 3.93482 -1.76 0.079 -14.62438 .7998281 ------------------------------------------------------------------------------ Note: 4 failures and 0 successes completely determined. Logistic model for HP2sxlife -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 44 14 | 58 - | 25 221 | 246 -----------+--------------------------+----------- Total | 69 235 | 304 Classified + if predicted Pr(D) >= .5 True D defined as HP2sxlife != 0 -------------------------------------------------- Sensitivity Pr( +| D) 63.77% Specificity Pr( -|~D) 94.04% Positive predictive value Pr( D| +) 75.86% Negative predictive value Pr(~D| -) 89.84% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 5.96% False - rate for true D Pr( -| D) 36.23% False + rate for classified + Pr(~D| +) 24.14% False - rate for classified - Pr( D| -) 10.16% -------------------------------------------------- Correctly classified 87.17% -------------------------------------------------- Logistic model for HP2sxlife, goodness-of-fit test number of observations = 304 number of covariate patterns = 304 Pearson chi2(256) = 202.32 Prob > chi2 = 0.9943 Measures of Fit for logistic of HP2sxlife Log-Lik Intercept Only: -162.820 Log-Lik Full Model: -86.083 D(247): 172.165 LR(47): 153.476 Prob > LR: 0.000 McFadden's R2: 0.471 McFadden's Adj R2: 0.121 Maximum Likelihood R2: 0.396 Cragg & Uhler's R2: 0.603 McKelvey and Zavoina's R2: 0.800 Efron's R2: 0.484 Variance of y*: 16.474 Variance of error: 3.290 Count R2: 0.872 Adj Count R2: 0.435 AIC: 0.941 AIC*n: 286.165 BIC: -1239.941 BIC': 115.224 ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Full Nottingham Part 2 subscale models for male & females ***** ***** Full main model for HP2sxlife for wave= 3 ***** ***** chunk 7 H1 test:Gender= 2 model Wave = 3 for HP2sxlife ***** ***** ***** ***** ***** ***** 1 Jul 2012 20:39:12 ***** ******************************************************************************* ******************************************************************************* i.educ _Ieduc_1-8 (naturally coded; _Ieduc_1 omitted) note: occ8w3 != 0 predicts failure perfectly occ8w3 dropped and 1 obs not used note: bf15m != 0 predicts failure perfectly bf15m dropped and 12 obs not used note: bf29 != 0 predicts success perfectly bf29 dropped and 4 obs not used note: _Ieduc_8 omitted because of collinearity note: bf17 omitted because of collinearity note: radhlw3 omitted because of collinearity Logistic regression Number of obs = 345 LR chi2(50) = 168.03 Prob > chi2 = 0.0000 Log likelihood = -114.00457 Pseudo R2 = 0.4243 ------------------------------------------------------------------------------ HP2sxlife | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0813848 .0244496 3.33 0.001 .0334644 .1293053 _Ieduc_2 | -12.79022 653.1326 -0.02 0.984 -1292.907 1267.326 _Ieduc_3 | -11.94607 653.1326 -0.02 0.985 -1292.062 1268.17 _Ieduc_4 | -11.36768 653.1328 -0.02 0.986 -1291.484 1268.749 _Ieduc_5 | -12.54328 653.1327 -0.02 0.985 -1292.66 1267.573 _Ieduc_6 | -11.93918 653.1326 -0.02 0.985 -1292.055 1268.177 _Ieduc_7 | -12.87216 653.1524 -0.02 0.984 -1293.027 1267.283 _Ieduc_8 | 0 (omitted) occ1w3 | -2.703036 2.21975 -1.22 0.223 -7.053665 1.647593 occ2w3 | -2.165029 2.323461 -0.93 0.351 -6.718929 2.388871 occ3w3 | -2.030908 2.234964 -0.91 0.364 -6.411358 2.349542 occ4w3 | -1.625969 2.528132 -0.64 0.520 -6.581016 3.329078 occ5w3 | .7269315 2.820396 0.26 0.797 -4.800943 6.254806 occ6w3 | -.7633882 2.518786 -0.30 0.762 -5.700118 4.173342 occ7w3 | -1.433838 2.203631 -0.65 0.515 -5.752876 2.8852 occ8w3 | 0 (omitted) marrw31 | .3247443 1.774101 0.18 0.855 -3.152431 3.801919 marrw32 | .8501767 2.207491 0.39 0.700 -3.476427 5.17678 marrw33 | 1.557872 1.575773 0.99 0.323 -1.530585 4.646329 marrw35 | -.4253418 1.619183 -0.26 0.793 -3.598882 2.748198 marrw36 | 1.703593 1.601915 1.06 0.288 -1.436102 4.843288 inc1w3 | 1.766812 2.253827 0.78 0.433 -2.650608 6.184231 inc2w3 | 2.269344 2.224897 1.02 0.308 -2.091374 6.630061 inc3w3 | .9292343 2.201873 0.42 0.673 -3.386357 5.244826 inc4w3 | 1.449624 2.775037 0.52 0.601 -3.989349 6.888597 radhlw3 | .0277216 .0091569 3.03 0.002 .0097745 .0456688 havmil | .0021336 .0032179 0.66 0.507 -.0041733 .0084405 avgcumdosew3 | .1969924 .1165031 1.69 0.091 -.0313496 .4253343 bf1 | .0285984 .0382244 0.75 0.454 -.04632 .1035168 bf4 | -.4015139 .2038932 -1.97 0.049 -.8011373 -.0018905 bf2 | -.0001649 .0001225 -1.35 0.178 -.0004051 .0000753 bf4m | .3523301 .1864609 1.89 0.059 -.0131266 .7177867 bf5m | -.0026053 .001955 -1.33 0.183 -.006437 .0012264 bf7m | -.0000741 .0006237 -0.12 0.905 -.0012966 .0011483 bf8 | -5.22e-06 .0000423 -0.12 0.902 -.0000881 .0000777 bf15m | 0 (omitted) bf17 | 0 (omitted) bf20 | -.0120216 .031995 -0.38 0.707 -.0747307 .0506874 bf22 | -.0001004 .0001357 -0.74 0.459 -.0003664 .0001655 bf29 | 0 (omitted) bf30 | -.0002441 .0003438 -0.71 0.478 -.0009179 .0004298 bf40 | .095062 .1371931 0.69 0.488 -.1738314 .3639555 deaw3 | .0760781 .1918427 0.40 0.692 -.2999267 .4520829 dvcew3 | 1.127371 .952705 1.18 0.237 -.7398962 2.994639 sepaw3 | .5833047 .936842 0.62 0.534 -1.252872 2.419481 accdw3 | -.5118992 .5859911 -0.87 0.382 -1.660421 .6366223 movew3 | -.6063637 1.823477 -0.33 0.739 -4.180313 2.967586 illw3 | .1168429 .1761008 0.66 0.507 -.2283082 .4619941 shfamw3 | .0084815 .007536 1.13 0.260 -.0062888 .0232518 shhlw3 | .0066923 .0066985 1.00 0.318 -.0064365 .0198212 shjobw3 | -.0046191 .0070704 -0.65 0.514 -.0184767 .0092386 shrelaw3 | -.0123617 .0074084 -1.67 0.095 -.0268819 .0021585 suprtw3 | -.0091554 .0078461 -1.17 0.243 -.0245335 .0062227 suchrw3 | -.0034248 .0055225 -0.62 0.535 -.0142486 .0073991 havmilsq | -2.54e-06 2.55e-06 -1.00 0.319 -7.52e-06 2.45e-06 radhlw3 | 0 (omitted) _cons | 1.83356 653.1407 0.00 0.998 -1278.299 1281.966 ------------------------------------------------------------------------------ Note: 1 failure and 0 successes completely determined. Logistic model for HP2sxlife -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 60 12 | 72 - | 30 243 | 273 -----------+--------------------------+----------- Total | 90 255 | 345 Classified + if predicted Pr(D) >= .5 True D defined as HP2sxlife != 0 -------------------------------------------------- Sensitivity Pr( +| D) 66.67% Specificity Pr( -|~D) 95.29% Positive predictive value Pr( D| +) 83.33% Negative predictive value Pr(~D| -) 89.01% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 4.71% False - rate for true D Pr( -| D) 33.33% False + rate for classified + Pr(~D| +) 16.67% False - rate for classified - Pr( D| -) 10.99% -------------------------------------------------- Correctly classified 87.83% -------------------------------------------------- Logistic model for HP2sxlife, goodness-of-fit test number of observations = 345 number of covariate patterns = 345 Pearson chi2(294) = 343.22 Prob > chi2 = 0.0254 Measures of Fit for logistic of HP2sxlife Log-Lik Intercept Only: -198.018 Log-Lik Full Model: -114.005 D(288): 228.009 LR(50): 168.026 Prob > LR: 0.000 McFadden's R2: 0.424 McFadden's Adj R2: 0.136 Maximum Likelihood R2: 0.386 Cragg & Uhler's R2: 0.565 McKelvey and Zavoina's R2: 0.693 Efron's R2: 0.483 Variance of y*: 10.715 Variance of error: 3.290 Count R2: 0.878 Adj Count R2: 0.533 AIC: 0.991 AIC*n: 342.009 BIC: -1454.932 BIC': 124.151 848 . *-----Chunk 7 dose3 moderator => sex life impact---------------------------- 849 . title "Chunk 7 trimmed male model of dose and HP2sxlife relationship in wave > 3" ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** *****Chunk 7 trimmed male model of dose and HP2sxlife relationship in wave 3*** > ** ***** ***** ***** ***** ***** 1 Jul 2012 20:39:14 ***** ******************************************************************************* ******************************************************************************* 850 . * male models 851 . forvalues j=3/3 { 2. di as input "trimmed HP2sexlife main effects models wave 1 for H1 part 2 > with dose ns" 3. di as input "Wave 3 male dose avgcumdosew`j' main effect not signif" 4. logit HP2sxlife age marrw31-marrw36 bf4 bf5m dvcew`j' illw`j' shhl > w`j' /// > havmilsq shrelaw`j' /// > avgcumdosew`j' radhlw`j' if gender==1 5. estat class 6. estat gof 7. fitstat 8. } trimmed HP2sexlife main effects models wave 1 for H1 part 2 with dose ns Wave 3 male dose avgcumdosew3 main effect not signif note: marrw34 omitted because of collinearity note: marrw36 omitted because of collinearity Iteration 0: log likelihood = -171.51396 Iteration 1: log likelihood = -116.02941 Iteration 2: log likelihood = -108.27742 Iteration 3: log likelihood = -107.96025 Iteration 4: log likelihood = -107.95802 Iteration 5: log likelihood = -107.95802 Logistic regression Number of obs = 340 LR chi2(14) = 127.11 Prob > chi2 = 0.0000 Log likelihood = -107.95802 Pseudo R2 = 0.3706 ------------------------------------------------------------------------------ HP2sxlife | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0742276 .0176614 4.20 0.000 .0396119 .1088433 marrw31 | 1.295459 1.079283 1.20 0.230 -.8198963 3.410814 marrw32 | -.2171872 1.393226 -0.16 0.876 -2.94786 2.513485 marrw33 | .8215567 .8316513 0.99 0.323 -.80845 2.451563 marrw34 | 0 (omitted) marrw35 | .6845196 1.274778 0.54 0.591 -1.813999 3.183038 marrw36 | 0 (omitted) bf4 | -.1751874 .0433174 -4.04 0.000 -.2600878 -.0902869 bf5m | -.0005252 .001056 -0.50 0.619 -.002595 .0015447 dvcew3 | .7519715 .9602947 0.78 0.434 -1.130172 2.634115 illw3 | .4656174 .1837911 2.53 0.011 .1053935 .8258412 shhlw3 | -.0078344 .0055669 -1.41 0.159 -.0187453 .0030765 havmilsq | -4.85e-06 5.73e-06 -0.85 0.398 -.0000161 6.39e-06 shrelaw3 | -.0015114 .0058428 -0.26 0.796 -.0129631 .0099403 avgcumdosew3 | .0567392 .0450409 1.26 0.208 -.0315395 .1450178 radhlw3 | .0138841 .0063766 2.18 0.029 .0013861 .0263821 _cons | -4.875148 1.618703 -3.01 0.003 -8.047748 -1.702548 ------------------------------------------------------------------------------ Logistic model for HP2sxlife -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 37 17 | 54 - | 32 254 | 286 -----------+--------------------------+----------- Total | 69 271 | 340 Classified + if predicted Pr(D) >= .5 True D defined as HP2sxlife != 0 -------------------------------------------------- Sensitivity Pr( +| D) 53.62% Specificity Pr( -|~D) 93.73% Positive predictive value Pr( D| +) 68.52% Negative predictive value Pr(~D| -) 88.81% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 6.27% False - rate for true D Pr( -| D) 46.38% False + rate for classified + Pr(~D| +) 31.48% False - rate for classified - Pr( D| -) 11.19% -------------------------------------------------- Correctly classified 85.59% -------------------------------------------------- Logistic model for HP2sxlife, goodness-of-fit test number of observations = 340 number of covariate patterns = 338 Pearson chi2(323) = 289.05 Prob > chi2 = 0.9130 Measures of Fit for logit of HP2sxlife Log-Lik Intercept Only: -171.514 Log-Lik Full Model: -107.958 D(323): 215.916 LR(14): 127.112 Prob > LR: 0.000 McFadden's R2: 0.371 McFadden's Adj R2: 0.271 Maximum Likelihood R2: 0.312 Cragg & Uhler's R2: 0.491 McKelvey and Zavoina's R2: 0.534 Efron's R2: 0.390 Variance of y*: 7.057 Variance of error: 3.290 Count R2: 0.856 Adj Count R2: 0.290 AIC: 0.735 AIC*n: 249.916 BIC: -1666.833 BIC': -45.507 852 . title "Chunk 7 trimmed male model of dose and HP2sxlife relationship in wave > 3" ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** *****Chunk 7 trimmed male model of dose and HP2sxlife relationship in wave 3*** > ** ***** ***** ***** ***** ***** 1 Jul 2012 20:39:15 ***** ******************************************************************************* ******************************************************************************* 853 . * male models 854 . forvalues j=3/3 { 2. set more off 3. di as input "trimmed HP2sexlife main effects models wave 1 for H1 part 2 > with dose ns" 4. di as input "Wave 3 male dose avgcumdosew`j' main effect not signif" 5. logit HP2sxlife age bf4 illw`j' shhlw`j' /// > havmilsq /// > avgcumdosew`j' radhlw`j' if gender==1 6. estat class 7. estat gof 8. fitstat 9. } trimmed HP2sexlife main effects models wave 1 for H1 part 2 with dose ns Wave 3 male dose avgcumdosew3 main effect not signif Iteration 0: log likelihood = -171.51396 Iteration 1: log likelihood = -116.88501 Iteration 2: log likelihood = -109.88634 Iteration 3: log likelihood = -109.5831 Iteration 4: log likelihood = -109.58073 Iteration 5: log likelihood = -109.58073 Logistic regression Number of obs = 340 LR chi2(7) = 123.87 Prob > chi2 = 0.0000 Log likelihood = -109.58073 Pseudo R2 = 0.3611 ------------------------------------------------------------------------------ HP2sxlife | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0642517 .0157234 4.09 0.000 .0334344 .095069 bf4 | -.1765469 .0392111 -4.50 0.000 -.2533993 -.0996945 illw3 | .4690318 .1644894 2.85 0.004 .1466384 .7914252 shhlw3 | -.0087591 .0051634 -1.70 0.090 -.0188791 .001361 havmilsq | -6.11e-06 5.71e-06 -1.07 0.285 -.0000173 5.09e-06 avgcumdosew3 | .0558129 .0448722 1.24 0.214 -.032135 .1437607 radhlw3 | .0122374 .0056656 2.16 0.031 .001133 .0233417 _cons | -3.483368 1.099461 -3.17 0.002 -5.638272 -1.328464 ------------------------------------------------------------------------------ Logistic model for HP2sxlife -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 37 17 | 54 - | 32 254 | 286 -----------+--------------------------+----------- Total | 69 271 | 340 Classified + if predicted Pr(D) >= .5 True D defined as HP2sxlife != 0 -------------------------------------------------- Sensitivity Pr( +| D) 53.62% Specificity Pr( -|~D) 93.73% Positive predictive value Pr( D| +) 68.52% Negative predictive value Pr(~D| -) 88.81% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 6.27% False - rate for true D Pr( -| D) 46.38% False + rate for classified + Pr(~D| +) 31.48% False - rate for classified - Pr( D| -) 11.19% -------------------------------------------------- Correctly classified 85.59% -------------------------------------------------- Logistic model for HP2sxlife, goodness-of-fit test number of observations = 340 number of covariate patterns = 333 Pearson chi2(325) = 283.30 Prob > chi2 = 0.9540 Measures of Fit for logit of HP2sxlife Log-Lik Intercept Only: -171.514 Log-Lik Full Model: -109.581 D(332): 219.161 LR(7): 123.866 Prob > LR: 0.000 McFadden's R2: 0.361 McFadden's Adj R2: 0.314 Maximum Likelihood R2: 0.305 Cragg & Uhler's R2: 0.481 McKelvey and Zavoina's R2: 0.515 Efron's R2: 0.378 Variance of y*: 6.788 Variance of error: 3.290 Count R2: 0.856 Adj Count R2: 0.290 AIC: 0.692 AIC*n: 235.161 BIC: -1716.048 BIC': -83.064 855 . 856 . scalar MainEffsxlifeMw3 = "age bf4 illw3 radhlw3" 857 . scalar SigDosesxlifeMw3 = "no" 858 . 859 . 860 . forvalues j=3/3 { 2. title "trimmed HP2sxlife main effects models wave `j' for H1 part 2 with d > ose ns" 3. title2 "Wave `j dose HPsxlife relationship but avgcumdosew`j': Dose not si > gnif" 4. } ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** *****trimmed HP2sxlife main effects models wave 3 for H1 part 2 with dose ns*** > ** ***** ***** ***** ***** ***** 1 Jul 2012 20:39:17 ***** ******************************************************************************* ******************************************************************************* ------------------------------------------------------------------------------- title2: Wave `j dose HPsxlife relationship but avgcumdosew3: Dose not signif Date and time: 1 Jul 2012 20:39:17 Working directory: /Users/robertyaffee/ > Documents/data/research/chwk/phase3/Htests/H1tests/h1pt2 Stata data file: chwide1jul2012.dta ha > s 2402 variables and 703 observations Wave `j dose HPsxlife relationship but avgcumdosew3: Dose not signif ------------------------------------------------------------------------------- 861 . 862 . 863 . cap gen radhlw3Xd3 = radhlw3*avgcumdosew3 864 . 865 . set more off 866 . des bf4 storage display value variable name type format label variable label ------------------------------------------------------------------------------- bf4 float %9.0g bf4 = max(0, 24 - BSIsoma) 867 . forvalues j=3/3 { 2. sw, pr(.1):logistic HP2sxlife age bf4 illw`j' /// > avgcumdosew`j' radhlw`j' ageXd3 radhlw3Xd3 illw3Xd3 if gender > ==1, coef nolog 3. estat class 4. estat gof 5. fitstat 6. } begin with full model p = 0.9949 >= 0.1000 removing illw3Xd3 p = 0.2976 >= 0.1000 removing radhlw3Xd3 p = 0.1716 >= 0.1000 removing avgcumdosew3 p = 0.1751 >= 0.1000 removing ageXd3 Logistic regression Number of obs = 340 LR chi2(4) = 117.89 Prob > chi2 = 0.0000 Log likelihood = -112.56939 Pseudo R2 = 0.3437 ------------------------------------------------------------------------------ HP2sxlife | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0655592 .0156078 4.20 0.000 .0349684 .09615 bf4 | -.1526795 .0362827 -4.21 0.000 -.2237922 -.0815668 illw3 | .3916574 .1538103 2.55 0.011 .0901948 .69312 radhlw3 | .0122253 .0056017 2.18 0.029 .0012461 .0232046 _cons | -4.135046 1.063355 -3.89 0.000 -6.219184 -2.050907 ------------------------------------------------------------------------------ Logistic model for HP2sxlife -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 37 15 | 52 - | 32 256 | 288 -----------+--------------------------+----------- Total | 69 271 | 340 Classified + if predicted Pr(D) >= .5 True D defined as HP2sxlife != 0 -------------------------------------------------- Sensitivity Pr( +| D) 53.62% Specificity Pr( -|~D) 94.46% Positive predictive value Pr( D| +) 71.15% Negative predictive value Pr(~D| -) 88.89% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 5.54% False - rate for true D Pr( -| D) 46.38% False + rate for classified + Pr(~D| +) 28.85% False - rate for classified - Pr( D| -) 11.11% -------------------------------------------------- Correctly classified 86.18% -------------------------------------------------- Logistic model for HP2sxlife, goodness-of-fit test number of observations = 340 number of covariate patterns = 309 Pearson chi2(304) = 278.23 Prob > chi2 = 0.8529 Measures of Fit for logistic of HP2sxlife Log-Lik Intercept Only: -171.514 Log-Lik Full Model: -112.569 D(335): 225.139 LR(4): 117.889 Prob > LR: 0.000 McFadden's R2: 0.344 McFadden's Adj R2: 0.315 Maximum Likelihood R2: 0.293 Cragg & Uhler's R2: 0.461 McKelvey and Zavoina's R2: 0.477 Efron's R2: 0.359 Variance of y*: 6.295 Variance of error: 3.290 Count R2: 0.862 Adj Count R2: 0.319 AIC: 0.692 AIC*n: 235.139 BIC: -1727.558 BIC': -94.573 868 . 869 . scalar sxlifeModMw3 = "none" 870 . *xx male moderators: no main significant dose effect 871 . *xx no male moderators for sexlife impact 872 . 873 . 874 . * female models 875 . *-----Chunk 7 dose3 moderator => sex life impact---------------------------- 876 . di as input "chunk 7 female wave=3" chunk 7 female wave=3 877 . title "Chunk 7 trimmed female model:" "dose and HP2sxlife relationship in wav > e 3" ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Chunk 7 trimmed female model: ***** ***** dose and HP2sxlife relationship in wave 3 ***** ***** ***** ***** ***** ***** 1 Jul 2012 20:39:25 ***** ******************************************************************************* ******************************************************************************* 878 . * female models 879 . forvalues j=3/3 { 2. 880 . set more off 3. des bf4 bf4m shfamw3 shrelaw3 avgcumdosew3 4. title "trimmed HP2sexlife main effects models" "wave 3 for H1 part 2 with > dose ns" 5. title "Wave 3 dose HP2sexlife relationship" "avgcumdosew`j' Dose not signi > f" 6. logit HP2sxlife age marrw31-marrw36 radhlw`j' bf4 bf4m /// > shfamw`j' shrelaw`j' avgcumdosew`j' if gender==2 7. estat class 8. estat gof 9. fitstat 10. } storage display value variable name type format label variable label ------------------------------------------------------------------------------- bf4 float %9.0g bf4 = max(0, 24 - BSIsoma) bf4m float %9.0g bf4m = max(0, 32 - BSIsoma) shfamw3 double %8.0g Percentage of strains and hassles related to family NOW shrelaw3 double %8.0g Percentage of strains and hassles related to relationships NOW avgcumdosew3 double %8.0g Avg Mean dose of CS137 ending 12/31/2009 ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** trimmed HP2sexlife main effects models ***** ***** wave 3 for H1 part 2 with dose ns ***** ***** ***** ***** ***** ***** 1 Jul 2012 20:39:25 ***** ******************************************************************************* ******************************************************************************* ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Wave 3 dose HP2sexlife relationship ***** ***** avgcumdosew3 Dose not signif ***** ***** ***** ***** ***** ***** 1 Jul 2012 20:39:25 ***** ******************************************************************************* ******************************************************************************* note: marrw36 omitted because of collinearity Iteration 0: log likelihood = -207.62116 Iteration 1: log likelihood = -144.17685 Iteration 2: log likelihood = -138.48259 Iteration 3: log likelihood = -138.36775 Iteration 4: log likelihood = -138.36738 Iteration 5: log likelihood = -138.36738 Logistic regression Number of obs = 363 LR chi2(12) = 138.51 Prob > chi2 = 0.0000 Log likelihood = -138.36738 Pseudo R2 = 0.3336 ------------------------------------------------------------------------------ HP2sxlife | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0754579 .0170423 4.43 0.000 .0420555 .1088603 marrw31 | -.9421212 .8010808 -1.18 0.240 -2.512211 .6279684 marrw32 | -.440823 1.344699 -0.33 0.743 -3.076384 2.194738 marrw33 | -.9501207 .4286832 -2.22 0.027 -1.790324 -.109917 marrw34 | -.9642797 1.745537 -0.55 0.581 -4.38547 2.45691 marrw35 | -.8586239 .6388872 -1.34 0.179 -2.11082 .393572 marrw36 | 0 (omitted) radhlw3 | .0100484 .0049263 2.04 0.041 .000393 .0197038 bf4 | -.5151847 .1744193 -2.95 0.003 -.8570402 -.1733292 bf4m | .3491023 .1586783 2.20 0.028 .0380985 .6601061 shfamw3 | .0106246 .0054177 1.96 0.050 6.14e-06 .0212431 shrelaw3 | -.0125055 .00593 -2.11 0.035 -.024128 -.0008829 avgcumdosew3 | .1255823 .0854354 1.47 0.142 -.0418679 .2930326 _cons | -6.549884 1.704204 -3.84 0.000 -9.890063 -3.209705 ------------------------------------------------------------------------------ Logistic model for HP2sxlife -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 57 16 | 73 - | 37 253 | 290 -----------+--------------------------+----------- Total | 94 269 | 363 Classified + if predicted Pr(D) >= .5 True D defined as HP2sxlife != 0 -------------------------------------------------- Sensitivity Pr( +| D) 60.64% Specificity Pr( -|~D) 94.05% Positive predictive value Pr( D| +) 78.08% Negative predictive value Pr(~D| -) 87.24% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 5.95% False - rate for true D Pr( -| D) 39.36% False + rate for classified + Pr(~D| +) 21.92% False - rate for classified - Pr( D| -) 12.76% -------------------------------------------------- Correctly classified 85.40% -------------------------------------------------- Logistic model for HP2sxlife, goodness-of-fit test number of observations = 363 number of covariate patterns = 362 Pearson chi2(349) = 482.36 Prob > chi2 = 0.0000 Measures of Fit for logit of HP2sxlife Log-Lik Intercept Only: -207.621 Log-Lik Full Model: -138.367 D(349): 276.735 LR(12): 138.508 Prob > LR: 0.000 McFadden's R2: 0.334 McFadden's Adj R2: 0.266 Maximum Likelihood R2: 0.317 Cragg & Uhler's R2: 0.466 McKelvey and Zavoina's R2: 0.500 Efron's R2: 0.407 Variance of y*: 6.573 Variance of error: 3.290 Count R2: 0.854 Adj Count R2: 0.436 AIC: 0.839 AIC*n: 304.735 BIC: -1780.412 BIC': -67.775 881 . scalar SigDoseSxlifeFw3 = "no" 882 . scalar MainEffsxlifeFw3 = "age marrw33 radhlw3 bf4 bf4m shrelaw3" 883 . *----- constructing possible moderators 884 . 885 . foreach var in marrw31 marrw32 marrw33 marrw34 marrw35 marrw36 /// > bf4 bf4m shfamw3 shrelaw3 radhlw3 { 2. cap gen `var'Xd3 = `var'*avgcumdosew3 3. } 886 . 887 . title "Chunk 7 trimmed female model:" "dose and HP2sxlife relationship in wav > e 3" ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Chunk 7 trimmed female model: ***** ***** dose and HP2sxlife relationship in wave 3 ***** ***** ***** ***** ***** ***** 1 Jul 2012 20:39:26 ***** ******************************************************************************* ******************************************************************************* 888 . * female models 889 . forvalues j=3/3 { 2. 890 . set more off 3. des bf4 bf4m shfamw3 shrelaw3 avgcumdosew3 4. title "trimmed HP2sexlife main effects models" "wave 3 for H1 part 2 with > dose ns" 5. title "Wave 3 dose HP2sexlife relationship" "avgcumdosew`j' Dose not signi > f" 6. logit HP2sxlife age marrw31-marrw36 radhlw`j' bf4 bf4m /// > shfamw`j' shrelaw`j' avgcumdosew`j' ageXd3 marrw31Xd3 marrw32Xd3 > /// > marrw33Xd3 marrw34Xd3 marrw35Xd3 bf4Xd3 bf4mXd3 shrelaw3Xd3 /// > if gender==2 7. estat class 8. estat gof 9. fitstat 10. } storage display value variable name type format label variable label ------------------------------------------------------------------------------- bf4 float %9.0g bf4 = max(0, 24 - BSIsoma) bf4m float %9.0g bf4m = max(0, 32 - BSIsoma) shfamw3 double %8.0g Percentage of strains and hassles related to family NOW shrelaw3 double %8.0g Percentage of strains and hassles related to relationships NOW avgcumdosew3 double %8.0g Avg Mean dose of CS137 ending 12/31/2009 ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** trimmed HP2sexlife main effects models ***** ***** wave 3 for H1 part 2 with dose ns ***** ***** ***** ***** ***** ***** 1 Jul 2012 20:39:26 ***** ******************************************************************************* ******************************************************************************* ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Wave 3 dose HP2sexlife relationship ***** ***** avgcumdosew3 Dose not signif ***** ***** ***** ***** ***** ***** 1 Jul 2012 20:39:26 ***** ******************************************************************************* ******************************************************************************* note: marrw36 omitted because of collinearity Iteration 0: log likelihood = -207.62116 Iteration 1: log likelihood = -141.7263 Iteration 2: log likelihood = -135.5357 Iteration 3: log likelihood = -135.21704 Iteration 4: log likelihood = -135.16073 Iteration 5: log likelihood = -135.14259 Iteration 6: log likelihood = -135.139 Iteration 7: log likelihood = -135.13799 Iteration 8: log likelihood = -135.13774 Iteration 9: log likelihood = -135.13769 Iteration 10: log likelihood = -135.13768 Logistic regression Number of obs = 363 LR chi2(21) = 144.97 Prob > chi2 = 0.0000 Log likelihood = -135.13768 Pseudo R2 = 0.3491 ------------------------------------------------------------------------------ HP2sxlife | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .092952 .0233865 3.97 0.000 .0471154 .1387886 marrw31 | -1.341334 1.898438 -0.71 0.480 -5.062204 2.379537 marrw32 | 2.268161 4.581638 0.50 0.621 -6.711685 11.24801 marrw33 | -.8067892 .6165677 -1.31 0.191 -2.01524 .4016614 marrw34 | -32.82787 1800.902 -0.02 0.985 -3562.53 3496.875 marrw35 | -.858144 1.080921 -0.79 0.427 -2.976711 1.260423 marrw36 | 0 (omitted) radhlw3 | .0109474 .0050586 2.16 0.030 .0010328 .0208621 bf4 | -.3690314 .3776717 -0.98 0.329 -1.109254 .3711915 bf4m | .245895 .3444988 0.71 0.475 -.4293101 .9211002 shfamw3 | .0116586 .005533 2.11 0.035 .0008141 .0225031 shrelaw3 | -.0021905 .0093988 -0.23 0.816 -.0206118 .0162308 avgcumdosew3 | 1.180905 2.36415 0.50 0.617 -3.452744 5.814553 ageXd3 | -.0203615 .0150978 -1.35 0.177 -.0499527 .0092297 marrw31Xd3 | .399261 1.599068 0.25 0.803 -2.734855 3.533377 marrw32Xd3 | -3.261172 5.78271 -0.56 0.573 -14.59508 8.072732 marrw33Xd3 | -.061554 .4565407 -0.13 0.893 -.9563573 .8332492 marrw34Xd3 | 17.30052 1074.65 0.02 0.987 -2088.975 2123.576 marrw35Xd3 | .0357107 .7782966 0.05 0.963 -1.489723 1.561144 bf4Xd3 | -.1255356 .3211828 -0.39 0.696 -.7550423 .5039711 bf4mXd3 | .0907915 .2884138 0.31 0.753 -.4744893 .6560722 shrelaw3Xd3 | -.0097172 .0069227 -1.40 0.160 -.0232854 .0038511 _cons | -7.579904 3.069205 -2.47 0.014 -13.59544 -1.564373 ------------------------------------------------------------------------------ Note: 4 failures and 0 successes completely determined. Logistic model for HP2sxlife -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 55 15 | 70 - | 39 254 | 293 -----------+--------------------------+----------- Total | 94 269 | 363 Classified + if predicted Pr(D) >= .5 True D defined as HP2sxlife != 0 -------------------------------------------------- Sensitivity Pr( +| D) 58.51% Specificity Pr( -|~D) 94.42% Positive predictive value Pr( D| +) 78.57% Negative predictive value Pr(~D| -) 86.69% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 5.58% False - rate for true D Pr( -| D) 41.49% False + rate for classified + Pr(~D| +) 21.43% False - rate for classified - Pr( D| -) 13.31% -------------------------------------------------- Correctly classified 85.12% -------------------------------------------------- Logistic model for HP2sxlife, goodness-of-fit test number of observations = 363 number of covariate patterns = 362 Pearson chi2(340) = 452.30 Prob > chi2 = 0.0000 Measures of Fit for logit of HP2sxlife Log-Lik Intercept Only: -207.621 Log-Lik Full Model: -135.138 D(340): 270.275 LR(21): 144.967 Prob > LR: 0.000 McFadden's R2: 0.349 McFadden's Adj R2: 0.238 Maximum Likelihood R2: 0.329 Cragg & Uhler's R2: 0.483 McKelvey and Zavoina's R2: 0.779 Efron's R2: 0.416 Variance of y*: 14.905 Variance of error: 3.290 Count R2: 0.851 Adj Count R2: 0.426 AIC: 0.871 AIC*n: 316.275 BIC: -1733.822 BIC': -21.185 891 . scalar sxlifeModFw3="none" 892 . 893 . 894 . 895 . 896 . *----- testing female moderators 897 . title "partly trimmed female moderator model of dose & HP2sxlife relationship > in wv 3" ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** *****partly trimmed female moderator model of dose & HP2sxlife relationship in > wv 3***** ***** ***** ***** ***** ***** 1 Jul 2012 20:39:28 ***** ******************************************************************************* ******************************************************************************* 898 . * male models 899 . forvalues j=3/3 { 2. set more off 3. des bf4 bf4m shfamw3 shrelaw3 avgcumdosew3 4. title3 "trimmed HP2sexlife main effects models wave 1 for H1 part 2 with d > ose ns" 5. title "Wave 3 dose HP2sexlife relationship but avgcumdosew`j': Dose not si > gnif" 6. logit HP2sxlife age marrw31-marrw36 radhlw`j' bf4 bf4m /// > shfamw`j' shrelaw`j' avgcumdosew`j' marrw31Xd3 marrw32Xd3 /// > marrw33Xd3 marrw34Xd3 marrw35Xd3 marrw36Xd3 radhlw`j'Xd3 /// > bf4Xd3 shfamw3Xd3 shrelaw3Xd3 if gender==2 7. estat class 8. estat gof 9. fitstat 10. } storage display value variable name type format label variable label ------------------------------------------------------------------------------- bf4 float %9.0g bf4 = max(0, 24 - BSIsoma) bf4m float %9.0g bf4m = max(0, 32 - BSIsoma) shfamw3 double %8.0g Percentage of strains and hassles related to family NOW shrelaw3 double %8.0g Percentage of strains and hassles related to relationships NOW avgcumdosew3 double %8.0g Avg Mean dose of CS137 ending 12/31/2009 ------------------------------------------------------------------------------- title3 : trimmed HP2sexlife main effects models wave 1 for H1 part 2 with dose > ns 1 Jul 2012 20:39:28 computer Macintosh (Intel 64-bit) folder /Users/robertyaffee/Documents/data/research/chwk/phase3/Htests/H1tests/ > h1pt2 Data file chwide1jul2012.dta currrently has 2402 variables and 703 observ > ations ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** *****Wave 3 dose HP2sexlife relationship but avgcumdosew3: Dose not signif***** ***** ***** ***** ***** ***** 1 Jul 2012 20:39:28 ***** ******************************************************************************* ******************************************************************************* note: marrw36 omitted because of collinearity note: marrw36Xd3 omitted because of collinearity Iteration 0: log likelihood = -207.62116 Iteration 1: log likelihood = -141.24621 Iteration 2: log likelihood = -135.45322 Iteration 3: log likelihood = -135.06483 Iteration 4: log likelihood = -134.9957 Iteration 5: log likelihood = -134.97466 Iteration 6: log likelihood = -134.9706 Iteration 7: log likelihood = -134.96946 Iteration 8: log likelihood = -134.96923 Iteration 9: log likelihood = -134.96917 Iteration 10: log likelihood = -134.96916 Iteration 11: log likelihood = -134.96915 Logistic regression Number of obs = 363 LR chi2(21) = 145.30 Prob > chi2 = 0.0000 Log likelihood = -134.96915 Pseudo R2 = 0.3499 ------------------------------------------------------------------------------ HP2sxlife | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0704827 .0174387 4.04 0.000 .0363034 .104662 marrw31 | -1.526734 1.875648 -0.81 0.416 -5.202936 2.149468 marrw32 | 1.103621 4.081036 0.27 0.787 -6.895063 9.102305 marrw33 | -.8740582 .7389686 -1.18 0.237 -2.32241 .5742937 marrw34 | -36.63611 3874.821 -0.01 0.992 -7631.146 7557.874 marrw35 | -1.152859 1.129412 -1.02 0.307 -3.366467 1.060749 marrw36 | 0 (omitted) radhlw3 | .0014141 .0096951 0.15 0.884 -.0175881 .0204162 bf4 | -.4636015 .1826527 -2.54 0.011 -.8215941 -.1056089 bf4m | .3302633 .1629809 2.03 0.043 .0108266 .6497 shfamw3 | .0067642 .0105079 0.64 0.520 -.0138309 .0273592 shrelaw3 | .0028404 .0117929 0.24 0.810 -.0202733 .0259542 avgcumdosew3 | -.2391157 1.08948 -0.22 0.826 -2.374458 1.896226 marrw31Xd3 | .5553424 1.593846 0.35 0.728 -2.568538 3.679223 marrw32Xd3 | -1.935909 5.073174 -0.38 0.703 -11.87915 8.007329 marrw33Xd3 | -.0368709 .6566922 -0.06 0.955 -1.323964 1.250222 marrw34Xd3 | 19.23126 2306.55 0.01 0.993 -4501.524 4539.987 marrw35Xd3 | .3214642 .8715872 0.37 0.712 -1.386815 2.029744 marrw36Xd3 | 0 (omitted) radhlw3Xd3 | .0091172 .0095954 0.95 0.342 -.0096893 .0279238 bf4Xd3 | -.0273194 .0643627 -0.42 0.671 -.1534679 .0988292 shfamw3Xd3 | .0037913 .0100871 0.38 0.707 -.015979 .0235616 shrelaw3Xd3 | -.0141156 .0103071 -1.37 0.171 -.0343171 .0060859 _cons | -5.898959 2.139999 -2.76 0.006 -10.09328 -1.704637 ------------------------------------------------------------------------------ Note: 6 failures and 0 successes completely determined. Logistic model for HP2sxlife -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 56 17 | 73 - | 38 252 | 290 -----------+--------------------------+----------- Total | 94 269 | 363 Classified + if predicted Pr(D) >= .5 True D defined as HP2sxlife != 0 -------------------------------------------------- Sensitivity Pr( +| D) 59.57% Specificity Pr( -|~D) 93.68% Positive predictive value Pr( D| +) 76.71% Negative predictive value Pr(~D| -) 86.90% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 6.32% False - rate for true D Pr( -| D) 40.43% False + rate for classified + Pr(~D| +) 23.29% False - rate for classified - Pr( D| -) 13.10% -------------------------------------------------- Correctly classified 84.85% -------------------------------------------------- Logistic model for HP2sxlife, goodness-of-fit test number of observations = 363 number of covariate patterns = 362 Pearson chi2(340) = 451.96 Prob > chi2 = 0.0000 Measures of Fit for logit of HP2sxlife Log-Lik Intercept Only: -207.621 Log-Lik Full Model: -134.969 D(339): 269.938 LR(21): 145.304 Prob > LR: 0.000 McFadden's R2: 0.350 McFadden's Adj R2: 0.234 Maximum Likelihood R2: 0.330 Cragg & Uhler's R2: 0.484 McKelvey and Zavoina's R2: 0.810 Efron's R2: 0.421 Variance of y*: 17.337 Variance of error: 3.290 Count R2: 0.848 Adj Count R2: 0.415 AIC: 0.876 AIC*n: 317.938 BIC: -1728.264 BIC': -21.522 900 . 901 . title "fully female moderator model of dose & HP2sxlife relationship in wv 3" > ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** *****fully female moderator model of dose & HP2sxlife relationship in wv 3***** ***** ***** ***** ***** ***** 1 Jul 2012 20:39:29 ***** ******************************************************************************* ******************************************************************************* 902 . title2 "Signif female dose main effect " ------------------------------------------------------------------------------- title2: Signif female dose main effect Date and time: 1 Jul 2012 20:39:29 Working directory: /Users/robertyaffee/ > Documents/data/research/chwk/phase3/Htests/H1tests/h1pt2 Stata data file: chwide1jul2012.dta ha > s 2402 variables and 703 observations Signif female dose main effect ------------------------------------------------------------------------------- 903 . 904 . * female models 905 . forvalues j=3/3 { 2. des bf4 bf4m shfamw3 shrelaw3 avgcumdosew3 3. title3 "trimmed HP2sexlife main effects models wave 1 for H1 part 2 with d > ose ns" 4. title "Wave 3 dose HP2sexlife relationship but avgcumdosew`j': Dose not si > gnif" 5. logit HP2sxlife age radhlw`j' bf4 bf4m /// > shrelaw3 shfamw`j' avgcumdosew`j' /// > shrelaw3Xd3 if gender==2 6. estat class 7. estat gof 8. fitstat 9. } storage display value variable name type format label variable label ------------------------------------------------------------------------------- bf4 float %9.0g bf4 = max(0, 24 - BSIsoma) bf4m float %9.0g bf4m = max(0, 32 - BSIsoma) shfamw3 double %8.0g Percentage of strains and hassles related to family NOW shrelaw3 double %8.0g Percentage of strains and hassles related to relationships NOW avgcumdosew3 double %8.0g Avg Mean dose of CS137 ending 12/31/2009 ------------------------------------------------------------------------------- title3 : trimmed HP2sexlife main effects models wave 1 for H1 part 2 with dose > ns 1 Jul 2012 20:39:29 computer Macintosh (Intel 64-bit) folder /Users/robertyaffee/Documents/data/research/chwk/phase3/Htests/H1tests/ > h1pt2 Data file chwide1jul2012.dta currrently has 2402 variables and 703 observ > ations ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** *****Wave 3 dose HP2sexlife relationship but avgcumdosew3: Dose not signif***** ***** ***** ***** ***** ***** 1 Jul 2012 20:39:29 ***** ******************************************************************************* ******************************************************************************* Iteration 0: log likelihood = -207.62116 Iteration 1: log likelihood = -144.9565 Iteration 2: log likelihood = -139.33502 Iteration 3: log likelihood = -139.24024 Iteration 4: log likelihood = -139.24007 Iteration 5: log likelihood = -139.24007 Logistic regression Number of obs = 363 LR chi2(8) = 136.76 Prob > chi2 = 0.0000 Log likelihood = -139.24007 Pseudo R2 = 0.3294 ------------------------------------------------------------------------------ HP2sxlife | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0850443 .0159459 5.33 0.000 .0537908 .1162978 radhlw3 | .0101855 .0048586 2.10 0.036 .0006629 .0197081 bf4 | -.5127452 .1800997 -2.85 0.004 -.8657342 -.1597562 bf4m | .3584755 .1654365 2.17 0.030 .034226 .682725 shrelaw3 | -.0011763 .0085087 -0.14 0.890 -.017853 .0155004 shfamw3 | .0102584 .0053613 1.91 0.056 -.0002495 .0207662 avgcumdosew3 | .4196812 .2507095 1.67 0.094 -.0717004 .9110629 shrelaw3Xd3 | -.0090959 .0060346 -1.51 0.132 -.0209235 .0027318 _cons | -8.337805 1.647879 -5.06 0.000 -11.56759 -5.108021 ------------------------------------------------------------------------------ Logistic model for HP2sxlife -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 53 21 | 74 - | 41 248 | 289 -----------+--------------------------+----------- Total | 94 269 | 363 Classified + if predicted Pr(D) >= .5 True D defined as HP2sxlife != 0 -------------------------------------------------- Sensitivity Pr( +| D) 56.38% Specificity Pr( -|~D) 92.19% Positive predictive value Pr( D| +) 71.62% Negative predictive value Pr(~D| -) 85.81% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 7.81% False - rate for true D Pr( -| D) 43.62% False + rate for classified + Pr(~D| +) 28.38% False - rate for classified - Pr( D| -) 14.19% -------------------------------------------------- Correctly classified 82.92% -------------------------------------------------- Logistic model for HP2sxlife, goodness-of-fit test number of observations = 363 number of covariate patterns = 362 Pearson chi2(353) = 444.64 Prob > chi2 = 0.0007 Measures of Fit for logit of HP2sxlife Log-Lik Intercept Only: -207.621 Log-Lik Full Model: -139.240 D(354): 278.480 LR(8): 136.762 Prob > LR: 0.000 McFadden's R2: 0.329 McFadden's Adj R2: 0.286 Maximum Likelihood R2: 0.314 Cragg & Uhler's R2: 0.461 McKelvey and Zavoina's R2: 0.509 Efron's R2: 0.394 Variance of y*: 6.704 Variance of error: 3.290 Count R2: 0.829 Adj Count R2: 0.340 AIC: 0.817 AIC*n: 296.480 BIC: -1808.138 BIC': -89.607 906 . * female models 907 . forvalues j=3/3 { 2. des bf4 bf4m shfamw3 shrelaw3 avgcumdosew3 3. title3 "trimmed HP2sexlife main effects models wave 1 for H1 part 2 with d > ose ns" 4. title "Wave 3 dose HP2sexlife relationship but avgcumdosew`j': Dose not si > gnif" 5. logit HP2sxlife age radhlw`j' bf4 bf4m /// > shrelaw3 shfamw`j' /// > if gender==2 6. estat class 7. estat gof 8. fitstat 9. } storage display value variable name type format label variable label ------------------------------------------------------------------------------- bf4 float %9.0g bf4 = max(0, 24 - BSIsoma) bf4m float %9.0g bf4m = max(0, 32 - BSIsoma) shfamw3 double %8.0g Percentage of strains and hassles related to family NOW shrelaw3 double %8.0g Percentage of strains and hassles related to relationships NOW avgcumdosew3 double %8.0g Avg Mean dose of CS137 ending 12/31/2009 ------------------------------------------------------------------------------- title3 : trimmed HP2sexlife main effects models wave 1 for H1 part 2 with dose > ns 1 Jul 2012 20:39:31 computer Macintosh (Intel 64-bit) folder /Users/robertyaffee/Documents/data/research/chwk/phase3/Htests/H1tests/ > h1pt2 Data file chwide1jul2012.dta currrently has 2402 variables and 703 observ > ations ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** *****Wave 3 dose HP2sexlife relationship but avgcumdosew3: Dose not signif***** ***** ***** ***** ***** ***** 1 Jul 2012 20:39:31 ***** ******************************************************************************* ******************************************************************************* Iteration 0: log likelihood = -207.62116 Iteration 1: log likelihood = -148.10457 Iteration 2: log likelihood = -142.10924 Iteration 3: log likelihood = -142.00423 Iteration 4: log likelihood = -142.00406 Iteration 5: log likelihood = -142.00406 Logistic regression Number of obs = 363 LR chi2(6) = 131.23 Prob > chi2 = 0.0000 Log likelihood = -142.00406 Pseudo R2 = 0.3160 ------------------------------------------------------------------------------ HP2sxlife | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0888985 .0158716 5.60 0.000 .0577907 .1200062 radhlw3 | .0104339 .0048228 2.16 0.031 .0009812 .0198865 bf4 | -.5221133 .1784046 -2.93 0.003 -.8717799 -.1724467 bf4m | .3612435 .1636356 2.21 0.027 .0405235 .6819635 shrelaw3 | -.0123377 .0056981 -2.17 0.030 -.0235058 -.0011696 shfamw3 | .0113877 .005213 2.18 0.029 .0011705 .0216049 _cons | -8.106812 1.61823 -5.01 0.000 -11.27848 -4.93514 ------------------------------------------------------------------------------ Logistic model for HP2sxlife -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 58 21 | 79 - | 36 248 | 284 -----------+--------------------------+----------- Total | 94 269 | 363 Classified + if predicted Pr(D) >= .5 True D defined as HP2sxlife != 0 -------------------------------------------------- Sensitivity Pr( +| D) 61.70% Specificity Pr( -|~D) 92.19% Positive predictive value Pr( D| +) 73.42% Negative predictive value Pr(~D| -) 87.32% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 7.81% False - rate for true D Pr( -| D) 38.30% False + rate for classified + Pr(~D| +) 26.58% False - rate for classified - Pr( D| -) 12.68% -------------------------------------------------- Correctly classified 84.30% -------------------------------------------------- Logistic model for HP2sxlife, goodness-of-fit test number of observations = 363 number of covariate patterns = 359 Pearson chi2(352) = 469.29 Prob > chi2 = 0.0000 Measures of Fit for logit of HP2sxlife Log-Lik Intercept Only: -207.621 Log-Lik Full Model: -142.004 D(356): 284.008 LR(6): 131.234 Prob > LR: 0.000 McFadden's R2: 0.316 McFadden's Adj R2: 0.282 Maximum Likelihood R2: 0.303 Cragg & Uhler's R2: 0.445 McKelvey and Zavoina's R2: 0.483 Efron's R2: 0.385 Variance of y*: 6.366 Variance of error: 3.290 Count R2: 0.843 Adj Count R2: 0.394 AIC: 0.821 AIC*n: 298.008 BIC: -1814.399 BIC': -95.868 908 . 909 . scalar MainEffsxlifeFw3 = "age radhlw3 bf4 bf4m shrelaw3 shfamw3" 910 . scalar SigDoseSxlifeFw3="no" 911 . * xx female main effects model: no sign dose main effect 912 . * xx 6 signif main effects 913 . * xx no moderator effects significant 914 . 915 . *----------- mediator models for Dose => sexlife impact 916 . 917 . di as input "testing possible sex life mediator effects for males" testing possible sex life mediator effects for males 918 . 919 . * age is a mediating effect for males for Dose=> sex life for men 920 . des bf4 bf4m storage display value variable name type format label variable label ------------------------------------------------------------------------------- bf4 float %9.0g bf4 = max(0, 24 - BSIsoma) bf4m float %9.0g bf4m = max(0, 32 - BSIsoma) 921 . glm age avgcumdosew3 if gender==1, fam(gaus) link(identity) Iteration 0: log likelihood = -1330.6336 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = 147.7142 Deviance = 49927.38549 (1/df) Deviance = 147.7142 Pearson = 49927.38549 (1/df) Pearson = 147.7142 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 7.839021 Log likelihood = -1330.633586 BIC = 47957.2 ------------------------------------------------------------------------------ | OIM age | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | .5433648 .2472657 2.20 0.028 .058733 1.027997 _cons | 48.52021 .7247376 66.95 0.000 47.09975 49.94067 ------------------------------------------------------------------------------ 922 . glm HP2sxlife age if gender==1, fam(bin) irls scale(dev) link(probit) Iteration 1: deviance = 287.05 Iteration 2: deviance = 282.9134 Iteration 3: deviance = 282.8157 Iteration 4: deviance = 282.8156 Iteration 5: deviance = 282.8156 Generalized linear models No. of obs = 340 Optimization : MQL Fisher scoring Residual df = 338 (IRLS EIM) Scale parameter = 1 Deviance = 282.8156218 (1/df) Deviance = .8367326 Pearson = 327.5643783 (1/df) Pearson = .9691254 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1687.368 ------------------------------------------------------------------------------ | EIM HP2sxlife | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0532907 .0067666 7.88 0.000 .0400283 .0665531 _cons | -3.620299 .3741324 -9.68 0.000 -4.353585 -2.887013 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 923 . 924 . * illness is a mediating effect for males = > sex life for men 925 . des illw3 storage display value variable name type format label variable label ------------------------------------------------------------------------------- illw3 double %8.0g Total number of illnesses experienced in time period 1996-NOW 926 . glm illw3 avgcumdosew3 if gender==1, fam(gaus) link(identity) Iteration 0: log likelihood = -461.99206 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = .8919217 Deviance = 301.469521 (1/df) Deviance = .8919217 Pearson = 301.469521 (1/df) Pearson = .8919217 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 2.729365 Log likelihood = -461.9920626 BIC = -1668.714 ------------------------------------------------------------------------------ | OIM illw3 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | .038211 .0192139 1.99 0.047 .0005524 .0758696 _cons | .4504952 .0563162 8.00 0.000 .3401176 .5608729 ------------------------------------------------------------------------------ 927 . glm HP2sxlife illw3 if gender==1, fam(bin) irls scale(dev) link(probit) Iteration 1: deviance = 314.6325 Iteration 2: deviance = 314.577 Iteration 3: deviance = 314.5769 Iteration 4: deviance = 314.5769 Generalized linear models No. of obs = 340 Optimization : MQL Fisher scoring Residual df = 338 (IRLS EIM) Scale parameter = 1 Deviance = 314.5769306 (1/df) Deviance = .930701 Pearson = 334.8347324 (1/df) Pearson = .9906353 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1655.607 ------------------------------------------------------------------------------ | EIM HP2sxlife | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- illw3 | .406576 .0768494 5.29 0.000 .2559539 .5571981 _cons | -1.080731 .0906035 -11.93 0.000 -1.258311 -.9031518 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 928 . 929 . des radhlw3 storage display value variable name type format label variable label ------------------------------------------------------------------------------- radhlw3 double %8.0g Self-perceived Chornobyl health threat in wave 3 930 . glm radhlw3 avgcumdosew3 if gender==1, fam(gaus) link(identity) Iteration 0: log likelihood = -1695.1855 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = 1261.052 Deviance = 426235.7205 (1/df) Deviance = 1261.052 Pearson = 426235.7205 (1/df) Pearson = 1261.052 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 9.983444 Log likelihood = -1695.185473 BIC = 424265.5 ------------------------------------------------------------------------------ | OIM radhlw3 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | .9606492 .7224692 1.33 0.184 -.4553645 2.376663 _cons | 46.19995 2.117563 21.82 0.000 42.0496 50.3503 ------------------------------------------------------------------------------ 931 . glm HP2sxlife radhlw3 if gender==1, fam(bin) irls scale(dev) link(probit) Iteration 1: deviance = 292.0816 Iteration 2: deviance = 288.766 Iteration 3: deviance = 288.7109 Iteration 4: deviance = 288.7109 Iteration 5: deviance = 288.7109 Generalized linear models No. of obs = 340 Optimization : MQL Fisher scoring Residual df = 338 (IRLS EIM) Scale parameter = 1 Deviance = 288.7109182 (1/df) Deviance = .8541743 Pearson = 337.697009 (1/df) Pearson = .9991036 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1681.473 ------------------------------------------------------------------------------ | EIM HP2sxlife | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- radhlw3 | .0170927 .0022806 7.49 0.000 .0126228 .0215625 _cons | -1.790621 .1598163 -11.20 0.000 -2.103856 -1.477387 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 932 . 933 . 934 . des bf4 storage display value variable name type format label variable label ------------------------------------------------------------------------------- bf4 float %9.0g bf4 = max(0, 24 - BSIsoma) 935 . glm bf4 avgcumdosew3 if gender==1, fam(gaus) link(identity) Iteration 0: log likelihood = -1027.1072 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = 24.77487 Deviance = 8373.906252 (1/df) Deviance = 24.77487 Pearson = 8373.906252 (1/df) Pearson = 24.77487 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 6.053572 Log likelihood = -1027.107224 BIC = 6403.723 ------------------------------------------------------------------------------ | OIM bf4 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | -.0357675 .1012648 -0.35 0.724 -.2342429 .1627078 _cons | 12.54064 .2968079 42.25 0.000 11.95891 13.12238 ------------------------------------------------------------------------------ 936 . glm HP2sxlife bf4 if gender==1, fam(bin) irls scale(dev) link(probit) Iteration 1: deviance = 265.0595 Iteration 2: deviance = 261.6959 Iteration 3: deviance = 261.6273 Iteration 4: deviance = 261.6271 Iteration 5: deviance = 261.6271 Generalized linear models No. of obs = 340 Optimization : MQL Fisher scoring Residual df = 338 (IRLS EIM) Scale parameter = 1 Deviance = 261.6270836 (1/df) Deviance = .7740446 Pearson = 301.9171445 (1/df) Pearson = .893246 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1708.557 ------------------------------------------------------------------------------ | EIM HP2sxlife | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- bf4 | -.1431725 .0149643 -9.57 0.000 -.172502 -.1138431 _cons | .7780696 .180124 4.32 0.000 .425033 1.131106 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 937 . 938 . des bf4m storage display value variable name type format label variable label ------------------------------------------------------------------------------- bf4m float %9.0g bf4m = max(0, 32 - BSIsoma) 939 . glm bf4m avgcumdosew3 if gender==1, fam(gaus) link(identity) Iteration 0: log likelihood = -1060.7697 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = 30.20008 Deviance = 10207.62832 (1/df) Deviance = 30.20008 Pearson = 10207.62832 (1/df) Pearson = 30.20008 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 6.251587 Log likelihood = -1060.769747 BIC = 8237.445 ------------------------------------------------------------------------------ | OIM bf4m | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | -.0292413 .1118039 -0.26 0.794 -.2483729 .1898903 _cons | 20.35328 .327698 62.11 0.000 19.711 20.99556 ------------------------------------------------------------------------------ 940 . glm HP2sxlife bf4m if gender==1, fam(bin) irls scale(dev) link(probit) Iteration 1: deviance = 266.1375 Iteration 2: deviance = 263.3205 Iteration 3: deviance = 263.273 Iteration 4: deviance = 263.2729 Iteration 5: deviance = 263.2729 Generalized linear models No. of obs = 340 Optimization : MQL Fisher scoring Residual df = 338 (IRLS EIM) Scale parameter = 1 Deviance = 263.2728985 (1/df) Deviance = .7789139 Pearson = 303.0162706 (1/df) Pearson = .8964978 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1706.911 ------------------------------------------------------------------------------ | EIM HP2sxlife | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- bf4m | -.1287243 .0140303 -9.17 0.000 -.1562231 -.1012255 _cons | 1.624944 .276779 5.87 0.000 1.082468 2.167421 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 941 . 942 . 943 . * age is a mediating effect for females for Dose=> sex life for women 944 . glm age avgcumdosew3 if gender==2, fam(gaus) link(identity) Iteration 0: log likelihood = -1408.064 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = 137.7687 Deviance = 49734.51399 (1/df) Deviance = 137.7687 Pearson = 49734.51399 (1/df) Pearson = 137.7687 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 7.768948 Log likelihood = -1408.06405 BIC = 47606.63 ------------------------------------------------------------------------------ | OIM age | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | 1.058366 .3512614 3.01 0.003 .3699069 1.746826 _cons | 48.94293 .7468173 65.54 0.000 47.47919 50.40666 ------------------------------------------------------------------------------ 945 . glm HP2sxlife age if gender==2, fam(bin) irls scale(dev) link(probit) Iteration 1: deviance = 336.5251 Iteration 2: deviance = 333.7638 Iteration 3: deviance = 333.7326 Iteration 4: deviance = 333.7326 Iteration 5: deviance = 333.7326 Generalized linear models No. of obs = 363 Optimization : MQL Fisher scoring Residual df = 361 (IRLS EIM) Scale parameter = 1 Deviance = 333.7325644 (1/df) Deviance = .9244669 Pearson = 379.4384762 (1/df) Pearson = 1.051076 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1794.147 ------------------------------------------------------------------------------ | EIM HP2sxlife | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0606116 .0071416 8.49 0.000 .0466144 .0746088 _cons | -3.838422 .3937027 -9.75 0.000 -4.610065 -3.066779 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 946 . 947 . * illness is a mediating effect for females = > sex life for men 948 . des illw3 storage display value variable name type format label variable label ------------------------------------------------------------------------------- illw3 double %8.0g Total number of illnesses experienced in time period 1996-NOW 949 . glm illw3 avgcumdosew3 if gender==2, fam(gaus) link(identity) Iteration 0: log likelihood = -562.81042 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = 1.308042 Deviance = 472.2033151 (1/df) Deviance = 1.308042 Pearson = 472.2033151 (1/df) Pearson = 1.308042 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 3.111903 Log likelihood = -562.8104237 BIC = -1655.676 ------------------------------------------------------------------------------ | OIM illw3 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | .1284565 .0342268 3.75 0.000 .0613733 .1955398 _cons | .5563644 .0727696 7.65 0.000 .4137387 .6989902 ------------------------------------------------------------------------------ 950 . glm HP2sxlife illw3 if gender==2, fam(bin) irls scale(dev) link(probit) Iteration 1: deviance = 400.2066 Iteration 2: deviance = 399.9405 Iteration 3: deviance = 399.9404 Iteration 4: deviance = 399.9404 Generalized linear models No. of obs = 363 Optimization : MQL Fisher scoring Residual df = 361 (IRLS EIM) Scale parameter = 1 Deviance = 399.9403905 (1/df) Deviance = 1.107868 Pearson = 359.3006709 (1/df) Pearson = .9952927 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1727.939 ------------------------------------------------------------------------------ | EIM HP2sxlife | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- illw3 | .2312781 .0622433 3.72 0.000 .1092835 .3532726 _cons | -.8313252 .0911599 -9.12 0.000 -1.009995 -.6526552 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 951 . 952 . des radhlw3 storage display value variable name type format label variable label ------------------------------------------------------------------------------- radhlw3 double %8.0g Self-perceived Chornobyl health threat in wave 3 953 . glm radhlw3 avgcumdosew3 if gender==2, fam(gaus) link(identity) Iteration 0: log likelihood = -1798.7074 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = 1185.454 Deviance = 427948.9522 (1/df) Deviance = 1185.454 Pearson = 427948.9522 (1/df) Pearson = 1185.454 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 9.921253 Log likelihood = -1798.707367 BIC = 425821.1 ------------------------------------------------------------------------------ | OIM radhlw3 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | 2.751602 1.03038 2.67 0.008 .7320943 4.77111 _cons | 57.70689 2.190692 26.34 0.000 53.41321 62.00057 ------------------------------------------------------------------------------ 954 . glm HP2sxlife radhlw3 if gender==2, fam(bin) irls scale(dev) link(probit) Iteration 1: deviance = 385.4256 Iteration 2: deviance = 385.0487 Iteration 3: deviance = 385.0486 Iteration 4: deviance = 385.0486 Generalized linear models No. of obs = 363 Optimization : MQL Fisher scoring Residual df = 361 (IRLS EIM) Scale parameter = 1 Deviance = 385.0485907 (1/df) Deviance = 1.066617 Pearson = 374.8310541 (1/df) Pearson = 1.038313 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1742.831 ------------------------------------------------------------------------------ | EIM HP2sxlife | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- radhlw3 | .0117559 .0023184 5.07 0.000 .0072119 .0162999 _cons | -1.417393 .1757229 -8.07 0.000 -1.761803 -1.072982 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 955 . 956 . des bf4 // soma recentered storage display value variable name type format label variable label ------------------------------------------------------------------------------- bf4 float %9.0g bf4 = max(0, 24 - BSIsoma) 957 . * bf4 is a mediting effect for females for Dose=> sex life for women 958 . glm bf4 avgcumdosew3 if gender==2, fam(gaus) link(identity) Iteration 0: log likelihood = -1109.6569 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = 26.6146 Deviance = 9607.869105 (1/df) Deviance = 26.6146 Pearson = 9607.869105 (1/df) Pearson = 26.6146 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 6.124831 Log likelihood = -1109.656873 BIC = 7479.99 ------------------------------------------------------------------------------ | OIM bf4 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | -.4386292 .1543885 -2.84 0.004 -.7412252 -.1360333 _cons | 11.01475 .3282456 33.56 0.000 10.3714 11.6581 ------------------------------------------------------------------------------ 959 . glm HP2sxlife bf4 if gender==2, fam(bin) irls scale(dev) link(probit) Iteration 1: deviance = 344.0399 Iteration 2: deviance = 342.6827 Iteration 3: deviance = 342.6686 Iteration 4: deviance = 342.6686 Iteration 5: deviance = 342.6686 Generalized linear models No. of obs = 363 Optimization : MQL Fisher scoring Residual df = 361 (IRLS EIM) Scale parameter = 1 Deviance = 342.6686152 (1/df) Deviance = .9492205 Pearson = 336.3540555 (1/df) Pearson = .9317287 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1785.211 ------------------------------------------------------------------------------ | EIM HP2sxlife | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- bf4 | -.1230087 .0148291 -8.30 0.000 -.1520732 -.0939442 _cons | .5134392 .1542351 3.33 0.001 .211144 .8157344 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 960 . 961 . des bf4m // soma recentered storage display value variable name type format label variable label ------------------------------------------------------------------------------- bf4m float %9.0g bf4m = max(0, 32 - BSIsoma) 962 . * bf4m is a possible mediating effect for female sex life 963 . glm bf4m avgcumdosew3 if gender==2, fam(gaus) link(identity) Iteration 0: log likelihood = -1141.3116 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = 31.68572 Deviance = 11438.54371 (1/df) Deviance = 31.68572 Pearson = 11438.54371 (1/df) Pearson = 31.68572 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 6.299237 Log likelihood = -1141.311602 BIC = 9310.664 ------------------------------------------------------------------------------ | OIM bf4m | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | -.441173 .1684561 -2.62 0.009 -.771341 -.1110051 _cons | 18.82772 .3581548 52.57 0.000 18.12575 19.52969 ------------------------------------------------------------------------------ 964 . glm HP2sxlife bf4m if gender==2, fam(bin) irls scale(dev) link(probit) Iteration 1: deviance = 356.1451 Iteration 2: deviance = 355.6209 Iteration 3: deviance = 355.6178 Iteration 4: deviance = 355.6178 Iteration 5: deviance = 355.6178 Generalized linear models No. of obs = 363 Optimization : MQL Fisher scoring Residual df = 361 (IRLS EIM) Scale parameter = 1 Deviance = 355.6178202 (1/df) Deviance = .9850909 Pearson = 340.0032816 (1/df) Pearson = .9418373 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1772.262 ------------------------------------------------------------------------------ | EIM HP2sxlife | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- bf4m | -.0990193 .0135516 -7.31 0.000 -.12558 -.0724586 _cons | 1.063679 .244399 4.35 0.000 .584666 1.542693 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 965 . 966 . des shfamw3 storage display value variable name type format label variable label ------------------------------------------------------------------------------- shfamw3 double %8.0g Percentage of strains and hassles related to family NOW 967 . glm shfamw3 avgcumdosew3 if gender==2, fam(gaus) link(identity) Iteration 0: log likelihood = -1798.0166 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = 1180.951 Deviance = 426323.4314 (1/df) Deviance = 1180.951 Pearson = 426323.4314 (1/df) Pearson = 1180.951 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 9.917447 Log likelihood = -1798.016645 BIC = 424195.6 ------------------------------------------------------------------------------ | OIM shfamw3 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | 3.038333 1.028421 2.95 0.003 1.022665 5.054002 _cons | 48.29894 2.186528 22.09 0.000 44.01342 52.58445 ------------------------------------------------------------------------------ 968 . glm HP2sxlife shfamw3 if gender==2, fam(bin) irls scale(dev) link(probit) Iteration 1: deviance = 412.3031 Iteration 2: deviance = 411.7515 Iteration 3: deviance = 411.7513 Iteration 4: deviance = 411.7513 Generalized linear models No. of obs = 363 Optimization : MQL Fisher scoring Residual df = 361 (IRLS EIM) Scale parameter = 1 Deviance = 411.7512965 (1/df) Deviance = 1.140585 Pearson = 363.5689973 (1/df) Pearson = 1.007116 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1716.128 ------------------------------------------------------------------------------ | EIM HP2sxlife | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- shfamw3 | .003818 .0022067 1.73 0.084 -.000507 .0081429 _cons | -.850427 .1417252 -6.00 0.000 -1.128203 -.5726507 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 969 . 970 . des shrelaw3 storage display value variable name type format label variable label ------------------------------------------------------------------------------- shrelaw3 double %8.0g Percentage of strains and hassles related to relationships NOW 971 . glm shrelaw3 avgcumdosew3 if gender==2, fam(gaus) link(identity) Iteration 0: log likelihood = -1781.6583 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = 1079.169 Deviance = 389580.0745 (1/df) Deviance = 1079.169 Pearson = 389580.0745 (1/df) Pearson = 1079.169 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 9.827318 Log likelihood = -1781.658257 BIC = 387452.2 ------------------------------------------------------------------------------ | OIM shrelaw3 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | .719866 .9831048 0.73 0.464 -1.206984 2.646716 _cons | 27.62247 2.09018 13.22 0.000 23.52579 31.71915 ------------------------------------------------------------------------------ 972 . glm HP2sxlife shrelaw3 if gender==2, fam(bin) irls scale(dev) link(probit) Iteration 1: deviance = 415.8457 Iteration 2: deviance = 415.1882 Iteration 3: deviance = 415.1879 Iteration 4: deviance = 415.1879 Generalized linear models No. of obs = 363 Optimization : MQL Fisher scoring Residual df = 361 (IRLS EIM) Scale parameter = 1 Deviance = 415.1879244 (1/df) Deviance = 1.150105 Pearson = 363.0035925 (1/df) Pearson = 1.00555 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1712.691 ------------------------------------------------------------------------------ | EIM HP2sxlife | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- shrelaw3 | .0005023 .0023156 0.22 0.828 -.0040363 .0050408 _cons | -.6609704 .101163 -6.53 0.000 -.8592462 -.4626947 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 973 . 974 . 975 . 976 . *xx summary of mediating effects: age and illness mediate sex life for men 977 . * age illnesss radhlw3 bf4 bf4m (soma) media > te sex life for women 978 . 979 . scalar sxlifeMedMw3 = "age illw3" 980 . scalar sxlifeMedFw3 = "age illw3 radhlw3 bf4 bf4m" 981 . title4 "5. summary matrix contstruction for dose -> sexlife impact" ------------------------------------------------------------------------------- 5. summary matrix contstruction for dose -> sexlife impact ------------------------------------------------------------------------------- 982 . 983 . matrix define HP2sxlifeMw3 = J(1,8, 0) 984 . matrix define HP2sxlifeFw3 = J(1,8, 0) 985 . matrix colnames HP2sxlifeMw3 = hypnum ptnum wave gender medsig numMAsig numM > odsig numMed 986 . matrix colnames HP2sxlifeFw3 = hypnum ptnum wave gender medsig numMA > sig numModsig numMed 987 . matrix define HP2sxlifeMw3 = (1, 2, 3, 1, 0, 4, 0, 2 ) 988 . matrix define HP2sxlifeFw3 = (1, 2, 3, 2, 1, 6, 0, 5) 989 . matrix rowname HP2sxlifeMw3 = HP2sxlifeMw3 990 . matrix rowname HP2sxlifeFw3 = HP2sxlifeFw3 991 . matlist HP2sxlifeMw3 | c1 c2 c3 c4 c5 c6 > -------------+----------------------------------------------------------------- - HP2sxlifeMw3 | 1 2 3 1 0 4 > | c7 c8 -------------+---------------------- HP2sxlifeMw3 | 0 2 992 . matlist HP2sxlifeFw3 | c1 c2 c3 c4 c5 c6 > -------------+----------------------------------------------------------------- - HP2sxlifeFw3 | 1 2 3 2 1 6 > | c7 c8 -------------+---------------------- HP2sxlifeFw3 | 0 5 993 . matrix define H1pt2w3 = ( HP2wkMw3 \ HP2wkFw3 \ HP2hmcrMw3 \ HP2hmcrFw3 \ HP2 > spMw3 \ HP2spFw3 \ HP2prbfamMw3 \ HP2prbfamFw3 \ HP2sxlifeMw3 \ HP2sxlifeFw3 > ) 994 . 995 . matlist H1pt2w3 | c1 c2 c3 c4 c5 c6 > -------------+----------------------------------------------------------------- - r1 | 1 2 3 1 0 4 > r1 | 1 2 3 2 0 1 > r1 | 1 2 3 1 0 4 > r1 | 1 2 3 2 0 2 > HP2spMw3 | 1 2 3 1 0 2 > HP2spFw3 | 1 2 3 2 1 5 > HP2prbfamM | 1 2 3 1 0 5 > HP2prbfamF | 1 2 3 2 0 2 > HP2sxlifeMw3 | 1 2 3 1 0 4 > HP2sxlifeFw3 | 1 2 3 2 1 6 > | c7 c8 -------------+---------------------- r1 | 0 4 r1 | 0 6 r1 | 0 2 r1 | 0 2 HP2spMw3 | 0 1 HP2spFw3 | 5 3 HP2prbfamM | 0 1 HP2prbfamF | 2 2 HP2sxlifeMw3 | 0 2 HP2sxlifeFw3 | 0 5 996 . matrix colnames H1pt2w3 = hypnum ptnum wave gender medsig numMAsig numMo > dsig numMed 997 . matrix rownames H1pt2w3 = HP2wkMw3 HP2wkFw3 HP2hmcrMw3 HP2hmcrFw3 HP2pr > bfhmMw3 HP2prbfhmFw3 998 . matlist H1pt2w3 | hypnum ptnum wave gender medsig numMAsig > -------------+----------------------------------------------------------------- - HP2wkMw3 | 1 2 3 1 0 4 > HP2wkFw3 | 1 2 3 2 0 1 > HP2hmcrMw3 | 1 2 3 1 0 4 > HP2hmcrFw3 | 1 2 3 2 0 2 > HP2prbfhmMw3 | 1 2 3 1 0 2 > HP2prbfhmFw3 | 1 2 3 2 1 5 > HP2prbfhmFw3 | 1 2 3 1 0 5 > HP2prbfhmFw3 | 1 2 3 2 0 2 > HP2prbfhmFw3 | 1 2 3 1 0 4 > HP2prbfhmFw3 | 1 2 3 2 1 6 > | numModsig numMed -------------+---------------------- HP2wkMw3 | 0 4 HP2wkFw3 | 0 6 HP2hmcrMw3 | 0 2 HP2hmcrFw3 | 0 2 HP2prbfhmMw3 | 0 1 HP2prbfhmFw3 | 5 3 HP2prbfhmFw3 | 0 1 HP2prbfhmFw3 | 2 2 HP2prbfhmFw3 | 0 2 HP2prbfhmFw3 | 0 5 999 . 1000 . 1001 . 1002 . 1003 . *=================== Chunk 8 Dose => interests and Hobbies relationship 1004 . title "6. Moderators and Mediators of the Dose = > interests and hobbies Imp > act" ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** *****6. Moderators and Mediators of the Dose = > interests and hobbies Impact** > *** ***** ***** ***** ***** ***** 1 Jul 2012 20:40:05 ***** ******************************************************************************* ******************************************************************************* 1005 . 1006 . title4 " Hyp. 1. pt 2 Wave 3 Main effects Dose=> Interests and Hobbies impact > identification" ------------------------------------------------------------------------------- Hyp. 1. pt 2 Wave 3 Main effects Dose=> Interests and Hobbies impact identific > ation ------------------------------------------------------------------------------- 1007 . 1008 . * Chunk 8 ---male models 1009 . forvalues j=3/3 { 2. set more off 3. 1010 . des age educ1-educ7 marrw`j'1-marrw`j'6 inc1w`j'-inc4w`j' /// > bf1 bf4 bf9 bf11 bf4m bf15m bf30 bf40 4. 1011 . foreach var in HP2inthob { 5. forvalues k=1/2 { 6. local w3bf bf1 bf4 bf2 bf4m bf5m bf7m bf8 bf15m bf17 bf20 bf22 bf29 bf30 b > f40 7. 1012 . di as input "Full main model for `var' for wave= `j' " 8. di _skip(4) 9. di as input "chunk 8 H1 test:Gender= `k' model Wave = `j' for `e(depvar > )' " 10. di _skip(4) 11. title "Full Nottingham Part 2 subscale models for male and then females" 12. di as input "Model for gender==`k' and wave == `j'" 13. di _skip(2) 14. xi: logistic `var' age i.educ occ1w`j'-occ8w`j' /// > marrw`j'1- marrw`j'3 marrw`j'5-marrw`j'6 inc1w`j'-inc4w`j' // > / > radhlw`j' havmil avgcumdosew`j' `w`j'bf' /// > deaw`j' dvcew`j' sepaw`j' accdw`j' movew`j' /// > illw`j' shfamw`j' shhlw`j' shjobw`j' shrelaw`j' suprtw`j' suc > hrw`j' /// > havmilsq radhlw3 if gender==`k', coef nolog difficult itera > te(50) 15. estat class 16. estat gof 17. fitstat 18. } 19. } 20. } storage display value variable name type format label variable label ------------------------------------------------------------------------------- age double %8.0g * Respondent's age educ1 byte %8.0g educ==1. did not graduate high school educ2 byte %8.0g educ==2. graduated high school educ3 byte %8.0g educ==3. technical degree educ4 byte %8.0g educ==4. did not finish college/bachelor's educ5 byte %8.0g educ==5. graduated college/bachelor's educ6 byte %8.0g educ==6. finished specialist/master's degree educ7 byte %8.0g educ==7. doctor of science/phd marrw31 byte %8.0g marrw3==1. single marrw32 byte %8.0g marrw3==2. cohabitating marrw33 byte %8.0g marrw3==3. married marrw34 byte %8.0g marrw3==4. separated marrw35 byte %8.0g marrw3==5. divorced marrw36 byte %8.0g marrw3==6. widowed inc1w3 double %15.0g LABJ Income is not sufficient for basic neccessities NOW inc2w3 double %15.0g LABJ Income is just sufficient for basic neccessities NOW inc3w3 double %15.0g LABJ Income is sufficient for basics plus extra purchases/savings NOW inc4w3 double %15.0g LABJ Income allows to comfortably afford luxury items NOW bf1 float %9.0g bf1 = max(0, kzchorn - 40) bf4 float %9.0g bf4 = max(0, 24 - BSIsoma) bf9 float %9.0g bf9= max(0, 30 - shhlw1) bf11 float %9.0g bf11= max(0, 20 - sufamw1) bf4m float %9.0g bf4m = max(0, 32 - BSIsoma) bf15m float %9.0g bf15m= max(0, 1 - icdxcnt) * bf2 bf30 float %9.0g bf30 = max(0, neiw1 - 85) * bf20 bf40 float %9.0g bf40 = max(0, icdxcnt - 1.01635E-007) Full main model for HP2inthob for wave= 3 chunk 8 H1 test:Gender= 1 model Wave = 3 for HP2sxlife ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Full Nottingham Part 2 subscale models for male and then females ***** ***** ***** ***** ***** ***** 1 Jul 2012 20:40:05 ***** ******************************************************************************* ******************************************************************************* Model for gender==1 and wave == 3 i.educ _Ieduc_1-8 (naturally coded; _Ieduc_1 omitted) note: _Ieduc_4 != 0 predicts failure perfectly _Ieduc_4 dropped and 14 obs not used note: _Ieduc_7 != 0 predicts failure perfectly _Ieduc_7 dropped and 4 obs not used note: _Ieduc_8 != 0 predicts failure perfectly _Ieduc_8 dropped and 2 obs not used note: occ5w3 != 0 predicts failure perfectly occ5w3 dropped and 15 obs not used note: occ6w3 != 0 predicts failure perfectly occ6w3 dropped and 4 obs not used note: bf15m != 0 predicts failure perfectly bf15m dropped and 18 obs not used note: bf29 != 0 predicts failure perfectly bf29 dropped and 7 obs not used note: _Ieduc_6 omitted because of collinearity note: occ8w3 omitted because of collinearity note: marrw36 omitted because of collinearity note: bf17 omitted because of collinearity note: radhlw3 omitted because of collinearity convergence not achieved Logistic regression Number of obs = 276 LR chi2(42) = 117.91 Prob > chi2 = 0.0000 Log likelihood = -51.649162 Pseudo R2 = 0.5330 ------------------------------------------------------------------------------ HP2inthob | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0817005 .0490304 1.67 0.096 -.0143972 .1777983 _Ieduc_2 | -1.531634 1.790651 -0.86 0.392 -5.041245 1.977977 _Ieduc_3 | -1.560462 .8580327 -1.82 0.069 -3.242176 .1212508 _Ieduc_4 | 0 (omitted) _Ieduc_5 | -.5489736 .8124194 -0.68 0.499 -2.141286 1.043339 _Ieduc_6 | 0 (omitted) _Ieduc_7 | 0 (omitted) _Ieduc_8 | 0 (omitted) occ1w3 | -16.51737 2.253408 -7.33 0.000 -20.93397 -12.10077 occ2w3 | -19.33038 2.062721 -9.37 0.000 -23.37324 -15.28752 occ3w3 | -17.4588 2.676679 -6.52 0.000 -22.70499 -12.2126 occ4w3 | -16.4147 2.207406 -7.44 0.000 -20.74113 -12.08826 occ5w3 | 0 (omitted) occ6w3 | 0 (omitted) occ7w3 | -16.18451 2.199404 -7.36 0.000 -20.49527 -11.87376 occ8w3 | 0 (omitted) marrw31 | .8557338 1.989444 0.43 0.667 -3.043506 4.754973 marrw32 | 1.067638 2.133137 0.50 0.617 -3.113233 5.248509 marrw33 | -.0597494 1.809944 -0.03 0.974 -3.607174 3.487675 marrw35 | 4.178796 2.178555 1.92 0.055 -.091092 8.448685 marrw36 | 0 (omitted) inc1w3 | 14.99624 2.039372 7.35 0.000 10.99915 18.99334 inc2w3 | 15.54638 1.847372 8.42 0.000 11.92559 19.16716 inc3w3 | 16.08957 1.659414 9.70 0.000 12.83718 19.34196 inc4w3 | 20.06926 . . . . . radhlw3 | .0608448 .0162567 3.74 0.000 .0289822 .0927074 havmil | .004278 .0106932 0.40 0.689 -.0166802 .0252362 avgcumdosew3 | -.3594081 .1656258 -2.17 0.030 -.6840288 -.0347874 bf1 | -1.832947 .1402107 -13.07 0.000 -2.107755 -1.558139 bf4 | -.1459909 .3386475 -0.43 0.666 -.8097278 .5177459 bf2 | -.0007134 .0002919 -2.44 0.015 -.0012855 -.0001412 bf4m | -.0648788 .3169386 -0.20 0.838 -.6860671 .5563094 bf5m | -.0059221 .0033107 -1.79 0.074 -.0124109 .0005667 bf7m | -.00068 .0010134 -0.67 0.502 -.0026661 .0013062 bf8 | .0000248 .0000707 0.35 0.726 -.0001137 .0001633 bf15m | 0 (omitted) bf17 | 0 (omitted) bf20 | 1.839453 .1331884 13.81 0.000 1.578408 2.100497 bf22 | .000278 .0003035 0.92 0.360 -.0003168 .0008728 bf29 | 0 (omitted) bf30 | .0006467 .000603 1.07 0.284 -.0005352 .0018286 bf40 | .2996033 .3950361 0.76 0.448 -.4746533 1.07386 deaw3 | -.6086988 .5212369 -1.17 0.243 -1.630304 .4129068 dvcew3 | -.2319255 1.621511 -0.14 0.886 -3.410029 2.946178 sepaw3 | -1.758194 2.087814 -0.84 0.400 -5.850234 2.333846 accdw3 | .9189185 1.049895 0.88 0.381 -1.138839 2.976676 movew3 | -1.391188 1.335043 -1.04 0.297 -4.007824 1.225448 illw3 | -.3817302 .3999312 -0.95 0.340 -1.165581 .4021205 shfamw3 | .0654585 .0176224 3.71 0.000 .0309192 .0999978 shhlw3 | -.0105181 .0103515 -1.02 0.310 -.0308067 .0097705 shjobw3 | -.0144707 .0115767 -1.25 0.211 -.0371606 .0082192 shrelaw3 | -.0392022 .0137786 -2.85 0.004 -.0662077 -.0121967 suprtw3 | .0070974 .0130297 0.54 0.586 -.0184403 .0326352 suchrw3 | -.00232 .0110986 -0.21 0.834 -.0240728 .0194327 havmilsq | -7.67e-06 .0000192 -0.40 0.690 -.0000453 .00003 radhlw3 | 0 (omitted) _cons | -80.28913 . . . . . ------------------------------------------------------------------------------ Note: 32 failures and 0 successes completely determined. Warning: convergence not achieved Logistic model for HP2inthob -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 23 7 | 30 - | 15 231 | 246 -----------+--------------------------+----------- Total | 38 238 | 276 Classified + if predicted Pr(D) >= .5 True D defined as HP2inthob != 0 -------------------------------------------------- Sensitivity Pr( +| D) 60.53% Specificity Pr( -|~D) 97.06% Positive predictive value Pr( D| +) 76.67% Negative predictive value Pr(~D| -) 93.90% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 2.94% False - rate for true D Pr( -| D) 39.47% False + rate for classified + Pr(~D| +) 23.33% False - rate for classified - Pr( D| -) 6.10% -------------------------------------------------- Correctly classified 92.03% -------------------------------------------------- Logistic model for HP2inthob, goodness-of-fit test number of observations = 276 number of covariate patterns = 276 Pearson chi2(231) = 123.26 Prob > chi2 = 1.0000 Measures of Fit for logistic of HP2inthob Log-Lik Intercept Only: -110.602 Log-Lik Full Model: -51.649 D(219): 103.298 LR(42): 117.906 Prob > LR: 0.000 McFadden's R2: 0.533 McFadden's Adj R2: 0.018 Maximum Likelihood R2: 0.348 Cragg & Uhler's R2: 0.631 McKelvey and Zavoina's R2: 0.982 Efron's R2: 0.500 Variance of y*: 180.636 Variance of error: 3.290 Count R2: 0.920 Adj Count R2: 0.421 AIC: 0.787 AIC*n: 217.298 BIC: -1127.569 BIC': 118.151 Full main model for HP2inthob for wave= 3 chunk 8 H1 test:Gender= 2 model Wave = 3 for HP2inthob ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Full Nottingham Part 2 subscale models for male and then females ***** ***** ***** ***** ***** ***** 1 Jul 2012 20:40:07 ***** ******************************************************************************* ******************************************************************************* Model for gender==2 and wave == 3 i.educ _Ieduc_1-8 (naturally coded; _Ieduc_1 omitted) note: occ4w3 != 0 predicts failure perfectly occ4w3 dropped and 8 obs not used note: occ5w3 != 0 predicts failure perfectly occ5w3 dropped and 5 obs not used note: occ8w3 != 0 predicts failure perfectly occ8w3 dropped and 1 obs not used note: bf15m != 0 predicts failure perfectly bf15m dropped and 11 obs not used note: _Ieduc_8 omitted because of collinearity note: bf17 omitted because of collinearity note: radhlw3 omitted because of collinearity Logistic regression Number of obs = 337 LR chi2(49) = 118.21 Prob > chi2 = 0.0000 Log likelihood = -107.57156 Pseudo R2 = 0.3546 ------------------------------------------------------------------------------ HP2inthob | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0683881 .0247447 2.76 0.006 .0198893 .1168869 _Ieduc_2 | -13.79024 962.4068 -0.01 0.989 -1900.073 1872.492 _Ieduc_3 | -12.92792 962.4068 -0.01 0.989 -1899.211 1873.355 _Ieduc_4 | -12.05387 962.4069 -0.01 0.990 -1898.337 1874.229 _Ieduc_5 | -12.19345 962.407 -0.01 0.990 -1898.476 1874.09 _Ieduc_6 | -13.09489 962.4068 -0.01 0.989 -1899.378 1873.188 _Ieduc_7 | -13.1998 962.4102 -0.01 0.989 -1899.489 1873.089 _Ieduc_8 | 0 (omitted) occ1w3 | -1.2723 3.511631 -0.36 0.717 -8.154969 5.61037 occ2w3 | -2.590551 3.713618 -0.70 0.485 -9.869108 4.688006 occ3w3 | -.8635752 3.536644 -0.24 0.807 -7.79527 6.06812 occ4w3 | 0 (omitted) occ5w3 | 0 (omitted) occ6w3 | -.2036246 3.739879 -0.05 0.957 -7.533652 7.126403 occ7w3 | -.4066434 3.50728 -0.12 0.908 -7.280786 6.467499 occ8w3 | 0 (omitted) marrw31 | -2.820802 1.835568 -1.54 0.124 -6.418449 .776846 marrw32 | -2.10882 2.397053 -0.88 0.379 -6.806958 2.589318 marrw33 | -2.047151 1.625637 -1.26 0.208 -5.233341 1.13904 marrw35 | -2.933509 1.682447 -1.74 0.081 -6.231043 .3640262 marrw36 | -2.100943 1.718745 -1.22 0.222 -5.469621 1.267736 inc1w3 | 1.771469 3.538577 0.50 0.617 -5.164014 8.706952 inc2w3 | 1.229926 3.52319 0.35 0.727 -5.675399 8.13525 inc3w3 | 1.602207 3.508288 0.46 0.648 -5.273911 8.478326 inc4w3 | 2.650063 3.832399 0.69 0.489 -4.861301 10.16143 radhlw3 | .0254128 .010363 2.45 0.014 .0051018 .0457239 havmil | .0052121 .0043654 1.19 0.232 -.003344 .0137682 avgcumdosew3 | .0592875 .0898505 0.66 0.509 -.1168163 .2353913 bf1 | -.0386178 .0465636 -0.83 0.407 -.1298807 .0526452 bf4 | -.3299735 .2318908 -1.42 0.155 -.7844712 .1245242 bf2 | 5.14e-06 .0001261 0.04 0.967 -.000242 .0002523 bf4m | .24058 .2177227 1.10 0.269 -.1861487 .6673088 bf5m | -.0019924 .0019912 -1.00 0.317 -.0058951 .0019104 bf7m | -.000918 .0006896 -1.33 0.183 -.0022697 .0004336 bf8 | 6.91e-06 .0000428 0.16 0.872 -.0000771 .0000909 bf15m | 0 (omitted) bf17 | 0 (omitted) bf20 | .0290415 .0410365 0.71 0.479 -.0513885 .1094715 bf22 | .000145 .000139 1.04 0.297 -.0001275 .0004175 bf29 | .0000291 .0000389 0.75 0.455 -.0000472 .0001054 bf30 | .0005863 .0003477 1.69 0.092 -.0000953 .0012679 bf40 | -.1903404 .1540477 -1.24 0.217 -.4922683 .1115876 deaw3 | -.0727208 .201017 -0.36 0.718 -.4667069 .3212652 dvcew3 | -.3675995 .8921998 -0.41 0.680 -2.116279 1.38108 sepaw3 | 1.146748 .9391994 1.22 0.222 -.6940491 2.987545 accdw3 | -.0400125 .5697822 -0.07 0.944 -1.156765 1.07674 movew3 | .1242816 1.400684 0.09 0.929 -2.621008 2.869572 illw3 | .0326786 .1772251 0.18 0.854 -.3146761 .3800333 shfamw3 | -.0089451 .0081686 -1.10 0.273 -.0249552 .0070651 shhlw3 | -.0019331 .0067351 -0.29 0.774 -.0151336 .0112673 shjobw3 | .0022608 .0074164 0.30 0.760 -.012275 .0167966 shrelaw3 | .0045217 .0078937 0.57 0.567 -.0109497 .0199931 suprtw3 | -.0034378 .0085075 -0.40 0.686 -.0201123 .0132366 suchrw3 | -.0106093 .0056039 -1.89 0.058 -.0215928 .0003741 havmilsq | -4.33e-06 6.65e-06 -0.65 0.515 -.0000174 8.70e-06 radhlw3 | 0 (omitted) _cons | 7.330327 962.4125 0.01 0.994 -1878.964 1893.624 ------------------------------------------------------------------------------ Note: 1 failure and 0 successes completely determined. Logistic model for HP2inthob -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 33 12 | 45 - | 33 259 | 292 -----------+--------------------------+----------- Total | 66 271 | 337 Classified + if predicted Pr(D) >= .5 True D defined as HP2inthob != 0 -------------------------------------------------- Sensitivity Pr( +| D) 50.00% Specificity Pr( -|~D) 95.57% Positive predictive value Pr( D| +) 73.33% Negative predictive value Pr(~D| -) 88.70% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 4.43% False - rate for true D Pr( -| D) 50.00% False + rate for classified + Pr(~D| +) 26.67% False - rate for classified - Pr( D| -) 11.30% -------------------------------------------------- Correctly classified 86.65% -------------------------------------------------- Logistic model for HP2inthob, goodness-of-fit test number of observations = 337 number of covariate patterns = 337 Pearson chi2(287) = 317.53 Prob > chi2 = 0.1040 Measures of Fit for logistic of HP2inthob Log-Lik Intercept Only: -166.677 Log-Lik Full Model: -107.572 D(280): 215.143 LR(49): 118.210 Prob > LR: 0.000 McFadden's R2: 0.355 McFadden's Adj R2: 0.013 Maximum Likelihood R2: 0.296 Cragg & Uhler's R2: 0.471 McKelvey and Zavoina's R2: 0.678 Efron's R2: 0.373 Variance of y*: 10.209 Variance of error: 3.290 Count R2: 0.866 Adj Count R2: 0.318 AIC: 0.977 AIC*n: 329.143 BIC: -1414.480 BIC': 166.974 1013 . 1014 . label var radhlw3 "Self-perceived Chornobyl health threat in wave 3" 1015 . 1016 . title4 "6. trimmed Moderators of male Dose => Interests and Hobbies Impact" ------------------------------------------------------------------------------- 6. trimmed Moderators of male Dose => Interests and Hobbies Impact ------------------------------------------------------------------------------- 1017 . 1018 . di as input "Wave 3 Main effects Dose=> Interests and Hobbies impact identifi > cation" Wave 3 Main effects Dose=> Interests and Hobbies impact identification 1019 . forvalues j=3/3 { 2. set more off 3. 1020 . des age educ1-educ7 marrw`j'1-marrw`j'6 inc1w`j'-inc4w`j' /// > bf1 bf4 bf9 bf11 bf4m bf15m bf30 bf40 4. 1021 . foreach var in HP2inthob { 5. local w3bf bf1 bf4 bf2 bf4m bf5m bf7m bf8 bf15m bf17 bf20 bf22 bf29 bf30 b > f40 6. di _skip(2) 7. di as input "Full main model for `var' for wave= `j' " 8. di _skip(4) 9. di as input "chunk 8 H1 test:Gender= male model Wave = `j' for `e(depva > r)' " 10. di _skip(4) 11. title "Full Nottingham Part 2 subscale models " "males on wave=`j'" 12. des bf5m shfamw3 radhlw3 bf4m 13. xi: logistic `var' age radhlw3 avgcumdosew3 shfamw3 /// > bf5m if gender==1, coef nolog difficult iterate(50) 14. estat class 15. estat gof 16. fitstat 17. di _skip(2) 18. di as input "Note: bf4m is necssary for bf5 but if bf4m is in model bf5 is > not signif." 19. di as input " Therefore, bf5 is not deemed significant." 20. } 21. } storage display value variable name type format label variable label ------------------------------------------------------------------------------- age double %8.0g * Respondent's age educ1 byte %8.0g educ==1. did not graduate high school educ2 byte %8.0g educ==2. graduated high school educ3 byte %8.0g educ==3. technical degree educ4 byte %8.0g educ==4. did not finish college/bachelor's educ5 byte %8.0g educ==5. graduated college/bachelor's educ6 byte %8.0g educ==6. finished specialist/master's degree educ7 byte %8.0g educ==7. doctor of science/phd marrw31 byte %8.0g marrw3==1. single marrw32 byte %8.0g marrw3==2. cohabitating marrw33 byte %8.0g marrw3==3. married marrw34 byte %8.0g marrw3==4. separated marrw35 byte %8.0g marrw3==5. divorced marrw36 byte %8.0g marrw3==6. widowed inc1w3 double %15.0g LABJ Income is not sufficient for basic neccessities NOW inc2w3 double %15.0g LABJ Income is just sufficient for basic neccessities NOW inc3w3 double %15.0g LABJ Income is sufficient for basics plus extra purchases/savings NOW inc4w3 double %15.0g LABJ Income allows to comfortably afford luxury items NOW bf1 float %9.0g bf1 = max(0, kzchorn - 40) bf4 float %9.0g bf4 = max(0, 24 - BSIsoma) bf9 float %9.0g bf9= max(0, 30 - shhlw1) bf11 float %9.0g bf11= max(0, 20 - sufamw1) bf4m float %9.0g bf4m = max(0, 32 - BSIsoma) bf15m float %9.0g bf15m= max(0, 1 - icdxcnt) * bf2 bf30 float %9.0g bf30 = max(0, neiw1 - 85) * bf20 bf40 float %9.0g bf40 = max(0, icdxcnt - 1.01635E-007) Full main model for HP2inthob for wave= 3 chunk 8 H1 test:Gender= male model Wave = 3 for HP2inthob ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Full Nottingham Part 2 subscale models ***** ***** males on wave=3 ***** ***** ***** ***** ***** ***** 1 Jul 2012 20:40:09 ***** ******************************************************************************* ******************************************************************************* storage display value variable name type format label variable label ------------------------------------------------------------------------------- bf5m float %9.0g bf5m = max(0, ecprw3 - 75) * bf4m shfamw3 double %8.0g Percentage of strains and hassles related to family NOW radhlw3 double %8.0g Self-perceived Chornobyl health threat in wave 3 bf4m float %9.0g bf4m = max(0, 32 - BSIsoma) Logistic regression Number of obs = 340 LR chi2(5) = 68.96 Prob > chi2 = 0.0000 Log likelihood = -84.583465 Pseudo R2 = 0.2896 ------------------------------------------------------------------------------ HP2inthob | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0503393 .0177324 2.84 0.005 .0155844 .0850941 radhlw3 | .036284 .0076652 4.73 0.000 .0212606 .0513075 avgcumdosew3 | -.1055965 .1287622 -0.82 0.412 -.3579659 .1467728 shfamw3 | .015864 .0063173 2.51 0.012 .0034822 .0282458 bf5m | -.002198 .001127 -1.95 0.051 -.0044068 .0000109 _cons | -7.784484 1.20097 -6.48 0.000 -10.13834 -5.430625 ------------------------------------------------------------------------------ Logistic model for HP2inthob -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 11 6 | 17 - | 27 296 | 323 -----------+--------------------------+----------- Total | 38 302 | 340 Classified + if predicted Pr(D) >= .5 True D defined as HP2inthob != 0 -------------------------------------------------- Sensitivity Pr( +| D) 28.95% Specificity Pr( -|~D) 98.01% Positive predictive value Pr( D| +) 64.71% Negative predictive value Pr(~D| -) 91.64% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 1.99% False - rate for true D Pr( -| D) 71.05% False + rate for classified + Pr(~D| +) 35.29% False - rate for classified - Pr( D| -) 8.36% -------------------------------------------------- Correctly classified 90.29% -------------------------------------------------- Logistic model for HP2inthob, goodness-of-fit test number of observations = 340 number of covariate patterns = 336 Pearson chi2(330) = 249.07 Prob > chi2 = 0.9997 Measures of Fit for logistic of HP2inthob Log-Lik Intercept Only: -119.064 Log-Lik Full Model: -84.583 D(334): 169.167 LR(5): 68.962 Prob > LR: 0.000 McFadden's R2: 0.290 McFadden's Adj R2: 0.239 Maximum Likelihood R2: 0.184 Cragg & Uhler's R2: 0.365 McKelvey and Zavoina's R2: 0.495 Efron's R2: 0.236 Variance of y*: 6.512 Variance of error: 3.290 Count R2: 0.903 Adj Count R2: 0.132 AIC: 0.533 AIC*n: 181.167 BIC: -1777.701 BIC': -39.817 Note: bf4m is necssary for bf5 but if bf4m is in model bf5 is not signif. Therefore, bf5 is not deemed significant. 1022 . 1023 . cap gen bf5mXd3 = bf5m*avgcumdosew3 1024 . 1025 . 1026 . 1027 . title3 "Wave 3 Main effects Dose=> Interests and Hobbies impact identificatio > n" ------------------------------------------------------------------------------- title3 : Wave 3 Main effects Dose=> Interests and Hobbies impact identification 1 Jul 2012 20:40:10 computer Macintosh (Intel 64-bit) folder /Users/robertyaffee/Documents/data/research/chwk/phase3/Htests/H1tests/ > h1pt2 Data file chwide1jul2012.dta currrently has 2395 variables and 703 observ > ations 1028 . forvalues j=3/3 { 2. set more off 3. 1029 . des age educ1-educ7 marrw`j'1-marrw`j'6 inc1w`j'-inc4w`j' /// > bf1 bf4 bf9 bf11 bf4m bf15m bf30 bf40 4. 1030 . foreach var in HP2inthob { 5. local w3bf bf1 bf4 bf2 bf4m bf5m bf7m bf8 bf15m bf17 bf20 bf22 bf29 bf30 b > f40 6. di as input "Full main model for `var' for wave= `j' " 7. di _skip(4) 8. di as input "chunk 8 H1 test:Gender= male model Wave = `j' for `e(depva > r)' " 9. di _skip(4) 10. title "Full Nottingham Part 2 subscale models for males in wave=`j'" 11. 1031 . xi: logistic `var' age /// > radhlw`j' avgcumdosew`j' /// > shfamw`j' bf4m /// > bf5m bf5mXd3 if gender==1, coef nolog difficult iterate(50 > ) 12. estat class 13. estat gof 14. fitstat 15. } 16. } storage display value variable name type format label variable label ------------------------------------------------------------------------------- age double %8.0g * Respondent's age educ1 byte %8.0g educ==1. did not graduate high school educ2 byte %8.0g educ==2. graduated high school educ3 byte %8.0g educ==3. technical degree educ4 byte %8.0g educ==4. did not finish college/bachelor's educ5 byte %8.0g educ==5. graduated college/bachelor's educ6 byte %8.0g educ==6. finished specialist/master's degree educ7 byte %8.0g educ==7. doctor of science/phd marrw31 byte %8.0g marrw3==1. single marrw32 byte %8.0g marrw3==2. cohabitating marrw33 byte %8.0g marrw3==3. married marrw34 byte %8.0g marrw3==4. separated marrw35 byte %8.0g marrw3==5. divorced marrw36 byte %8.0g marrw3==6. widowed inc1w3 double %15.0g LABJ Income is not sufficient for basic neccessities NOW inc2w3 double %15.0g LABJ Income is just sufficient for basic neccessities NOW inc3w3 double %15.0g LABJ Income is sufficient for basics plus extra purchases/savings NOW inc4w3 double %15.0g LABJ Income allows to comfortably afford luxury items NOW bf1 float %9.0g bf1 = max(0, kzchorn - 40) bf4 float %9.0g bf4 = max(0, 24 - BSIsoma) bf9 float %9.0g bf9= max(0, 30 - shhlw1) bf11 float %9.0g bf11= max(0, 20 - sufamw1) bf4m float %9.0g bf4m = max(0, 32 - BSIsoma) bf15m float %9.0g bf15m= max(0, 1 - icdxcnt) * bf2 bf30 float %9.0g bf30 = max(0, neiw1 - 85) * bf20 bf40 float %9.0g bf40 = max(0, icdxcnt - 1.01635E-007) Full main model for HP2inthob for wave= 3 chunk 8 H1 test:Gender= male model Wave = 3 for HP2inthob ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Full Nottingham Part 2 subscale models for males in wave=3 ***** ***** ***** ***** ***** ***** 1 Jul 2012 20:40:10 ***** ******************************************************************************* ******************************************************************************* Logistic regression Number of obs = 340 LR chi2(7) = 69.85 Prob > chi2 = 0.0000 Log likelihood = -84.141731 Pseudo R2 = 0.2933 ------------------------------------------------------------------------------ HP2inthob | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0427782 .0194796 2.20 0.028 .004599 .0809575 radhlw3 | .0323992 .0086278 3.76 0.000 .015489 .0493095 avgcumdosew3 | -.0334024 .265555 -0.13 0.900 -.5538806 .4870758 shfamw3 | .0129086 .006987 1.85 0.065 -.0007857 .0266028 bf4m | -.0374129 .040869 -0.92 0.360 -.1175146 .0426889 bf5m | -.0015707 .0014827 -1.06 0.289 -.0044767 .0013353 bf5mXd3 | -.0002159 .0008473 -0.25 0.799 -.0018766 .0014448 _cons | -6.355059 1.990746 -3.19 0.001 -10.25685 -2.453267 ------------------------------------------------------------------------------ Logistic model for HP2inthob -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 11 8 | 19 - | 27 294 | 321 -----------+--------------------------+----------- Total | 38 302 | 340 Classified + if predicted Pr(D) >= .5 True D defined as HP2inthob != 0 -------------------------------------------------- Sensitivity Pr( +| D) 28.95% Specificity Pr( -|~D) 97.35% Positive predictive value Pr( D| +) 57.89% Negative predictive value Pr(~D| -) 91.59% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 2.65% False - rate for true D Pr( -| D) 71.05% False + rate for classified + Pr(~D| +) 42.11% False - rate for classified - Pr( D| -) 8.41% -------------------------------------------------- Correctly classified 89.71% -------------------------------------------------- Logistic model for HP2inthob, goodness-of-fit test number of observations = 340 number of covariate patterns = 338 Pearson chi2(330) = 244.95 Prob > chi2 = 0.9999 Measures of Fit for logistic of HP2inthob Log-Lik Intercept Only: -119.064 Log-Lik Full Model: -84.142 D(332): 168.283 LR(7): 69.845 Prob > LR: 0.000 McFadden's R2: 0.293 McFadden's Adj R2: 0.226 Maximum Likelihood R2: 0.186 Cragg & Uhler's R2: 0.369 McKelvey and Zavoina's R2: 0.469 Efron's R2: 0.238 Variance of y*: 6.195 Variance of error: 3.290 Count R2: 0.897 Adj Count R2: 0.079 AIC: 0.542 AIC*n: 184.283 BIC: -1766.926 BIC': -29.042 1032 . scalar SigDoseInthbMw3 = "no" 1033 . scalar MainEffInthbMw3 = "age radhlw3 shfamw3" 1034 . scalar InthbMw3 = "none" 1035 . 1036 . *------chunk 8 female moderator models 1037 . title "trimmed Moderators of female Dose => Interests and Hobbies Impact" ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** trimmed Moderators of female Dose => Interests and Hobbies Impact ***** ***** ***** ***** ***** ***** 1 Jul 2012 20:40:11 ***** ******************************************************************************* ******************************************************************************* 1038 . 1039 . 1040 . forvalues j=3/3 { 2. set more off 3. 1041 . des age educ1-educ7 marrw`j'1-marrw`j'6 inc1w`j'-inc4w`j' /// > bf1 bf4 bf9 bf11 bf4m bf15m bf30 bf40 4. 1042 . foreach var in HP2inthob { 5. local w3bf bf1 bf4 bf2 bf4m bf5m bf7m bf8 bf15m bf17 bf20 bf22 bf29 bf30 b > f40 6. di as input "Full main model for `var' for wave= `j' " 7. di _skip(4) 8. di as input "chunk 8 H1 test:Gender= male model Wave = `j' for `e(depva > r)' " 9. di _skip(4) 10. title "Full Nottingham Part 2 subscale models for females " 11. 1043 . xi: logistic `var' age /// > radhlw`j' avgcumdosew`j' /// > bf4 /// > if gender==2, coef nolog difficult iterate(50) 12. estat class 13. estat gof 14. fitstat 15. } 16. } storage display value variable name type format label variable label ------------------------------------------------------------------------------- age double %8.0g * Respondent's age educ1 byte %8.0g educ==1. did not graduate high school educ2 byte %8.0g educ==2. graduated high school educ3 byte %8.0g educ==3. technical degree educ4 byte %8.0g educ==4. did not finish college/bachelor's educ5 byte %8.0g educ==5. graduated college/bachelor's educ6 byte %8.0g educ==6. finished specialist/master's degree educ7 byte %8.0g educ==7. doctor of science/phd marrw31 byte %8.0g marrw3==1. single marrw32 byte %8.0g marrw3==2. cohabitating marrw33 byte %8.0g marrw3==3. married marrw34 byte %8.0g marrw3==4. separated marrw35 byte %8.0g marrw3==5. divorced marrw36 byte %8.0g marrw3==6. widowed inc1w3 double %15.0g LABJ Income is not sufficient for basic neccessities NOW inc2w3 double %15.0g LABJ Income is just sufficient for basic neccessities NOW inc3w3 double %15.0g LABJ Income is sufficient for basics plus extra purchases/savings NOW inc4w3 double %15.0g LABJ Income allows to comfortably afford luxury items NOW bf1 float %9.0g bf1 = max(0, kzchorn - 40) bf4 float %9.0g bf4 = max(0, 24 - BSIsoma) bf9 float %9.0g bf9= max(0, 30 - shhlw1) bf11 float %9.0g bf11= max(0, 20 - sufamw1) bf4m float %9.0g bf4m = max(0, 32 - BSIsoma) bf15m float %9.0g bf15m= max(0, 1 - icdxcnt) * bf2 bf30 float %9.0g bf30 = max(0, neiw1 - 85) * bf20 bf40 float %9.0g bf40 = max(0, icdxcnt - 1.01635E-007) Full main model for HP2inthob for wave= 3 chunk 8 H1 test:Gender= male model Wave = 3 for HP2inthob ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Full Nottingham Part 2 subscale models for females ***** ***** ***** ***** ***** ***** 1 Jul 2012 20:40:11 ***** ******************************************************************************* ******************************************************************************* Logistic regression Number of obs = 363 LR chi2(4) = 85.17 Prob > chi2 = 0.0000 Log likelihood = -129.52718 Pseudo R2 = 0.2474 ------------------------------------------------------------------------------ HP2inthob | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0747817 .0159584 4.69 0.000 .0435038 .1060596 radhlw3 | .0177314 .0055334 3.20 0.001 .0068862 .0285766 avgcumdosew3 | .0423064 .0679809 0.62 0.534 -.0909337 .1755466 bf4 | -.092667 .0312315 -2.97 0.003 -.1538797 -.0314543 _cons | -6.042759 1.092151 -5.53 0.000 -8.183336 -3.902181 ------------------------------------------------------------------------------ Logistic model for HP2inthob -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 27 10 | 37 - | 39 287 | 326 -----------+--------------------------+----------- Total | 66 297 | 363 Classified + if predicted Pr(D) >= .5 True D defined as HP2inthob != 0 -------------------------------------------------- Sensitivity Pr( +| D) 40.91% Specificity Pr( -|~D) 96.63% Positive predictive value Pr( D| +) 72.97% Negative predictive value Pr(~D| -) 88.04% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 3.37% False - rate for true D Pr( -| D) 59.09% False + rate for classified + Pr(~D| +) 27.03% False - rate for classified - Pr( D| -) 11.96% -------------------------------------------------- Correctly classified 86.50% -------------------------------------------------- Logistic model for HP2inthob, goodness-of-fit test number of observations = 363 number of covariate patterns = 361 Pearson chi2(356) = 495.06 Prob > chi2 = 0.0000 Measures of Fit for logistic of HP2inthob Log-Lik Intercept Only: -172.113 Log-Lik Full Model: -129.527 D(358): 259.054 LR(4): 85.171 Prob > LR: 0.000 McFadden's R2: 0.247 McFadden's Adj R2: 0.218 Maximum Likelihood R2: 0.209 Cragg & Uhler's R2: 0.341 McKelvey and Zavoina's R2: 0.412 Efron's R2: 0.299 Variance of y*: 5.592 Variance of error: 3.290 Count R2: 0.865 Adj Count R2: 0.258 AIC: 0.741 AIC*n: 269.054 BIC: -1851.142 BIC': -61.593 1044 . scalar SigdoseInthbFw3 = "no" 1045 . scalar MainEffInthbFw3 = "age radhlw3 bf4" 1046 . 1047 . *------chunk 8 testing female moderators 1048 . title "trimmed Moderators of female Dose => Interests and Hobbies Impact" ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** trimmed Moderators of female Dose => Interests and Hobbies Impact ***** ***** ***** ***** ***** ***** 1 Jul 2012 20:40:13 ***** ******************************************************************************* ******************************************************************************* 1049 . 1050 . 1051 . forvalues j=3/3 { 2. set more off 3. 1052 . des age educ1-educ7 marrw`j'1-marrw`j'6 inc1w`j'-inc4w`j' /// > bf1 bf4 bf9 bf11 bf4m bf15m bf30 bf40 4. 1053 . foreach var in HP2inthob { 5. local w3bf bf1 bf4 bf2 bf4m bf5m bf7m bf8 bf15m bf17 bf20 bf22 bf29 bf30 b > f40 6. di as input "Full main model for `var' for wave= `j' " 7. di _skip(4) 8. di as input "chunk 8 H1 test:Gender= male model Wave = `j' for `e(depva > r)' " 9. di _skip(4) 10. title "Full Nottingham Part 2 subscale models for females in wave=`j' " 11. 1054 . xi: logistic `var' age /// > radhlw`j' avgcumdosew`j' /// > bf4 bf4Xd3 ageXd3 radhlw3Xd3 /// > if gender==2, coef nolog difficult iterate(50) 12. estat class 13. estat gof 14. fitstat 15. } 16. } storage display value variable name type format label variable label ------------------------------------------------------------------------------- age double %8.0g * Respondent's age educ1 byte %8.0g educ==1. did not graduate high school educ2 byte %8.0g educ==2. graduated high school educ3 byte %8.0g educ==3. technical degree educ4 byte %8.0g educ==4. did not finish college/bachelor's educ5 byte %8.0g educ==5. graduated college/bachelor's educ6 byte %8.0g educ==6. finished specialist/master's degree educ7 byte %8.0g educ==7. doctor of science/phd marrw31 byte %8.0g marrw3==1. single marrw32 byte %8.0g marrw3==2. cohabitating marrw33 byte %8.0g marrw3==3. married marrw34 byte %8.0g marrw3==4. separated marrw35 byte %8.0g marrw3==5. divorced marrw36 byte %8.0g marrw3==6. widowed inc1w3 double %15.0g LABJ Income is not sufficient for basic neccessities NOW inc2w3 double %15.0g LABJ Income is just sufficient for basic neccessities NOW inc3w3 double %15.0g LABJ Income is sufficient for basics plus extra purchases/savings NOW inc4w3 double %15.0g LABJ Income allows to comfortably afford luxury items NOW bf1 float %9.0g bf1 = max(0, kzchorn - 40) bf4 float %9.0g bf4 = max(0, 24 - BSIsoma) bf9 float %9.0g bf9= max(0, 30 - shhlw1) bf11 float %9.0g bf11= max(0, 20 - sufamw1) bf4m float %9.0g bf4m = max(0, 32 - BSIsoma) bf15m float %9.0g bf15m= max(0, 1 - icdxcnt) * bf2 bf30 float %9.0g bf30 = max(0, neiw1 - 85) * bf20 bf40 float %9.0g bf40 = max(0, icdxcnt - 1.01635E-007) Full main model for HP2inthob for wave= 3 chunk 8 H1 test:Gender= male model Wave = 3 for HP2inthob ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Full Nottingham Part 2 subscale models for females in wave=3 ***** ***** ***** ***** ***** ***** 1 Jul 2012 20:40:13 ***** ******************************************************************************* ******************************************************************************* Logistic regression Number of obs = 363 LR chi2(7) = 85.42 Prob > chi2 = 0.0000 Log likelihood = -129.40062 Pseudo R2 = 0.2482 ------------------------------------------------------------------------------ HP2inthob | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .07069 .0194156 3.64 0.000 .032636 .1087439 radhlw3 | .0190385 .0070172 2.71 0.007 .0052851 .0327919 avgcumdosew3 | -.0765606 .6162688 -0.12 0.901 -1.284425 1.131304 bf4 | -.0964948 .0400004 -2.41 0.016 -.1748942 -.0180954 bf4Xd3 | .0029229 .020246 0.14 0.885 -.0367585 .0426043 ageXd3 | .0035645 .0097808 0.36 0.716 -.0156055 .0227346 radhlw3Xd3 | -.0011667 .003632 -0.32 0.748 -.0082854 .0059519 _cons | -5.898722 1.310131 -4.50 0.000 -8.466531 -3.330913 ------------------------------------------------------------------------------ Logistic model for HP2inthob -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 28 10 | 38 - | 38 287 | 325 -----------+--------------------------+----------- Total | 66 297 | 363 Classified + if predicted Pr(D) >= .5 True D defined as HP2inthob != 0 -------------------------------------------------- Sensitivity Pr( +| D) 42.42% Specificity Pr( -|~D) 96.63% Positive predictive value Pr( D| +) 73.68% Negative predictive value Pr(~D| -) 88.31% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 3.37% False - rate for true D Pr( -| D) 57.58% False + rate for classified + Pr(~D| +) 26.32% False - rate for classified - Pr( D| -) 11.69% -------------------------------------------------- Correctly classified 86.78% -------------------------------------------------- Logistic model for HP2inthob, goodness-of-fit test number of observations = 363 number of covariate patterns = 361 Pearson chi2(353) = 496.78 Prob > chi2 = 0.0000 Measures of Fit for logistic of HP2inthob Log-Lik Intercept Only: -172.113 Log-Lik Full Model: -129.401 D(355): 258.801 LR(7): 85.424 Prob > LR: 0.000 McFadden's R2: 0.248 McFadden's Adj R2: 0.202 Maximum Likelihood R2: 0.210 Cragg & Uhler's R2: 0.342 McKelvey and Zavoina's R2: 0.413 Efron's R2: 0.301 Variance of y*: 5.602 Variance of error: 3.290 Count R2: 0.868 Adj Count R2: 0.273 AIC: 0.757 AIC*n: 274.801 BIC: -1833.712 BIC': -44.163 1055 . scalar InthbModFw3 = "none" 1056 . 1057 . title4 "Chunk 8 interests and hobbies testing mediator effects " ------------------------------------------------------------------------------- Chunk 8 interests and hobbies testing mediator effects ------------------------------------------------------------------------------- 1058 . 1059 . * age is a mediating effect for males for Dose=> sex life for men 1060 . 1061 . glm age avgcumdosew3 if gender==1, fam(gaus) link(identity) Iteration 0: log likelihood = -1330.6336 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = 147.7142 Deviance = 49927.38549 (1/df) Deviance = 147.7142 Pearson = 49927.38549 (1/df) Pearson = 147.7142 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 7.839021 Log likelihood = -1330.633586 BIC = 47957.2 ------------------------------------------------------------------------------ | OIM age | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | .5433648 .2472657 2.20 0.028 .058733 1.027997 _cons | 48.52021 .7247376 66.95 0.000 47.09975 49.94067 ------------------------------------------------------------------------------ 1062 . glm HP2inthob age if gender==1, fam(bin) irls scale(dev) link(probit) Iteration 1: deviance = 224.8585 Iteration 2: deviance = 219.8355 Iteration 3: deviance = 219.6997 Iteration 4: deviance = 219.6996 Iteration 5: deviance = 219.6996 Generalized linear models No. of obs = 340 Optimization : MQL Fisher scoring Residual df = 338 (IRLS EIM) Scale parameter = 1 Deviance = 219.6996277 (1/df) Deviance = .6499989 Pearson = 354.7105724 (1/df) Pearson = 1.04944 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1750.484 ------------------------------------------------------------------------------ | EIM HP2inthob | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .031726 .0062563 5.07 0.000 .0194638 .0439882 _cons | -2.867608 .344284 -8.33 0.000 -3.542392 -2.192824 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 1063 . 1064 . * illness is a mediating effect for males = > sex life for men 1065 . des illw3 storage display value variable name type format label variable label ------------------------------------------------------------------------------- illw3 double %8.0g Total number of illnesses experienced in time period 1996-NOW 1066 . glm illw3 avgcumdosew3 if gender==1, fam(gaus) link(identity) Iteration 0: log likelihood = -461.99206 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = .8919217 Deviance = 301.469521 (1/df) Deviance = .8919217 Pearson = 301.469521 (1/df) Pearson = .8919217 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 2.729365 Log likelihood = -461.9920626 BIC = -1668.714 ------------------------------------------------------------------------------ | OIM illw3 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | .038211 .0192139 1.99 0.047 .0005524 .0758696 _cons | .4504952 .0563162 8.00 0.000 .3401176 .5608729 ------------------------------------------------------------------------------ 1067 . glm HP2inthob illw3 if gender==1, fam(bin) irls scale(dev) link(probit) Iteration 1: deviance = 234.8681 Iteration 2: deviance = 233.1574 Iteration 3: deviance = 233.1444 Iteration 4: deviance = 233.1444 Iteration 5: deviance = 233.1444 Generalized linear models No. of obs = 340 Optimization : MQL Fisher scoring Residual df = 338 (IRLS EIM) Scale parameter = 1 Deviance = 233.144425 (1/df) Deviance = .6897764 Pearson = 334.1788359 (1/df) Pearson = .9886948 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1737.039 ------------------------------------------------------------------------------ | EIM HP2inthob | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- illw3 | .1917072 .0680987 2.82 0.005 .0582362 .3251781 _cons | -1.333765 .087554 -15.23 0.000 -1.505368 -1.162163 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 1068 . 1069 . des radhlw3 storage display value variable name type format label variable label ------------------------------------------------------------------------------- radhlw3 double %8.0g Self-perceived Chornobyl health threat in wave 3 1070 . glm radhlw3 avgcumdosew3 if gender==1, fam(gaus) link(identity) Iteration 0: log likelihood = -1695.1855 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = 1261.052 Deviance = 426235.7205 (1/df) Deviance = 1261.052 Pearson = 426235.7205 (1/df) Pearson = 1261.052 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 9.983444 Log likelihood = -1695.185473 BIC = 424265.5 ------------------------------------------------------------------------------ | OIM radhlw3 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | .9606492 .7224692 1.33 0.184 -.4553645 2.376663 _cons | 46.19995 2.117563 21.82 0.000 42.0496 50.3503 ------------------------------------------------------------------------------ 1071 . glm HP2inthob radhlw3 if gender==1, fam(bin) irls scale(dev) link(probit) Iteration 1: deviance = 203.3027 Iteration 2: deviance = 188.4084 Iteration 3: deviance = 186.1904 Iteration 4: deviance = 186.0891 Iteration 5: deviance = 186.0888 Iteration 6: deviance = 186.0888 Generalized linear models No. of obs = 340 Optimization : MQL Fisher scoring Residual df = 338 (IRLS EIM) Scale parameter = 1 Deviance = 186.088809 (1/df) Deviance = .5505586 Pearson = 318.4835319 (1/df) Pearson = .942259 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1784.095 ------------------------------------------------------------------------------ | EIM HP2inthob | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- radhlw3 | .0212428 .0025645 8.28 0.000 .0162164 .0262691 _cons | -2.562769 .2038548 -12.57 0.000 -2.962317 -2.163221 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 1072 . 1073 . 1074 . des shfamw3 storage display value variable name type format label variable label ------------------------------------------------------------------------------- shfamw3 double %8.0g Percentage of strains and hassles related to family NOW 1075 . glm shfamw3 avgcumdosew3 if gender==1, fam(gaus) link(identity) Iteration 0: log likelihood = -1708.9012 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = 1367.012 Deviance = 462050.0805 (1/df) Deviance = 1367.012 Pearson = 462050.0805 (1/df) Pearson = 1367.012 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 10.06412 Log likelihood = -1708.901202 BIC = 460079.9 ------------------------------------------------------------------------------ | OIM shfamw3 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | -.1212312 .7522098 -0.16 0.872 -1.595535 1.353073 _cons | 54.35361 2.204733 24.65 0.000 50.03242 58.67481 ------------------------------------------------------------------------------ 1076 . glm HP2inthob shfamw3 if gender==1, fam(bin) irls scale(dev) link(probit) Iteration 1: deviance = 226.2154 Iteration 2: deviance = 220.7262 Iteration 3: deviance = 220.4926 Iteration 4: deviance = 220.4922 Iteration 5: deviance = 220.4922 Generalized linear models No. of obs = 340 Optimization : MQL Fisher scoring Residual df = 338 (IRLS EIM) Scale parameter = 1 Deviance = 220.4922229 (1/df) Deviance = .6523439 Pearson = 359.3118386 (1/df) Pearson = 1.063053 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1749.691 ------------------------------------------------------------------------------ | EIM HP2inthob | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- shfamw3 | .0109039 .0022452 4.86 0.000 .0065034 .0153045 _cons | -1.9049 .171268 -11.12 0.000 -2.240579 -1.56922 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 1077 . 1078 . des bf5m storage display value variable name type format label variable label ------------------------------------------------------------------------------- bf5m float %9.0g bf5m = max(0, ecprw3 - 75) * bf4m 1079 . glm bf5m avgcumdosew3 if gender==1, fam(gaus) link(identity) Iteration 0: log likelihood = -2273.014 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = 37748.2 Deviance = 12758891.39 (1/df) Deviance = 37748.2 Pearson = 12758891.39 (1/df) Pearson = 37748.2 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 13.38244 Log likelihood = -2273.013968 BIC = 1.28e+07 ------------------------------------------------------------------------------ | OIM bf5m | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | 9.087842 3.952764 2.30 0.021 1.340566 16.83512 _cons | 102.4403 11.58558 8.84 0.000 79.73302 125.1477 ------------------------------------------------------------------------------ 1080 . glm HP2inthob bf5m if gender==1, fam(bin) irls scale(dev) link(probit) Iteration 1: deviance = 238.9021 Iteration 2: deviance = 238.0124 Iteration 3: deviance = 238.0098 Iteration 4: deviance = 238.0098 Iteration 5: deviance = 238.0098 Generalized linear models No. of obs = 340 Optimization : MQL Fisher scoring Residual df = 338 (IRLS EIM) Scale parameter = 1 Deviance = 238.0098185 (1/df) Deviance = .7041711 Pearson = 339.8073754 (1/df) Pearson = 1.005347 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1732.174 ------------------------------------------------------------------------------ | EIM HP2inthob | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- bf5m | .0001615 .000378 0.43 0.669 -.0005794 .0009024 _cons | -1.236147 .0878768 -14.07 0.000 -1.408382 -1.063912 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 1081 . 1082 . glm bf4 avgcumdosew3 if gender==1, fam(gaus) link(identity) Iteration 0: log likelihood = -1027.1072 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = 24.77487 Deviance = 8373.906252 (1/df) Deviance = 24.77487 Pearson = 8373.906252 (1/df) Pearson = 24.77487 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 6.053572 Log likelihood = -1027.107224 BIC = 6403.723 ------------------------------------------------------------------------------ | OIM bf4 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | -.0357675 .1012648 -0.35 0.724 -.2342429 .1627078 _cons | 12.54064 .2968079 42.25 0.000 11.95891 13.12238 ------------------------------------------------------------------------------ 1083 . glm HP2inthob bf4 if gender==1, fam(bin) irls scale(dev) link(probit) Iteration 1: deviance = 201.5914 Iteration 2: deviance = 191.8769 Iteration 3: deviance = 191.2682 Iteration 4: deviance = 191.2622 Iteration 5: deviance = 191.2622 Iteration 6: deviance = 191.2622 Generalized linear models No. of obs = 340 Optimization : MQL Fisher scoring Residual df = 338 (IRLS EIM) Scale parameter = 1 Deviance = 191.2622075 (1/df) Deviance = .5658645 Pearson = 305.593706 (1/df) Pearson = .9041234 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1778.921 ------------------------------------------------------------------------------ | EIM HP2inthob | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- bf4 | -.1182178 .013496 -8.76 0.000 -.1446695 -.091766 _cons | .0441185 .1517879 0.29 0.771 -.2533804 .3416174 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 1084 . 1085 . 1086 . * age is a mediating effect for females for Dose=> sex life for women 1087 . glm age avgcumdosew3 if gender==2, fam(gaus) link(identity) Iteration 0: log likelihood = -1408.064 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = 137.7687 Deviance = 49734.51399 (1/df) Deviance = 137.7687 Pearson = 49734.51399 (1/df) Pearson = 137.7687 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 7.768948 Log likelihood = -1408.06405 BIC = 47606.63 ------------------------------------------------------------------------------ | OIM age | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | 1.058366 .3512614 3.01 0.003 .3699069 1.746826 _cons | 48.94293 .7468173 65.54 0.000 47.47919 50.40666 ------------------------------------------------------------------------------ 1088 . glm HP2inthob age if gender==2, fam(bin) irls scale(dev) link(probit) Iteration 1: deviance = 293.9671 Iteration 2: deviance = 289.27 Iteration 3: deviance = 289.1951 Iteration 4: deviance = 289.1951 Iteration 5: deviance = 289.1951 Generalized linear models No. of obs = 363 Optimization : MQL Fisher scoring Residual df = 361 (IRLS EIM) Scale parameter = 1 Deviance = 289.1950995 (1/df) Deviance = .8010945 Pearson = 415.3464621 (1/df) Pearson = 1.150544 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1838.684 ------------------------------------------------------------------------------ | EIM HP2inthob | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0515323 .0068567 7.52 0.000 .0380933 .0649713 _cons | -3.649661 .3847198 -9.49 0.000 -4.403698 -2.895624 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 1089 . 1090 . des bf4 // soma recentered storage display value variable name type format label variable label ------------------------------------------------------------------------------- bf4 float %9.0g bf4 = max(0, 24 - BSIsoma) 1091 . * bf4 is a mediting effect for females for Dose=> sex life for women 1092 . glm bf4 avgcumdosew3 if gender==2, fam(gaus) link(identity) Iteration 0: log likelihood = -1109.6569 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = 26.6146 Deviance = 9607.869105 (1/df) Deviance = 26.6146 Pearson = 9607.869105 (1/df) Pearson = 26.6146 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 6.124831 Log likelihood = -1109.656873 BIC = 7479.99 ------------------------------------------------------------------------------ | OIM bf4 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | -.4386292 .1543885 -2.84 0.004 -.7412252 -.1360333 _cons | 11.01475 .3282456 33.56 0.000 10.3714 11.6581 ------------------------------------------------------------------------------ 1093 . glm HP2inthob bf4 if gender==2, fam(bin) irls scale(dev) link(probit) Iteration 1: deviance = 304.5744 Iteration 2: deviance = 301.504 Iteration 3: deviance = 301.4488 Iteration 4: deviance = 301.4487 Iteration 5: deviance = 301.4487 Generalized linear models No. of obs = 363 Optimization : MQL Fisher scoring Residual df = 361 (IRLS EIM) Scale parameter = 1 Deviance = 301.4486672 (1/df) Deviance = .8350379 Pearson = 341.1451194 (1/df) Pearson = .9450003 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1826.431 ------------------------------------------------------------------------------ | EIM HP2inthob | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- bf4 | -.0993749 .0142594 -6.97 0.000 -.1273229 -.071427 _cons | .0117358 .1447759 0.08 0.935 -.2720197 .2954914 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 1094 . 1095 . des bf4m // soma recentered storage display value variable name type format label variable label ------------------------------------------------------------------------------- bf4m float %9.0g bf4m = max(0, 32 - BSIsoma) 1096 . * bf4m is a possible mediating effect for female sex life 1097 . glm bf4m avgcumdosew3 if gender==2, fam(gaus) link(identity) Iteration 0: log likelihood = -1141.3116 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = 31.68572 Deviance = 11438.54371 (1/df) Deviance = 31.68572 Pearson = 11438.54371 (1/df) Pearson = 31.68572 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 6.299237 Log likelihood = -1141.311602 BIC = 9310.664 ------------------------------------------------------------------------------ | OIM bf4m | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | -.441173 .1684561 -2.62 0.009 -.771341 -.1110051 _cons | 18.82772 .3581548 52.57 0.000 18.12575 19.52969 ------------------------------------------------------------------------------ 1098 . glm HP2sxlife bf4m if gender==2, fam(bin) irls scale(dev) link(probit) Iteration 1: deviance = 356.1451 Iteration 2: deviance = 355.6209 Iteration 3: deviance = 355.6178 Iteration 4: deviance = 355.6178 Iteration 5: deviance = 355.6178 Generalized linear models No. of obs = 363 Optimization : MQL Fisher scoring Residual df = 361 (IRLS EIM) Scale parameter = 1 Deviance = 355.6178202 (1/df) Deviance = .9850909 Pearson = 340.0032816 (1/df) Pearson = .9418373 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1772.262 ------------------------------------------------------------------------------ | EIM HP2sxlife | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- bf4m | -.0990193 .0135516 -7.31 0.000 -.12558 -.0724586 _cons | 1.063679 .244399 4.35 0.000 .584666 1.542693 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 1099 . 1100 . des shfamw3 storage display value variable name type format label variable label ------------------------------------------------------------------------------- shfamw3 double %8.0g Percentage of strains and hassles related to family NOW 1101 . glm shfamw3 avgcumdosew3 if gender==1, fam(gaus) link(identity) Iteration 0: log likelihood = -1708.9012 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = 1367.012 Deviance = 462050.0805 (1/df) Deviance = 1367.012 Pearson = 462050.0805 (1/df) Pearson = 1367.012 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 10.06412 Log likelihood = -1708.901202 BIC = 460079.9 ------------------------------------------------------------------------------ | OIM shfamw3 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | -.1212312 .7522098 -0.16 0.872 -1.595535 1.353073 _cons | 54.35361 2.204733 24.65 0.000 50.03242 58.67481 ------------------------------------------------------------------------------ 1102 . glm HP2sxlife shfamw3 if gender==1, fam(bin) irls scale(dev) link(probit) Iteration 1: deviance = 329.7746 Iteration 2: deviance = 329.2454 Iteration 3: deviance = 329.2451 Iteration 4: deviance = 329.2451 Generalized linear models No. of obs = 340 Optimization : MQL Fisher scoring Residual df = 338 (IRLS EIM) Scale parameter = 1 Deviance = 329.2450963 (1/df) Deviance = .9740979 Pearson = 344.0536463 (1/df) Pearson = 1.01791 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1640.939 ------------------------------------------------------------------------------ | EIM HP2sxlife | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- shfamw3 | .0079286 .0021676 3.66 0.000 .0036802 .012177 _cons | -1.296137 .1536069 -8.44 0.000 -1.597201 -.9950731 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 1103 . 1104 . des shrelaw3 storage display value variable name type format label variable label ------------------------------------------------------------------------------- shrelaw3 double %8.0g Percentage of strains and hassles related to relationships NOW 1105 . glm shrelaw3 avgcumdosew3 if gender==1, fam(gaus) link(identity) Iteration 0: log likelihood = -1712.5647 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = 1396.791 Deviance = 472115.4213 (1/df) Deviance = 1396.791 Pearson = 472115.4213 (1/df) Pearson = 1396.791 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 10.08567 Log likelihood = -1712.564737 BIC = 470145.2 ------------------------------------------------------------------------------ | OIM shrelaw3 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | -.043239 .7603587 -0.06 0.955 -1.533515 1.447037 _cons | 34.40857 2.228617 15.44 0.000 30.04056 38.77658 ------------------------------------------------------------------------------ 1106 . glm HP2sxlife shrelaw3 if gender==1, fam(bin) irls scale(dev) link(probit) Iteration 1: deviance = 334.5762 Iteration 2: deviance = 334.3197 Iteration 3: deviance = 334.3197 Iteration 4: deviance = 334.3197 Generalized linear models No. of obs = 340 Optimization : MQL Fisher scoring Residual df = 338 (IRLS EIM) Scale parameter = 1 Deviance = 334.3196545 (1/df) Deviance = .9891114 Pearson = 339.7061699 (1/df) Pearson = 1.005048 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1635.864 ------------------------------------------------------------------------------ | EIM HP2sxlife | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- shrelaw3 | .0060138 .002025 2.97 0.003 .0020449 .0099827 _cons | -1.058186 .1113913 -9.50 0.000 -1.276509 -.8398629 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 1107 . 1108 . 1109 . *xx summary of mediating effects: males only age and illw3 2 1110 . *xx females: age 1111 . 1112 . 1113 . 1114 . * summary of sxlife moderator effects none 1115 . scalar sxLifeMedMw3 = "age illw3" 1116 . scalar sxLifeMedFw3 = "age bf4 bf4m" 1117 . 1118 . * no sign main dose effect for males 1119 . * no male moderators 1120 . * 3 signif main effects in male main effect model 1121 . 1122 . 1123 . * no signif dose main effect for females 1124 . * 3 main female effects 1125 . * no significant female moderators 1126 . matrix define HP2inthbMw3 = J(1,8, 0) 1127 . matrix define HP2inthbFw3 = J(1,8, 0) 1128 . matrix colnames HP2inthbMw3 = hypnum ptnum wave gender medsig numMAsig numMo > dsig numMed 1129 . matrix colnames HP2inthbFw3 = hypnum ptnum wave gender medsig numMAsig numMo > dsig numMed 1130 . matrix define HP2inthbMw3 = (1, 2, 3, 1, 0, 3, 0, 2 ) 1131 . matrix define HP2inthbFw3 = (1, 2, 3, 2, 0, 3, 0, 3 ) 1132 . matrix rowname HP2inthbMw3 = HP2inthbM 1133 . matrix rowname HP2inthbFw3 = HP2inthobF 1134 . matlist HP2inthbMw3 | c1 c2 c3 c4 c5 c6 > -------------+----------------------------------------------------------------- - HP2inthbM | 1 2 3 1 0 3 > | c7 c8 -------------+---------------------- HP2inthbM | 0 2 1135 . matlist HP2inthbFw3 | c1 c2 c3 c4 c5 c6 > -------------+----------------------------------------------------------------- - HP2inthobF | 1 2 3 2 0 3 > | c7 c8 -------------+---------------------- HP2inthobF | 0 3 1136 . matrix define H1pt2w3 = ( HP2wkMw3 \ HP2wkFw3 \ HP2hmcrMw3 \ HP2hmcrF > w3 \ HP2spMw3 /// > \ HP2spFw3 \ HP2prbfamMw3 \ HP2prbfamFw3 \ HP2inthbMw3 \ HP2inthb > Fw3 ) 1137 . matlist H1pt2w3 | c1 c2 c3 c4 c5 c6 > -------------+----------------------------------------------------------------- - r1 | 1 2 3 1 0 4 > r1 | 1 2 3 2 0 1 > r1 | 1 2 3 1 0 4 > r1 | 1 2 3 2 0 2 > HP2spMw3 | 1 2 3 1 0 2 > HP2spFw3 | 1 2 3 2 1 5 > HP2prbfamM | 1 2 3 1 0 5 > HP2prbfamF | 1 2 3 2 0 2 > HP2inthbM | 1 2 3 1 0 3 > HP2inthobF | 1 2 3 2 0 3 > | c7 c8 -------------+---------------------- r1 | 0 4 r1 | 0 6 r1 | 0 2 r1 | 0 2 HP2spMw3 | 0 1 HP2spFw3 | 5 3 HP2prbfamM | 0 1 HP2prbfamF | 2 2 HP2inthbM | 0 2 HP2inthobF | 0 3 1138 . matrix colnames H1pt2w3 = hypnum ptnum wave gender medsig numMAsig numMo > dsig numMed 1139 . matrix rownames H1pt2w3 = HP2wkMw3 HP2wkFw3 HP2hmcrMw3 HP2hmcrFw3 HP2sp > Mw3 HP2spFw3 HP2prbfamMw3 HP2prbfamFw3 HP2inthbMw3 HP2inthbFw3 1140 . matlist H1pt2w3 | hypnum ptnum wave gender medsig numMAsig > -------------+----------------------------------------------------------------- - HP2wkMw3 | 1 2 3 1 0 4 > HP2wkFw3 | 1 2 3 2 0 1 > HP2hmcrMw3 | 1 2 3 1 0 4 > HP2hmcrFw3 | 1 2 3 2 0 2 > HP2spMw3 | 1 2 3 1 0 2 > HP2spFw3 | 1 2 3 2 1 5 > HP2prbfamMw3 | 1 2 3 1 0 5 > HP2prbfamFw3 | 1 2 3 2 0 2 > HP2inthbMw3 | 1 2 3 1 0 3 > HP2inthbFw3 | 1 2 3 2 0 3 > | numModsig numMed -------------+---------------------- HP2wkMw3 | 0 4 HP2wkFw3 | 0 6 HP2hmcrMw3 | 0 2 HP2hmcrFw3 | 0 2 HP2spMw3 | 0 1 HP2spFw3 | 5 3 HP2prbfamMw3 | 0 1 HP2prbfamFw3 | 2 2 HP2inthbMw3 | 0 2 HP2inthbFw3 | 0 3 1141 . 1142 . *xxxxxxxxxxxxxxx chunk 9 Dose=> vacation plans impactxxxxxxxxxxxxxxxxxxxxxx > xxx 1143 . title "7. Hypothesis 1 pt 2 wave 3 dose vacation plans impact" ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** 7. Hypothesis 1 pt 2 wave 3 dose vacation plans impact ***** ***** ***** ***** ***** ***** 1 Jul 2012 20:40:45 ***** ******************************************************************************* ******************************************************************************* 1144 . 1145 . cap gen hp2vacatn = HP2vacatn 1146 . 1147 . forvalues j=3/3 { 2. title " Wave 3 Dose = >hp2vacatn main effects models for H1 pt2" 3. set more off 4. local w1bf bf1 bf4 bf9 bf10 bf11 bf4m bf15m bf20 bf22 bf30 bf40 5. local w3bf bf1 bf4 bf6 bf7 bf14 bf15 bf40 6. local w3bf bf1 bf4 bf2 bf4m bf5m bf7m bf8 bf15m bf17 bf20 bf22 bf29 bf30 b > f40 7. di _skip(3) 8. 1148 . di as input "Male model wave 3 dose-hp2vactn moderator model " 9. di _skip(4) 10. xi: logistic hp2vacatn age i.educ occ1w`j'-occ8w`j' /// > marrw`j'1- marrw`j'3 marrw`j'5-marrw`j'6 inc1w`j'-inc4w`j' /// > radhlw`j' havmil avgcumdosew`j' `w`j'bf' /// > deaw`j' dvcew`j' sepaw`j' accdw`j' movew`j' /// > illw`j' shfamw`j' shhlw`j' shjobw`j' shrelaw`j' suprtw`j' suchrw`j' havmils > q /// > radhlw`j' avgcumdosew`j' if gender==1, coef nolog 11. di _skip(4) 12. title3 "trimmed hp2hmcare main effects models for H1 no direct dose effec > t for male" 13. pwcorr hp2hmcare age deaw3 shjobw3 bf7m shjobw3 havmilsq /// > radhlw3 avgcumdosew3 if gender==1, sig obs sidak star(.05) listwise 14. di _skip(1) 15. di as input "For males hp2hmcare on wave3 and d3 is not signif " 16. di _skip(1) 17. logistic hp2hmcare age deaw3 shjobw3 bf7m havmilsq /// > radhlw3 avgcumdosew3 if /// > gender==1, coef nolog 18. } ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Wave 3 Dose = >hp2vacatn main effects models for H1 pt2 ***** ***** ***** ***** ***** ***** 1 Jul 2012 20:40:45 ***** ******************************************************************************* ******************************************************************************* Male model wave 3 dose-hp2vactn moderator model i.educ _Ieduc_1-8 (naturally coded; _Ieduc_1 omitted) note: _Ieduc_7 != 0 predicts failure perfectly _Ieduc_7 dropped and 4 obs not used note: _Ieduc_8 != 0 predicts failure perfectly _Ieduc_8 dropped and 2 obs not used note: occ5w3 != 0 predicts failure perfectly occ5w3 dropped and 18 obs not used note: occ6w3 != 0 predicts failure perfectly occ6w3 dropped and 4 obs not used note: bf15m != 0 predicts failure perfectly bf15m dropped and 19 obs not used note: bf29 != 0 predicts failure perfectly bf29 dropped and 7 obs not used note: _Ieduc_6 omitted because of collinearity note: occ8w3 omitted because of collinearity note: marrw36 omitted because of collinearity note: bf17 omitted because of collinearity note: radhlw3 omitted because of collinearity note: avgcumdosew3 omitted because of collinearity Logistic regression Number of obs = 286 LR chi2(45) = 130.35 Prob > chi2 = 0.0000 Log likelihood = -52.374274 Pseudo R2 = 0.5544 ------------------------------------------------------------------------------ hp2vacatn | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .1141267 .0450696 2.53 0.011 .025792 .2024615 _Ieduc_2 | 1.212945 1.630503 0.74 0.457 -1.982782 4.408672 _Ieduc_3 | -1.181748 .8345653 -1.42 0.157 -2.817465 .4539703 _Ieduc_4 | -.2703336 1.707405 -0.16 0.874 -3.616786 3.076119 _Ieduc_5 | .0781642 .821705 0.10 0.924 -1.532348 1.688676 _Ieduc_6 | 0 (omitted) _Ieduc_7 | 0 (omitted) _Ieduc_8 | 0 (omitted) occ1w3 | -13.38278 1622.421 -0.01 0.993 -3193.27 3166.504 occ2w3 | -12.82938 1622.421 -0.01 0.994 -3192.717 3167.058 occ3w3 | -12.16922 1622.422 -0.01 0.994 -3192.057 3167.719 occ4w3 | -9.847245 1622.421 -0.01 0.995 -3189.735 3170.04 occ5w3 | 0 (omitted) occ6w3 | 0 (omitted) occ7w3 | -10.21639 1622.421 -0.01 0.995 -3190.104 3169.671 occ8w3 | 0 (omitted) marrw31 | 2.471663 1.877772 1.32 0.188 -1.208702 6.152028 marrw32 | 3.882172 2.040109 1.90 0.057 -.116367 7.880711 marrw33 | .7861586 1.848468 0.43 0.671 -2.836772 4.409089 marrw35 | 5.481699 2.097529 2.61 0.009 1.370617 9.592781 marrw36 | 0 (omitted) inc1w3 | 12.51469 1622.421 0.01 0.994 -3167.373 3192.402 inc2w3 | 14.55722 1622.421 0.01 0.993 -3165.329 3194.444 inc3w3 | 14.35316 1622.421 0.01 0.993 -3165.533 3194.24 inc4w3 | 15.92527 1622.422 0.01 0.992 -3163.963 3195.813 radhlw3 | .0197321 .0147075 1.34 0.180 -.0090941 .0485583 havmil | .0234742 .0160068 1.47 0.143 -.0078985 .054847 avgcumdosew3 | .1032883 .1755565 0.59 0.556 -.240796 .4473726 bf1 | -.4769574 .3289335 -1.45 0.147 -1.121655 .1677405 bf4 | -.1442369 .2873042 -0.50 0.616 -.7073429 .4188691 bf2 | .0000186 .0002978 0.06 0.950 -.0005651 .0006023 bf4m | -.1956152 .2497206 -0.78 0.433 -.6850586 .2938281 bf5m | -.0071533 .0043294 -1.65 0.098 -.0156388 .0013321 bf7m | .0000185 .0010386 0.02 0.986 -.0020172 .0020542 bf8 | -.0000173 .0000922 -0.19 0.851 -.0001981 .0001635 bf15m | 0 (omitted) bf17 | 0 (omitted) bf20 | .4362509 .3222411 1.35 0.176 -.1953299 1.067832 bf22 | .0001349 .0003106 0.43 0.664 -.0004739 .0007437 bf29 | 0 (omitted) bf30 | -.0009931 .0006553 -1.52 0.130 -.0022775 .0002912 bf40 | .5185801 .3611964 1.44 0.151 -.1893518 1.226512 deaw3 | .2097501 .3135963 0.67 0.504 -.4048875 .8243876 dvcew3 | 2.012022 1.543197 1.30 0.192 -1.012588 5.036632 sepaw3 | -2.054184 1.443349 -1.42 0.155 -4.883097 .7747288 accdw3 | .2022258 1.25899 0.16 0.872 -2.265349 2.669801 movew3 | -4.177869 1.807922 -2.31 0.021 -7.721331 -.6344073 illw3 | -.4549089 .4293751 -1.06 0.289 -1.296469 .3866508 shfamw3 | .0141549 .0145895 0.97 0.332 -.0144399 .0427498 shhlw3 | .004885 .011315 0.43 0.666 -.0172919 .0270619 shjobw3 | -.0003857 .0112584 -0.03 0.973 -.0224516 .0216803 shrelaw3 | -.008433 .0120996 -0.70 0.486 -.0321477 .0152817 suprtw3 | .0050194 .0152005 0.33 0.741 -.0247729 .0348118 suchrw3 | -.0175411 .0097951 -1.79 0.073 -.0367391 .0016569 havmilsq | -.000046 .0000341 -1.35 0.178 -.0001129 .0000209 radhlw3 | 0 (omitted) avgcumdosew3 | 0 (omitted) _cons | -25.70032 13.82795 -1.86 0.063 -52.80261 1.40197 ------------------------------------------------------------------------------ Note: 8 failures and 0 successes completely determined. ------------------------------------------------------------------------------- title3 : trimmed hp2hmcare main effects models for H1 no direct dose effect for > male 1 Jul 2012 20:40:46 computer Macintosh (Intel 64-bit) folder /Users/robertyaffee/Documents/data/research/chwk/phase3/Htests/H1tests/ > h1pt2 Data file chwide1jul2012.dta currrently has 2402 variables and 703 observ > ations | hp2hmc~e age deaw3 shjobw3 bf7m shjobw3 havmilsq -------------+--------------------------------------------------------------- hp2hmcare | 1.0000 | | 340 | age | 0.2761* 1.0000 | 0.0000 | 340 340 | deaw3 | -0.0456 0.1402 1.0000 | 1.0000 0.2940 | 340 340 340 | shjobw3 | -0.1006 -0.2840* -0.1099 1.0000 | 0.9068 0.0000 0.7935 | 340 340 340 340 | bf7m | -0.1339 -0.0182 0.1015 -0.0869 1.0000 | 0.3860 1.0000 0.8986 0.9848 | 340 340 340 340 340 | shjobw3 | -0.1006 -0.2840* -0.1099 1.0000* -0.0869 1.0000 | 0.9068 0.0000 0.7935 0.0000 0.9848 | 340 340 340 340 340 340 | havmilsq | -0.0347 0.0207 0.0454 -0.0558 -0.0420 -0.0558 1.0000 | 1.0000 1.0000 1.0000 1.0000 1.0000 1.0000 | 340 340 340 340 340 340 340 | radhlw3 | 0.2838* 0.3440* -0.0287 0.0799 0.1399 0.0799 -0.0586 | 0.0000 0.0000 1.0000 0.9959 0.2988 0.9959 1.0000 | 340 340 340 340 340 340 340 | avgcumdosew3 | 0.0272 0.1187 0.0324 -0.0140 0.0339 -0.0140 -0.0471 | 1.0000 0.6490 1.0000 1.0000 1.0000 1.0000 1.0000 | 340 340 340 340 340 340 340 | | radhlw3 avgcu~w3 -------------+------------------ radhlw3 | 1.0000 | | 340 | avgcumdosew3 | 0.0721 1.0000 | 0.9994 | 340 340 | For males hp2hmcare on wave3 and d3 is not signif Logistic regression Number of obs = 340 LR chi2(7) = 52.51 Prob > chi2 = 0.0000 Log likelihood = -146.61786 Pseudo R2 = 0.1519 ------------------------------------------------------------------------------ hp2hmcare | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0355627 .0137739 2.58 0.010 .0085664 .062559 deaw3 | -.1753451 .1955831 -0.90 0.370 -.558681 .2079907 shjobw3 | -.0061002 .0041748 -1.46 0.144 -.0142827 .0020822 bf7m | -.0006241 .0002098 -2.97 0.003 -.0010353 -.0002129 havmilsq | -1.46e-06 2.84e-06 -0.51 0.608 -7.03e-06 4.11e-06 radhlw3 | .0182143 .0044455 4.10 0.000 .0095012 .0269274 avgcumdosew3 | .0012605 .0491638 0.03 0.980 -.0950988 .0976199 _cons | -3.220671 .8063703 -3.99 0.000 -4.801128 -1.640214 ------------------------------------------------------------------------------ 1149 . 1150 . scalar SigDoseVactnMw3 = "no" 1151 . scalar MainEffVactnMw3 = "age bf7m radhlw3 " 1152 . 1153 . local cn7:colnames(e(b)) 1154 . di "`cn7'" age deaw3 shjobw3 bf7m havmilsq radhlw3 avgcumdosew3 _cons 1155 . local len7 = length("`cn7'") 1156 . di `len7' 58 1157 . local len7b = `len7' - 6 1158 . di `len7b' 52 1159 . local myvarlist = substr("`cn7'",1,`len7b') 1160 . di "`myvarlist'" age deaw3 shjobw3 bf7m havmilsq radhlw3 avgcumdosew3 1161 . 1162 . foreach var in `myvarlist' { 2. cap gen `var'Xd3 = `var'*avgcumdosew3 3. } 1163 . 1164 . title " Trimmed male main effects dose=> vacation plans model" ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Trimmed male main effects dose=> vacation plans model ***** ***** ***** ***** ***** ***** 1 Jul 2012 20:40:47 ***** ******************************************************************************* ******************************************************************************* 1165 . di as input "No sig main male dose main effects model" No sig main male dose main effects model 1166 . sw, pr(.1): logit hp2vacatn `myvarlist' if gender==1 begin with full model p = 0.8250 >= 0.1000 removing avgcumdosew3 p = 0.4319 >= 0.1000 removing deaw3 p = 0.4230 >= 0.1000 removing havmilsq p = 0.2153 >= 0.1000 removing shjobw3 Logistic regression Number of obs = 340 LR chi2(3) = 38.31 Prob > chi2 = 0.0000 Log likelihood = -105.99881 Pseudo R2 = 0.1530 ------------------------------------------------------------------------------ hp2vacatn | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0582498 .0159119 3.66 0.000 .027063 .0894366 radhlw3 | .0163308 .0053758 3.04 0.002 .0057944 .0268671 bf7m | -.0003954 .0002402 -1.65 0.100 -.0008662 .0000754 _cons | -5.639649 .9231625 -6.11 0.000 -7.449014 -3.830284 ------------------------------------------------------------------------------ 1167 . 1168 . 1169 . local cn8:colnames(e(b)) 1170 . di "`cn8'" age radhlw3 bf7m _cons 1171 . local len8 = length("`cn8'") 1172 . di `len7' 58 1173 . local len8b = `len8' - 6 1174 . di `len8b' 16 1175 . local myvarlist = substr("`cn8'",1,`len8b') 1176 . di "`myvarlist'" age radhlw3 bf7m 1177 . 1178 . 1179 . 1180 . title4 "Trimmed male interaction dose=> vacation plans model" ------------------------------------------------------------------------------- Trimmed male interaction dose=> vacation plans model ------------------------------------------------------------------------------- 1181 . logit hp2vacatn age radhlw3 ageXd3 bf7m avgcumdosew3 bf4m bf4mXd3 bf7mXd3 if > gender==1 Iteration 0: log likelihood = -125.15243 Iteration 1: log likelihood = -103.468 Iteration 2: log likelihood = -95.130161 Iteration 3: log likelihood = -94.528514 Iteration 4: log likelihood = -94.47901 Iteration 5: log likelihood = -94.478195 Iteration 6: log likelihood = -94.478195 Logistic regression Number of obs = 340 LR chi2(8) = 61.35 Prob > chi2 = 0.0000 Log likelihood = -94.478195 Pseudo R2 = 0.2451 ------------------------------------------------------------------------------ hp2vacatn | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0800514 .0379791 2.11 0.035 .0056137 .1544891 radhlw3 | -.0025156 .0070187 -0.36 0.720 -.0162721 .0112409 ageXd3 | -.0428824 .0401478 -1.07 0.285 -.1215705 .0358058 bf7m | .0002096 .000436 0.48 0.631 -.0006449 .001064 avgcumdosew3 | 3.600094 3.230198 1.11 0.265 -2.730977 9.931165 bf4m | -.1155875 .069371 -1.67 0.096 -.2515523 .0203772 bf4mXd3 | -.0793872 .0595624 -1.33 0.183 -.1961273 .037353 bf7mXd3 | .0002138 .0002797 0.76 0.445 -.0003343 .000762 _cons | -4.31894 3.045103 -1.42 0.156 -10.28723 1.649352 ------------------------------------------------------------------------------ Note: 1 failure and 0 successes completely determined. 1182 . 1183 . scalar vactnModMw3 ="none" 1184 . 1185 . di as input "Trimmed Female model wave 3 main effects dose-hp2vacatn model " Trimmed Female model wave 3 main effects dose-hp2vacatn model 1186 . forvalues j=3/3 { 2. local w3bf bf1 bf4 bf2 bf4m bf5m bf7m bf8 bf15m bf17 bf20 bf22 bf29 bf30 > bf40 3. 1187 . xi: logistic hp2vacatn age radhlw`j' avgcumdosew`j' /// > deaw`j' suchrw`j' /// > if gender==2, coef nolog difficult iterate(50) 4. 1188 . } Logistic regression Number of obs = 363 LR chi2(5) = 69.60 Prob > chi2 = 0.0000 Log likelihood = -132.71672 Pseudo R2 = 0.2077 ------------------------------------------------------------------------------ hp2vacatn | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0916152 .0157813 5.81 0.000 .0606844 .1225459 radhlw3 | .0117344 .0050394 2.33 0.020 .0018573 .0216115 avgcumdosew3 | .0985606 .0692713 1.42 0.155 -.0372087 .2343299 deaw3 | .3433813 .158229 2.17 0.030 .0332581 .6535045 suchrw3 | -.0061918 .0037117 -1.67 0.095 -.0134666 .0010831 _cons | -7.50211 .9350027 -8.02 0.000 -9.334682 -5.669539 ------------------------------------------------------------------------------ 1189 . 1190 . scalar SigDoseVactnMw3 = "no" 1191 . 1192 . * summary of male moderating effects: no sign main dose effect in main effec > ts model 1193 . * no signif male moderators 1194 . * 3 significant main effects in main effects model 1195 . 1196 . * summary of female moderation main effects: no signif main dose effect 1197 . * 3 signif main effects 1198 . 1199 . local cn9:colnames(e(b)) 1200 . di "`cn9'" age radhlw3 avgcumdosew3 deaw3 suchrw3 _cons 1201 . local len9 = length("`cn9'") 1202 . di `len9' 44 1203 . local len9b = `len9' - 6 1204 . di `len9b' 38 1205 . local myvarlist = substr("`cn9'",1,`len9b') 1206 . di "`myvarlist'" age radhlw3 avgcumdosew3 deaw3 suchrw3 1207 . 1208 . 1209 . foreach var in `myvarlist' { 2. cap gen `var'Xd3 = `var'*avgcumdosew3 3. } 1210 . 1211 . 1212 . * female dose vacatn w3 models 1213 . 1214 . title4 "trimmed hp2vacatn wave3 main effects models for H1" ------------------------------------------------------------------------------- trimmed hp2vacatn wave3 main effects models for H1 ------------------------------------------------------------------------------- 1215 . di as input "For females hp2vacatn on wave3" For females hp2vacatn on wave3 1216 . sw, pr(.1):logit hp2vacatn `myvarlist' if gender==2 begin with full model p = 0.1548 >= 0.1000 removing avgcumdosew3 p = 0.1174 >= 0.1000 removing suchrw3 Logistic regression Number of obs = 363 LR chi2(3) = 65.18 Prob > chi2 = 0.0000 Log likelihood = -134.92371 Pseudo R2 = 0.1946 ------------------------------------------------------------------------------ hp2vacatn | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0872837 .0154104 5.66 0.000 .0570799 .1174875 radhlw3 | .0131054 .0049947 2.62 0.009 .003316 .0228948 deaw3 | .2791769 .1537034 1.82 0.069 -.0220763 .5804301 _cons | -7.430633 .9404734 -7.90 0.000 -9.273927 -5.587339 ------------------------------------------------------------------------------ 1217 . estat class Logistic model for hp2vacatn -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 15 5 | 20 - | 48 295 | 343 -----------+--------------------------+----------- Total | 63 300 | 363 Classified + if predicted Pr(D) >= .5 True D defined as hp2vacatn != 0 -------------------------------------------------- Sensitivity Pr( +| D) 23.81% Specificity Pr( -|~D) 98.33% Positive predictive value Pr( D| +) 75.00% Negative predictive value Pr(~D| -) 86.01% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 1.67% False - rate for true D Pr( -| D) 76.19% False + rate for classified + Pr(~D| +) 25.00% False - rate for classified - Pr( D| -) 13.99% -------------------------------------------------- Correctly classified 85.40% -------------------------------------------------- 1218 . estat gof Logistic model for hp2vacatn, goodness-of-fit test number of observations = 363 number of covariate patterns = 291 Pearson chi2(287) = 335.34 Prob > chi2 = 0.0261 1219 . fitstat Measures of Fit for logit of hp2vacatn Log-Lik Intercept Only: -167.516 Log-Lik Full Model: -134.924 D(359): 269.847 LR(3): 65.185 Prob > LR: 0.000 McFadden's R2: 0.195 McFadden's Adj R2: 0.171 Maximum Likelihood R2: 0.164 Cragg & Uhler's R2: 0.273 McKelvey and Zavoina's R2: 0.341 Efron's R2: 0.227 Variance of y*: 4.992 Variance of error: 3.290 Count R2: 0.854 Adj Count R2: 0.159 AIC: 0.765 AIC*n: 277.847 BIC: -1846.243 BIC': -47.501 1220 . 1221 . scalar SigDoseVactnFw3 = "no" 1222 . scalar MainEffVactnFw3 = "age radhlw3 deaw3" 1223 . 1224 . di as result " Full moderator model for females for dose=> Vacation plans" Full moderator model for females for dose=> Vacation plans 1225 . logit hp2vacatn age radhlw3 deaw3 suchrw3 avgcumdosew3 ageXd3 radhlw3Xd3 deaw > 3Xd3 /// > suchrw3Xd3 havmilsq if gender==2 Iteration 0: log likelihood = -167.516 Iteration 1: log likelihood = -131.66933 Iteration 2: log likelihood = -127.22328 Iteration 3: log likelihood = -127.01792 Iteration 4: log likelihood = -127.01661 Iteration 5: log likelihood = -127.0166 Logistic regression Number of obs = 363 LR chi2(10) = 81.00 Prob > chi2 = 0.0000 Log likelihood = -127.0166 Pseudo R2 = 0.2418 ------------------------------------------------------------------------------ hp2vacatn | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .1051773 .0237507 4.43 0.000 .0586268 .1517279 radhlw3 | .0086474 .0071994 1.20 0.230 -.0054632 .0227581 deaw3 | -.018111 .2299772 -0.08 0.937 -.4688582 .4326361 suchrw3 | -.0131465 .0051799 -2.54 0.011 -.0232988 -.0029941 avgcumdosew3 | -.4455554 1.249774 -0.36 0.721 -2.895067 2.003957 ageXd3 | -.0067688 .0178685 -0.38 0.705 -.0417904 .0282529 radhlw3Xd3 | .0045845 .0048868 0.94 0.348 -.0049935 .0141625 deaw3Xd3 | .3320908 .1608104 2.07 0.039 .0169081 .6472735 suchrw3Xd3 | .0055826 .0032326 1.73 0.084 -.0007533 .0119184 havmilsq | -3.31e-07 8.64e-07 -0.38 0.701 -2.02e-06 1.36e-06 _cons | -7.357805 1.47262 -5.00 0.000 -10.24409 -4.471523 ------------------------------------------------------------------------------ 1226 . 1227 . di as result "trimmed female moderator model for dose=> vacation plans" trimmed female moderator model for dose=> vacation plans 1228 . logit hp2vacatn age avgcumdosew3 suchrw3 deaw3 deaw3Xd3 if gender==2 Iteration 0: log likelihood = -167.516 Iteration 1: log likelihood = -136.37785 Iteration 2: log likelihood = -133.24846 Iteration 3: log likelihood = -133.21681 Iteration 4: log likelihood = -133.21679 Iteration 5: log likelihood = -133.21679 Logistic regression Number of obs = 363 LR chi2(5) = 68.60 Prob > chi2 = 0.0000 Log likelihood = -133.21679 Pseudo R2 = 0.2048 ------------------------------------------------------------------------------ hp2vacatn | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0997666 .0154683 6.45 0.000 .0694493 .1300839 avgcumdosew3 | .0469958 .0857324 0.55 0.584 -.1210366 .2150283 suchrw3 | -.0068988 .0037456 -1.84 0.065 -.01424 .0004423 deaw3 | .1355918 .2007115 0.68 0.499 -.2577956 .5289792 deaw3Xd3 | .2112882 .1167631 1.81 0.070 -.0175632 .4401397 _cons | -7.069816 .8971072 -7.88 0.000 -8.828114 -5.311518 ------------------------------------------------------------------------------ 1229 . 1230 . scalar VacatnModFw3 = "none" 1231 . *xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx > xxx 1232 . cap gen hp2vactn = HP2vacatn 1233 . title4 "Chunk 9 HP2vacatn plans mediator models for males" ------------------------------------------------------------------------------- Chunk 9 HP2vacatn plans mediator models for males ------------------------------------------------------------------------------- 1234 . 1235 . * age is a mediator for males 1236 . glm age avgcumdosew3 if gender==1, fam(gaus) link(identity) Iteration 0: log likelihood = -1330.6336 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = 147.7142 Deviance = 49927.38549 (1/df) Deviance = 147.7142 Pearson = 49927.38549 (1/df) Pearson = 147.7142 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 7.839021 Log likelihood = -1330.633586 BIC = 47957.2 ------------------------------------------------------------------------------ | OIM age | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | .5433648 .2472657 2.20 0.028 .058733 1.027997 _cons | 48.52021 .7247376 66.95 0.000 47.09975 49.94067 ------------------------------------------------------------------------------ 1237 . glm hp2vactn age if gender==1, fam(bin) irls scale(dev) link(probit) Iteration 1: deviance = 230.5483 Iteration 2: deviance = 224.6254 Iteration 3: deviance = 224.4149 Iteration 4: deviance = 224.4147 Iteration 5: deviance = 224.4147 Generalized linear models No. of obs = 340 Optimization : MQL Fisher scoring Residual df = 338 (IRLS EIM) Scale parameter = 1 Deviance = 224.4146771 (1/df) Deviance = .6639487 Pearson = 345.2370578 (1/df) Pearson = 1.021411 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1745.769 ------------------------------------------------------------------------------ | EIM hp2vactn | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0377399 .0063833 5.91 0.000 .0252289 .0502509 _cons | -3.150096 .3549593 -8.87 0.000 -3.845803 -2.454388 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 1238 . 1239 . * illness is a mediating effect for males = > vacatn for men 1240 . des illw3 storage display value variable name type format label variable label ------------------------------------------------------------------------------- illw3 double %8.0g Total number of illnesses experienced in time period 1996-NOW 1241 . glm illw3 avgcumdosew3 if gender==1, fam(gaus) link(identity) Iteration 0: log likelihood = -461.99206 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = .8919217 Deviance = 301.469521 (1/df) Deviance = .8919217 Pearson = 301.469521 (1/df) Pearson = .8919217 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 2.729365 Log likelihood = -461.9920626 BIC = -1668.714 ------------------------------------------------------------------------------ | OIM illw3 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | .038211 .0192139 1.99 0.047 .0005524 .0758696 _cons | .4504952 .0563162 8.00 0.000 .3401176 .5608729 ------------------------------------------------------------------------------ 1242 . glm hp2vactn illw3 if gender==1, fam(bin) irls scale(dev) link(probit) Iteration 1: deviance = 247.0817 Iteration 2: deviance = 245.9165 Iteration 3: deviance = 245.9101 Iteration 4: deviance = 245.9101 Iteration 5: deviance = 245.9101 Generalized linear models No. of obs = 340 Optimization : MQL Fisher scoring Residual df = 338 (IRLS EIM) Scale parameter = 1 Deviance = 245.9100555 (1/df) Deviance = .7275445 Pearson = 334.9802312 (1/df) Pearson = .9910658 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1724.274 ------------------------------------------------------------------------------ | EIM hp2vactn | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- illw3 | .1787158 .0693787 2.58 0.010 .0427362 .3146955 _cons | -1.278417 .0876012 -14.59 0.000 -1.450112 -1.106721 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 1243 . 1244 . des radhlw3 storage display value variable name type format label variable label ------------------------------------------------------------------------------- radhlw3 double %8.0g Self-perceived Chornobyl health threat in wave 3 1245 . glm radhlw3 avgcumdosew3 if gender==1, fam(gaus) link(identity) Iteration 0: log likelihood = -1695.1855 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = 1261.052 Deviance = 426235.7205 (1/df) Deviance = 1261.052 Pearson = 426235.7205 (1/df) Pearson = 1261.052 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 9.983444 Log likelihood = -1695.185473 BIC = 424265.5 ------------------------------------------------------------------------------ | OIM radhlw3 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | .9606492 .7224692 1.33 0.184 -.4553645 2.376663 _cons | 46.19995 2.117563 21.82 0.000 42.0496 50.3503 ------------------------------------------------------------------------------ 1246 . glm hp2vactn radhlw3 if gender==1, fam(bin) irls scale(dev) link(probit) Iteration 1: deviance = 235.0568 Iteration 2: deviance = 230.1721 Iteration 3: deviance = 230.0122 Iteration 4: deviance = 230.0119 Iteration 5: deviance = 230.0119 Generalized linear models No. of obs = 340 Optimization : MQL Fisher scoring Residual df = 338 (IRLS EIM) Scale parameter = 1 Deviance = 230.0118626 (1/df) Deviance = .6805085 Pearson = 338.3882304 (1/df) Pearson = 1.001149 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1740.172 ------------------------------------------------------------------------------ | EIM hp2vactn | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- radhlw3 | .0115045 .0021825 5.27 0.000 .0072269 .0157822 _cons | -1.814894 .1529622 -11.86 0.000 -2.114694 -1.515093 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 1247 . 1248 . title4 "HP2vacatn plans mediator models for females" ------------------------------------------------------------------------------- HP2vacatn plans mediator models for females ------------------------------------------------------------------------------- 1249 . 1250 . * age is a mediator for females 1251 . glm age avgcumdosew3 if gender==2, fam(gaus) link(identity) Iteration 0: log likelihood = -1408.064 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = 137.7687 Deviance = 49734.51399 (1/df) Deviance = 137.7687 Pearson = 49734.51399 (1/df) Pearson = 137.7687 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 7.768948 Log likelihood = -1408.06405 BIC = 47606.63 ------------------------------------------------------------------------------ | OIM age | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | 1.058366 .3512614 3.01 0.003 .3699069 1.746826 _cons | 48.94293 .7468173 65.54 0.000 47.47919 50.40666 ------------------------------------------------------------------------------ 1252 . glm hp2vactn age if gender==2, fam(bin) irls scale(dev) link(probit) Iteration 1: deviance = 288.2228 Iteration 2: deviance = 282.9212 Iteration 3: deviance = 282.8 Iteration 4: deviance = 282.8 Iteration 5: deviance = 282.8 Generalized linear models No. of obs = 363 Optimization : MQL Fisher scoring Residual df = 361 (IRLS EIM) Scale parameter = 1 Deviance = 282.7999835 (1/df) Deviance = .7833795 Pearson = 396.9154874 (1/df) Pearson = 1.099489 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1845.079 ------------------------------------------------------------------------------ | EIM hp2vactn | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0510238 .0068535 7.44 0.000 .0375912 .0644564 _cons | -3.660305 .3855366 -9.49 0.000 -4.415943 -2.904667 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 1253 . 1254 . * illness is a mediating effect for females = > vacatn 1255 . des illw3 storage display value variable name type format label variable label ------------------------------------------------------------------------------- illw3 double %8.0g Total number of illnesses experienced in time period 1996-NOW 1256 . glm illw3 avgcumdosew3 if gender==2, fam(gaus) link(identity) Iteration 0: log likelihood = -562.81042 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = 1.308042 Deviance = 472.2033151 (1/df) Deviance = 1.308042 Pearson = 472.2033151 (1/df) Pearson = 1.308042 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 3.111903 Log likelihood = -562.8104237 BIC = -1655.676 ------------------------------------------------------------------------------ | OIM illw3 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | .1284565 .0342268 3.75 0.000 .0613733 .1955398 _cons | .5563644 .0727696 7.65 0.000 .4137387 .6989902 ------------------------------------------------------------------------------ 1257 . glm hp2vactn illw3 if gender==2, fam(bin) irls scale(dev) link(probit) Iteration 1: deviance = 334.6961 Iteration 2: deviance = 334.6441 Iteration 3: deviance = 334.6441 Iteration 4: deviance = 334.6441 Generalized linear models No. of obs = 363 Optimization : MQL Fisher scoring Residual df = 361 (IRLS EIM) Scale parameter = 1 Deviance = 334.644123 (1/df) Deviance = .926992 Pearson = 362.8044598 (1/df) Pearson = 1.004999 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1793.235 ------------------------------------------------------------------------------ | EIM hp2vactn | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- illw3 | .041243 .0622857 0.66 0.508 -.0808348 .1633209 _cons | -.9706284 .0880746 -11.02 0.000 -1.143252 -.7980053 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 1258 . 1259 . * radhlw3 is a mediating effect for females => vactn 1260 . des radhlw3 storage display value variable name type format label variable label ------------------------------------------------------------------------------- radhlw3 double %8.0g Self-perceived Chornobyl health threat in wave 3 1261 . glm radhlw3 avgcumdosew3 if gender==2, fam(gaus) link(identity) Iteration 0: log likelihood = -1798.7074 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = 1185.454 Deviance = 427948.9522 (1/df) Deviance = 1185.454 Pearson = 427948.9522 (1/df) Pearson = 1185.454 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 9.921253 Log likelihood = -1798.707367 BIC = 425821.1 ------------------------------------------------------------------------------ | OIM radhlw3 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew3 | 2.751602 1.03038 2.67 0.008 .7320943 4.77111 _cons | 57.70689 2.190692 26.34 0.000 53.41321 62.00057 ------------------------------------------------------------------------------ 1262 . glm hp2vactn radhlw3 if gender==2, fam(bin) irls scale(dev) link(probit) Iteration 1: deviance = 316.824 Iteration 2: deviance = 314.9168 Iteration 3: deviance = 314.905 Iteration 4: deviance = 314.905 Iteration 5: deviance = 314.905 Generalized linear models No. of obs = 363 Optimization : MQL Fisher scoring Residual df = 361 (IRLS EIM) Scale parameter = 1 Deviance = 314.9050287 (1/df) Deviance = .8723131 Pearson = 371.6251351 (1/df) Pearson = 1.029433 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1812.974 ------------------------------------------------------------------------------ | EIM hp2vactn | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- radhlw3 | .0106148 .0023181 4.58 0.000 .0060715 .0151582 _cons | -1.651184 .179583 -9.19 0.000 -2.003161 -1.299208 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 1263 . 1264 . * summary of male moderating effects: no sign main dose effect in main effec > ts model 1265 . * no signif male moderators 1266 . * 3 significant main effects in main effects model 1267 . 1268 . scalar VactnMedMw3 = "age illw3" 1269 . scalar VactnMedFw3 = "age illw3 radhlw3" 1270 . 1271 . *xx summary of moderator effects for females: 1272 . * no signif main dose effect 1273 . * 3 signif main effects in main effect model 1274 . * 1 moderator: deaw3Xd3 1275 . title4 "7. SUMMARY MATRIX of dose - vacation plans impact" ------------------------------------------------------------------------------- 7. SUMMARY MATRIX of dose - vacation plans impact ------------------------------------------------------------------------------- 1276 . set more off 1277 . matrix define HP2vactnMw3 = J(1,8, 0) 1278 . matrix define HP2vactnFw3 = J(1,8, 0) 1279 . matrix colnames HP2vactnMw3= hypnum ptnum wave gender medsig numMAsig numMod > sig numMed 1280 . matrix colnames HP2vactnFw3= hypnum ptnum wave gender medsig numMAsig numMod > sig numMed 1281 . matrix define HP2vactnMw3= (1, 2, 3, 1, 0, 3, 0, 2 ) 1282 . matrix define HP2vactnFw3= (1, 2, 3, 2, 0, 3, 1, 3 ) 1283 . matrix rowname HP2vactnMw3 = HP2vactnM 1284 . matrix rowname HP2vactnFw3 = HP2vactnF 1285 . matlist HP2vactnMw3 | c1 c2 c3 c4 c5 c6 > -------------+----------------------------------------------------------------- - HP2vactnM | 1 2 3 1 0 3 > | c7 c8 -------------+---------------------- HP2vactnM | 0 2 1286 . matlist HP2vactnFw3 | c1 c2 c3 c4 c5 c6 > -------------+----------------------------------------------------------------- - HP2vactnF | 1 2 3 2 0 3 > | c7 c8 -------------+---------------------- HP2vactnF | 1 3 1287 . matrix define H1pt2w3=(HP2wkMw3 \ HP2wkFw3 \ HP2hmcrMw3 \ HP2hmcrFw3 \ HP2spM > w3 \ HP2spFw3 \ HP2prbfamMw3 \ HP2prbfamFw3 \ HP2inthbMw3 \ HP2inthbFw3 \ HP2 > vactnMw3 \ HP2vactnFw3 ) 1288 . 1289 . matlist H1pt2w3 | c1 c2 c3 c4 c5 c6 > -------------+----------------------------------------------------------------- - r1 | 1 2 3 1 0 4 > r1 | 1 2 3 2 0 1 > r1 | 1 2 3 1 0 4 > r1 | 1 2 3 2 0 2 > HP2spMw3 | 1 2 3 1 0 2 > HP2spFw3 | 1 2 3 2 1 5 > HP2prbfamM | 1 2 3 1 0 5 > HP2prbfamF | 1 2 3 2 0 2 > HP2inthbM | 1 2 3 1 0 3 > HP2inthobF | 1 2 3 2 0 3 > HP2vactnM | 1 2 3 1 0 3 > HP2vactnF | 1 2 3 2 0 3 > | c7 c8 -------------+---------------------- r1 | 0 4 r1 | 0 6 r1 | 0 2 r1 | 0 2 HP2spMw3 | 0 1 HP2spFw3 | 5 3 HP2prbfamM | 0 1 HP2prbfamF | 2 2 HP2inthbM | 0 2 HP2inthobF | 0 3 HP2vactnM | 0 2 HP2vactnF | 1 3 1290 . matrix colnames H1pt2w3 = hypnum ptnum wave gender medsig numMAsig numMo > dsig numMed 1291 . matrix rownames H1pt2w3 =HP2wkMw3 HP2wkFw3 HP2hmcrMw3 HP2hmcrFw3 HP2socprbMw3 > HP2socprbFw3 HP2prbfamMw3 HP2prbfamFw3 HP2inthbMw3 HP2inthbFw3 HP2vacatnMw3 > HP2vacatnFw3 1292 . matlist H1pt2w3 | hypnum ptnum wave gender medsig numMAsig > -------------+----------------------------------------------------------------- - HP2wkMw3 | 1 2 3 1 0 4 > HP2wkFw3 | 1 2 3 2 0 1 > HP2hmcrMw3 | 1 2 3 1 0 4 > HP2hmcrFw3 | 1 2 3 2 0 2 > HP2socprbMw3 | 1 2 3 1 0 2 > HP2socprbFw3 | 1 2 3 2 1 5 > HP2prbfamMw3 | 1 2 3 1 0 5 > HP2prbfamFw3 | 1 2 3 2 0 2 > HP2inthbMw3 | 1 2 3 1 0 3 > HP2inthbFw3 | 1 2 3 2 0 3 > HP2vacatnMw3 | 1 2 3 1 0 3 > HP2vacatnFw3 | 1 2 3 2 0 3 > | numModsig numMed -------------+---------------------- HP2wkMw3 | 0 4 HP2wkFw3 | 0 6 HP2hmcrMw3 | 0 2 HP2hmcrFw3 | 0 2 HP2socprbMw3 | 0 1 HP2socprbFw3 | 5 3 HP2prbfamMw3 | 0 1 HP2prbfamFw3 | 2 2 HP2inthbMw3 | 0 2 HP2inthbFw3 | 0 3 HP2vacatnMw3 | 0 2 HP2vacatnFw3 | 1 3 1293 . 1294 . 1295 . 1296 . 1297 . 1298 . 1299 . sjlog close, replace