___ ____ ____ ____ ____(R) /__ / ____/ / ____/ ___/ / /___/ / /___/ Statistics/Data Analysis 1 . set seed 1010101 2 . set matsize 11000 3 . 4 . 5 . ******* 6 . 7 . * This script requires pre-installation of spost2 by J. Scott Long for fits > tat command 8 . * It also requires installation of title2.ado, title3.ado 9 . * 10 . * for the fitstat command to function 11 . ****** 12 . 13 . global User "Robert Alan Yaffee" 14 . * 15 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 . 47 . ***-------------------------------------------------------------------------- > ---------------------------------------- 48 . 49 . * Part 2 Nottingham subscales 50 . * 1: hp2work 51 . * 2: hp2hmcare 52 . * 3: hp2probsoc 53 . * 4: hp2pbfhm 54 . * 5: hp2sexlife 55 . * 6: hp2inthob 56 . * 7: hp2vacatn 57 . 58 . local dvwhole HP2work-HP2vacatn 59 . local dv2 HP2work HP2hmcare HP2probsoc HP2pbfhm HP2sxlife HP2inthob HP2vacatn 60 . 61 . 62 . 63 . ************************************* 64 . di "$User" Robert Alan Yaffee 65 . 66 . title "Testing part 2 of hypothesis 1 for wave 2" ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Testing part 2 of hypothesis 1 for wave 2 ***** ***** ***** ***** ***** ***** 16 Jun 2012 21:51:20 ***** ******************************************************************************* ******************************************************************************* 67 . 68 . cd /Users/robertyaffee/Documents/data/research/chwk/phase3/Htests/H1tests/h1p > t2 /Users/robertyaffee/Documents/data/research/chwk/phase3/Htests/h1tests/h1pt2 69 . use chwide16june2012, clear (Zero for missing on all icdx) 70 . cd /Users/robertyaffee/Documents/data/research/chwk/phase3/Htests/H1tests/h1p > t2 /Users/robertyaffee/Documents/data/research/chwk/phase3/Htests/h1tests/h1pt2 71 . 72 . 73 . di "{hline}" ------------------------------------------------------------------------------- 74 . di "{hline}" ------------------------------------------------------------------------------- 75 . title "Chunk 1 Hyp 1:radiation dose and Nottingham Health profile subscales" ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** *****Chunk 1 Hyp 1:radiation dose and Nottingham Health profile subscales ***** ***** ***** ***** ***** ***** 16 Jun 2012 21:51:21 ***** ******************************************************************************* ******************************************************************************* 76 . 77 . 78 . // there is substantial intercorrelation among the items warranting a 79 . // multivariate regression model 80 . cap dummies educ 81 . cap order educ1-educ8, after(educ) 82 . 83 . * These variables are substantially correlated 84 . 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 | 85 . 86 . cap gen havmilsq = havmil^2 87 . 88 . cap rename Havmil havmil 89 . // controlling for potential confounders 90 . // socio-demographics age gender educ income occp marstat children inc 91 . // distance from accident side 92 . // perceived Chornobyl related health threat to oneself 93 . 94 . local w1bf bf1 bf4 bf9 bf10 bf11 bf4m bf15m bf20 bf22 bf30 bf40 95 . local w2bf bf1 bf4 bf6 bf7 bf14 bf15 bf40 96 . local w3bf bf1 bf4 bf2 bf4m bf5m bf7m bf8 bf15m bf17 bf20 bf22 bf29 bf30 bf40 97 . 98 . *---------------------------------------------------------------------------- > --- 99 . * Hypothesis 1 Part 2 Wave 2 tests male and female 100 . * endogneous Nottingham pt 2 subscales: HP2work HP2hmcare HP2probsoc HP2pbfhm > /// > * HP2sxlife HP2inthob HP2vacatn 101 . * structure of models 102 . * 1. general models on all Pt 2 subscales with all potential confounders 103 . * 2. trimmed models on all Pt 2 subscales with from all potential confound > ers 104 . * 3. from trimmed models examination of possible moderator variables 105 . * 4. from trimmed models examination of possible mediator variables 106 . * 5. Summary analysis and model evaluation of final models only 107 . * program is divided into 8 chunks one a general model and 1 for each 108 . * endogenous variable 109 . *---------------------------------------------------------------------------- > --- 110 . * Chunk 1 General models for all part 2 of Nottingham Health Profile 111 . 112 . title " H1: Test of hypothesis 1: Pt 2 wave 2 general models" ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** H1: Test of hypothesis 1: Pt 2 wave 2 general models ***** ***** ***** ***** ***** ***** 16 Jun 2012 21:51:21 ***** ******************************************************************************* ******************************************************************************* 113 . forvalues j = 2/2 { 2. set more off 3. 114 . des age educ1-educ7 marrw`j'1-marrw`j'6 inc1w`j'-inc4w`j' /// > bf1 bf4 bf9 bf11 bf4m bf15m bf30 bf40 4. 115 . foreach var in HP2work HP2hmcare HP2probsoc HP2pbfhm HP2sxlife HP2inthob // > / > HP2vacatn { 5. forvalues k=1/2 { 6. local w2bf bf1 bf4 bf6 bf7 bf14 bf15 bf40 7. di _skip(4) 8. 116 . di as input "Full main model for `var' for wave= `j' " 9. di _skip(4) 10. di as input "chunk 2 H1 test:Gender= `k' model Wave = `j' for `e(depvar > )' " 11. di _skip(4) 12. title "Full Nottingham Part 2 `var' subscale models" "wave `j' for gender= > =`k' " 13. 117 . 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 difficult iterate(50) 14. estat class 15. estat gof 16. fitstat 17. } 18. } 19. } 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 marrw21 byte %8.0g marrw2==1. single marrw22 byte %8.0g marrw2==2. cohabitating marrw23 byte %8.0g marrw2==3. married marrw24 byte %8.0g marrw2==4. separated marrw25 byte %8.0g marrw2==5. divorced marrw26 byte %8.0g marrw2==6. widowed inc1w2 double %15.0g LABJ Income is not sufficient for basic neccessities in 1996 inc2w2 double %15.0g LABJ Income is just sufficient for basic neccessities in 1996 inc3w2 double %15.0g LABJ Income is sufficient for basics plus extra purchases/savings in 1996 inc4w2 double %15.0g LABJ Income allows to comfortably afford luxury items in 1996 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= 2 chunk 2 H1 test:Gender= 1 model Wave = 2 for HP2probsoc ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Full Nottingham Part 2 HP2work subscale models ***** ***** wave 2 for gender==1 ***** ***** ***** ***** ***** ***** 16 Jun 2012 21:51:21 ***** ******************************************************************************* ******************************************************************************* i.educ _Ieduc_1-8 (naturally coded; _Ieduc_1 omitted) note: _Ieduc_4 != 0 predicts failure perfectly _Ieduc_4 dropped and 12 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: sepaw2 != 0 predicts failure perfectly sepaw2 dropped and 6 obs not used note: _Ieduc_6 omitted because of collinearity note: bf15 omitted because of collinearity Logistic regression Number of obs = 308 LR chi2(42) = 109.94 Prob > chi2 = 0.0000 Log likelihood = -106.34944 Pseudo R2 = 0.3408 ------------------------------------------------------------------------------ HP2work | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | -.0001692 .02372 -0.01 0.994 -.0466595 .0463212 _Ieduc_2 | .9181743 1.013818 0.91 0.365 -1.068872 2.90522 _Ieduc_3 | -.0025163 .4641718 -0.01 0.996 -.9122764 .9072438 _Ieduc_4 | 0 (omitted) _Ieduc_5 | .7217689 .6474494 1.11 0.265 -.5472086 1.990746 _Ieduc_6 | 0 (omitted) _Ieduc_7 | 0 (omitted) _Ieduc_8 | 0 (omitted) occ1w2 | -2.033983 2.039062 -1.00 0.319 -6.030472 1.962506 occ2w2 | -1.10022 2.055368 -0.54 0.592 -5.128666 2.928227 occ3w2 | -1.57744 2.098973 -0.75 0.452 -5.691352 2.536471 occ4w2 | -.7778101 2.07516 -0.37 0.708 -4.845048 3.289428 occ5w2 | -.1994034 2.080334 -0.10 0.924 -4.276783 3.877976 occ6w2 | .5724938 2.922442 0.20 0.845 -5.155386 6.300374 occ7w2 | 1.385601 2.162361 0.64 0.522 -2.852549 5.623751 occ8w2 | -2.621626 2.185931 -1.20 0.230 -6.905973 1.66272 marrw21 | 14.46418 1445.103 0.01 0.992 -2817.886 2846.815 marrw22 | 16.06999 1445.104 0.01 0.991 -2816.281 2848.421 marrw23 | 13.00974 1445.103 0.01 0.993 -2819.341 2845.36 marrw25 | 15.20349 1445.106 0.01 0.992 -2817.151 2847.558 marrw26 | 11.50222 1445.104 0.01 0.994 -2820.85 2843.855 inc1w2 | -1.510512 2.275504 -0.66 0.507 -5.970418 2.949394 inc2w2 | -.2432446 2.068579 -0.12 0.906 -4.297585 3.811096 inc3w2 | 1.229267 2.059579 0.60 0.551 -2.807434 5.265968 inc4w2 | .0340459 2.516571 0.01 0.989 -4.898343 4.966435 radhlw2 | -.0036868 .0074975 -0.49 0.623 -.0183817 .0110081 havmil | .0013907 .0046392 0.30 0.764 -.0077019 .0104833 avgcumdosew2 | .0423433 .0838158 0.51 0.613 -.1219326 .2066192 bf1 | -.0106479 .0111601 -0.95 0.340 -.0325212 .0112255 bf4 | -.1742962 .0530725 -3.28 0.001 -.2783165 -.070276 bf6 | .0126216 .0084824 1.49 0.137 -.0040036 .0292468 bf7 | .1335412 .0775552 1.72 0.085 -.0184641 .2855465 bf14 | .000083 .0000711 1.17 0.243 -.0000564 .0002224 bf15 | 0 (omitted) bf40 | .4649883 .132263 3.52 0.000 .2057576 .724219 deaw2 | .0562824 .3164534 0.18 0.859 -.5639548 .6765196 dvcew2 | .8659697 2.382497 0.36 0.716 -3.803639 5.535578 sepaw2 | 0 (omitted) accdw2 | .5552759 .4404199 1.26 0.207 -.3079312 1.418483 movew2 | .6056941 .4689768 1.29 0.197 -.3134835 1.524872 illw2 | -.0279332 .3103275 -0.09 0.928 -.6361639 .5802975 shfamw2 | .0059196 .0069893 0.85 0.397 -.0077792 .0196183 shhlw2 | .0168978 .0087333 1.93 0.053 -.000219 .0340147 shjobw2 | -.0044984 .0081883 -0.55 0.583 -.0205472 .0115504 shrelaw2 | -.0237032 .0083387 -2.84 0.004 -.0400468 -.0073596 suprtw2 | -.0017568 .0059642 -0.29 0.768 -.0134464 .0099328 suchrw2 | .003038 .005693 0.53 0.594 -.00812 .014196 havmilsq | -1.38e-06 6.35e-06 -0.22 0.828 -.0000138 .0000111 _cons | -14.33587 1445.105 -0.01 0.992 -2846.689 2818.017 ------------------------------------------------------------------------------ Logistic model for HP2work -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 35 13 | 48 - | 32 228 | 260 -----------+--------------------------+----------- Total | 67 241 | 308 Classified + if predicted Pr(D) >= .5 True D defined as HP2work != 0 -------------------------------------------------- Sensitivity Pr( +| D) 52.24% Specificity Pr( -|~D) 94.61% Positive predictive value Pr( D| +) 72.92% Negative predictive value Pr(~D| -) 87.69% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 5.39% False - rate for true D Pr( -| D) 47.76% False + rate for classified + Pr(~D| +) 27.08% False - rate for classified - Pr( D| -) 12.31% -------------------------------------------------- Correctly classified 85.39% -------------------------------------------------- Logistic model for HP2work, goodness-of-fit test number of observations = 308 number of covariate patterns = 308 Pearson chi2(265) = 283.15 Prob > chi2 = 0.2119 Measures of Fit for logistic of HP2work Log-Lik Intercept Only: -161.320 Log-Lik Full Model: -106.349 D(259): 212.699 LR(42): 109.942 Prob > LR: 0.000 McFadden's R2: 0.341 McFadden's Adj R2: 0.037 Maximum Likelihood R2: 0.300 Cragg & Uhler's R2: 0.462 McKelvey and Zavoina's R2: 0.625 Efron's R2: 0.371 Variance of y*: 8.782 Variance of error: 3.290 Count R2: 0.854 Adj Count R2: 0.328 AIC: 1.009 AIC*n: 310.699 BIC: -1271.397 BIC': 130.723 Full main model for HP2work for wave= 2 chunk 2 H1 test:Gender= 2 model Wave = 2 for HP2work ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Full Nottingham Part 2 HP2work subscale models ***** ***** wave 2 for gender==2 ***** ***** ***** ***** ***** ***** 16 Jun 2012 21:51:22 ***** ******************************************************************************* ******************************************************************************* i.educ _Ieduc_1-8 (naturally coded; _Ieduc_1 omitted) note: sepaw2 != 0 predicts failure perfectly sepaw2 dropped and 8 obs not used note: _Ieduc_8 omitted because of collinearity note: marrw26 omitted because of collinearity note: bf15 omitted because of collinearity Logistic regression Number of obs = 354 LR chi2(44) = 104.77 Prob > chi2 = 0.0000 Log likelihood = -150.43517 Pseudo R2 = 0.2583 ------------------------------------------------------------------------------ HP2work | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0369848 .0167931 2.20 0.028 .0040708 .0698987 _Ieduc_2 | -13.278 655.1046 -0.02 0.984 -1297.259 1270.703 _Ieduc_3 | -13.76722 655.1045 -0.02 0.983 -1297.749 1270.214 _Ieduc_4 | -12.56241 655.1048 -0.02 0.985 -1296.544 1271.419 _Ieduc_5 | -14.16942 655.1047 -0.02 0.983 -1298.151 1269.812 _Ieduc_6 | -13.46911 655.1045 -0.02 0.984 -1297.45 1270.512 _Ieduc_7 | -13.6852 655.1071 -0.02 0.983 -1297.672 1270.301 _Ieduc_8 | 0 (omitted) occ1w2 | -1.431885 1.490412 -0.96 0.337 -4.353039 1.48927 occ2w2 | -1.067234 1.511451 -0.71 0.480 -4.029624 1.895156 occ3w2 | -.6094536 1.500907 -0.41 0.685 -3.551177 2.33227 occ4w2 | -.7773088 1.581059 -0.49 0.623 -3.876128 2.321511 occ5w2 | -1.784723 1.846534 -0.97 0.334 -5.403863 1.834417 occ6w2 | -1.506062 1.711274 -0.88 0.379 -4.860097 1.847973 occ7w2 | -.374184 1.45347 -0.26 0.797 -3.222934 2.474566 occ8w2 | -.0539674 1.70334 -0.03 0.975 -3.392452 3.284517 marrw21 | -.7235313 1.007239 -0.72 0.473 -2.697684 1.250621 marrw22 | -.7861921 1.258786 -0.62 0.532 -3.253367 1.680983 marrw23 | -.156903 .704389 -0.22 0.824 -1.53748 1.223674 marrw25 | -.4149071 1.124423 -0.37 0.712 -2.618736 1.788922 marrw26 | 0 (omitted) inc1w2 | -.3011188 1.506651 -0.20 0.842 -3.2541 2.651862 inc2w2 | .2687204 1.456307 0.18 0.854 -2.585589 3.12303 inc3w2 | 1.036312 1.469535 0.71 0.481 -1.843923 3.916546 inc4w2 | -.1137536 1.952911 -0.06 0.954 -3.941389 3.713882 radhlw2 | .0092993 .0058818 1.58 0.114 -.0022288 .0208273 havmil | -.0020615 .0026074 -0.79 0.429 -.0071719 .0030489 avgcumdosew2 | .0807064 .0968033 0.83 0.404 -.1090246 .2704374 bf1 | -.004698 .0078862 -0.60 0.551 -.0201547 .0107586 bf4 | -.1182241 .0355711 -3.32 0.001 -.1879422 -.0485059 bf6 | .001791 .0066699 0.27 0.788 -.0112818 .0148637 bf7 | -.0450377 .0737224 -0.61 0.541 -.1895309 .0994556 bf14 | -.0001102 .0000711 -1.55 0.121 -.0002496 .0000292 bf15 | 0 (omitted) bf40 | .0952395 .072172 1.32 0.187 -.046215 .236694 deaw2 | .164384 .1960927 0.84 0.402 -.2199507 .5487186 dvcew2 | -.2821707 1.333785 -0.21 0.832 -2.89634 2.331999 sepaw2 | 0 (omitted) accdw2 | .6916732 .4937096 1.40 0.161 -.2759799 1.659326 movew2 | -.1373653 .5055449 -0.27 0.786 -1.128215 .8534845 illw2 | .1336732 .1739566 0.77 0.442 -.2072754 .4746219 shfamw2 | -.0053174 .0059668 -0.89 0.373 -.0170122 .0063773 shhlw2 | .0054362 .0062416 0.87 0.384 -.0067971 .0176695 shjobw2 | -.0006072 .0057431 -0.11 0.916 -.0118635 .0106491 shrelaw2 | -.0064495 .0065479 -0.98 0.325 -.0192832 .0063841 suprtw2 | -.0047857 .0047915 -1.00 0.318 -.0141769 .0046055 suchrw2 | .009761 .0053132 1.84 0.066 -.0006528 .0201747 havmilsq | 2.04e-07 1.76e-06 0.12 0.908 -3.25e-06 3.65e-06 _cons | 11.57916 655.1066 0.02 0.986 -1272.406 1295.565 ------------------------------------------------------------------------------ Logistic model for HP2work -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 44 21 | 65 - | 48 241 | 289 -----------+--------------------------+----------- Total | 92 262 | 354 Classified + if predicted Pr(D) >= .5 True D defined as HP2work != 0 -------------------------------------------------- Sensitivity Pr( +| D) 47.83% Specificity Pr( -|~D) 91.98% Positive predictive value Pr( D| +) 67.69% Negative predictive value Pr(~D| -) 83.39% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 8.02% False - rate for true D Pr( -| D) 52.17% False + rate for classified + Pr(~D| +) 32.31% False - rate for classified - Pr( D| -) 16.61% -------------------------------------------------- Correctly classified 80.51% -------------------------------------------------- Logistic model for HP2work, goodness-of-fit test number of observations = 354 number of covariate patterns = 354 Pearson chi2(309) = 452.09 Prob > chi2 = 0.0000 Measures of Fit for logistic of HP2work Log-Lik Intercept Only: -202.820 Log-Lik Full Model: -150.435 D(305): 300.870 LR(44): 104.770 Prob > LR: 0.000 McFadden's R2: 0.258 McFadden's Adj R2: 0.017 Maximum Likelihood R2: 0.256 Cragg & Uhler's R2: 0.376 McKelvey and Zavoina's R2: 0.477 Efron's R2: 0.297 Variance of y*: 6.291 Variance of error: 3.290 Count R2: 0.805 Adj Count R2: 0.250 AIC: 1.127 AIC*n: 398.870 BIC: -1489.265 BIC': 153.479 Full main model for HP2hmcare for wave= 2 chunk 2 H1 test:Gender= 1 model Wave = 2 for HP2work ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Full Nottingham Part 2 HP2hmcare subscale models ***** ***** wave 2 for gender==1 ***** ***** ***** ***** ***** ***** 16 Jun 2012 21:51:24 ***** ******************************************************************************* ******************************************************************************* i.educ _Ieduc_1-8 (naturally coded; _Ieduc_1 omitted) note: _Ieduc_4 != 0 predicts failure perfectly _Ieduc_4 dropped and 12 obs not used note: _Ieduc_8 != 0 predicts failure perfectly _Ieduc_8 dropped and 2 obs not used note: occ8w2 != 0 predicts failure perfectly occ8w2 dropped and 43 obs not used note: sepaw2 != 0 predicts failure perfectly sepaw2 dropped and 6 obs not used note: _Ieduc_7 omitted because of collinearity note: bf15 omitted because of collinearity Logistic regression Number of obs = 269 LR chi2(42) = 109.76 Prob > chi2 = 0.0000 Log likelihood = -97.204962 Pseudo R2 = 0.3609 ------------------------------------------------------------------------------ HP2hmcare | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0338165 .0226356 1.49 0.135 -.0105484 .0781815 _Ieduc_2 | -4.276213 1.974151 -2.17 0.030 -8.145479 -.406947 _Ieduc_3 | -2.496446 1.569642 -1.59 0.112 -5.572887 .579995 _Ieduc_4 | 0 (omitted) _Ieduc_5 | -1.933257 1.595074 -1.21 0.226 -5.059545 1.193031 _Ieduc_6 | -2.731404 1.5115 -1.81 0.071 -5.693888 .2310807 _Ieduc_7 | 0 (omitted) _Ieduc_8 | 0 (omitted) occ1w2 | .447866 3.337423 0.13 0.893 -6.093362 6.989094 occ2w2 | -.0398 3.356232 -0.01 0.991 -6.617893 6.538293 occ3w2 | .5016738 3.37088 0.15 0.882 -6.105129 7.108476 occ4w2 | .4812856 3.378935 0.14 0.887 -6.141306 7.103877 occ5w2 | 1.51252 3.404132 0.44 0.657 -5.159455 8.184496 occ6w2 | 2.9603 3.825064 0.77 0.439 -4.536687 10.45729 occ7w2 | .5681102 3.446364 0.16 0.869 -6.186638 7.322859 occ8w2 | 0 (omitted) marrw21 | -1.554879 1.682488 -0.92 0.355 -4.852495 1.742737 marrw22 | -3.80953 2.028746 -1.88 0.060 -7.785799 .1667393 marrw23 | -3.665421 1.71283 -2.14 0.032 -7.022506 -.3083347 marrw25 | -1.481731 4.126728 -0.36 0.720 -9.56997 6.606508 marrw26 | -2.880741 2.479902 -1.16 0.245 -7.741261 1.979778 inc1w2 | 2.844486 3.430733 0.83 0.407 -3.879627 9.568599 inc2w2 | 2.655327 3.349177 0.79 0.428 -3.908939 9.219593 inc3w2 | 3.052721 3.355091 0.91 0.363 -3.523137 9.628579 inc4w2 | 1.171678 3.639724 0.32 0.748 -5.96205 8.305406 radhlw2 | -.0026842 .0077227 -0.35 0.728 -.0178205 .0124521 havmil | .002871 .0081498 0.35 0.725 -.0131023 .0188444 avgcumdosew2 | -.0220473 .0954292 -0.23 0.817 -.2090852 .1649906 bf1 | -.0176257 .0110209 -1.60 0.110 -.0392262 .0039748 bf4 | -.3209329 .0601062 -5.34 0.000 -.4387388 -.203127 bf6 | .0142094 .0096047 1.48 0.139 -.0046155 .0330342 bf7 | .1041093 .0843677 1.23 0.217 -.0612484 .269467 bf14 | 5.78e-06 .0000736 0.08 0.937 -.0001386 .0001501 bf15 | 0 (omitted) bf40 | .3500268 .1396049 2.51 0.012 .0764063 .6236473 deaw2 | .0522034 .3200036 0.16 0.870 -.5749921 .6793989 dvcew2 | -.370905 3.78656 -0.10 0.922 -7.792426 7.050615 sepaw2 | 0 (omitted) accdw2 | .1929199 .4604851 0.42 0.675 -.7096143 1.095454 movew2 | .2586331 .5214207 0.50 0.620 -.7633328 1.280599 illw2 | -.1291222 .3453441 -0.37 0.708 -.8059842 .5477398 shfamw2 | -.0123461 .0080757 -1.53 0.126 -.0281741 .0034819 shhlw2 | -.0067088 .0095447 -0.70 0.482 -.0254161 .0119985 shjobw2 | -.0001525 .009703 -0.02 0.987 -.0191701 .018865 shrelaw2 | .0044873 .0074837 0.60 0.549 -.0101805 .0191551 suprtw2 | .0138227 .0067373 2.05 0.040 .0006178 .0270276 suchrw2 | -.0024443 .0059474 -0.41 0.681 -.0141011 .0092124 havmilsq | -7.11e-06 .0000151 -0.47 0.639 -.0000368 .0000226 _cons | 1.915103 3.160353 0.61 0.545 -4.279075 8.109282 ------------------------------------------------------------------------------ Logistic model for HP2hmcare -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 38 14 | 52 - | 30 187 | 217 -----------+--------------------------+----------- Total | 68 201 | 269 Classified + if predicted Pr(D) >= .5 True D defined as HP2hmcare != 0 -------------------------------------------------- Sensitivity Pr( +| D) 55.88% Specificity Pr( -|~D) 93.03% Positive predictive value Pr( D| +) 73.08% Negative predictive value Pr(~D| -) 86.18% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 6.97% False - rate for true D Pr( -| D) 44.12% False + rate for classified + Pr(~D| +) 26.92% False - rate for classified - Pr( D| -) 13.82% -------------------------------------------------- Correctly classified 83.64% -------------------------------------------------- Logistic model for HP2hmcare, goodness-of-fit test number of observations = 269 number of covariate patterns = 269 Pearson chi2(226) = 228.79 Prob > chi2 = 0.4356 Measures of Fit for logistic of HP2hmcare Log-Lik Intercept Only: -152.087 Log-Lik Full Model: -97.205 D(220): 194.410 LR(42): 109.763 Prob > LR: 0.000 McFadden's R2: 0.361 McFadden's Adj R2: 0.039 Maximum Likelihood R2: 0.335 Cragg & Uhler's R2: 0.495 McKelvey and Zavoina's R2: 0.599 Efron's R2: 0.381 Variance of y*: 8.208 Variance of error: 3.290 Count R2: 0.836 Adj Count R2: 0.353 AIC: 1.087 AIC*n: 292.410 BIC: -1036.427 BIC': 125.215 Full main model for HP2hmcare for wave= 2 chunk 2 H1 test:Gender= 2 model Wave = 2 for HP2hmcare ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Full Nottingham Part 2 HP2hmcare subscale models ***** ***** wave 2 for gender==2 ***** ***** ***** ***** ***** ***** 16 Jun 2012 21:51:26 ***** ******************************************************************************* ******************************************************************************* i.educ _Ieduc_1-8 (naturally coded; _Ieduc_1 omitted) note: _Ieduc_8 omitted because of collinearity note: marrw26 omitted because of collinearity note: bf15 omitted because of collinearity Logistic regression Number of obs = 362 LR chi2(45) = 176.34 Prob > chi2 = 0.0000 Log likelihood = -144.48759 Pseudo R2 = 0.3790 ------------------------------------------------------------------------------ HP2hmcare | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0738943 .0179039 4.13 0.000 .0388033 .1089852 _Ieduc_2 | -14.47538 1273.657 -0.01 0.991 -2510.798 2481.847 _Ieduc_3 | -15.05547 1273.657 -0.01 0.991 -2511.378 2481.267 _Ieduc_4 | -13.48341 1273.657 -0.01 0.992 -2509.806 2482.839 _Ieduc_5 | -14.88762 1273.657 -0.01 0.991 -2511.21 2481.435 _Ieduc_6 | -15.58826 1273.657 -0.01 0.990 -2511.911 2480.734 _Ieduc_7 | -13.81171 1273.659 -0.01 0.991 -2510.137 2482.513 _Ieduc_8 | 0 (omitted) occ1w2 | -2.359905 1.509597 -1.56 0.118 -5.318661 .5988504 occ2w2 | -2.373759 1.546944 -1.53 0.125 -5.405713 .6581945 occ3w2 | -1.535666 1.553674 -0.99 0.323 -4.58081 1.509479 occ4w2 | -2.972204 1.655316 -1.80 0.073 -6.216564 .2721556 occ5w2 | -4.352791 1.883178 -2.31 0.021 -8.043752 -.6618289 occ6w2 | -5.059677 2.021732 -2.50 0.012 -9.022199 -1.097155 occ7w2 | -1.364295 1.545156 -0.88 0.377 -4.392746 1.664156 occ8w2 | -.5789576 1.792303 -0.32 0.747 -4.091808 2.933892 marrw21 | -.0690078 1.129464 -0.06 0.951 -2.282717 2.144702 marrw22 | .7043443 1.44356 0.49 0.626 -2.124982 3.533671 marrw23 | 2.097285 .8281102 2.53 0.011 .4742186 3.720351 marrw25 | .9609574 1.20757 0.80 0.426 -1.405836 3.327751 marrw26 | 0 (omitted) inc1w2 | 2.105274 1.594442 1.32 0.187 -1.019775 5.230323 inc2w2 | 3.407471 1.542788 2.21 0.027 .3836621 6.43128 inc3w2 | 2.870172 1.549672 1.85 0.064 -.1671285 5.907473 inc4w2 | 3.606463 1.894634 1.90 0.057 -.1069505 7.319876 radhlw2 | -.0068123 .0061828 -1.10 0.271 -.0189302 .0053057 havmil | .0011484 .0030211 0.38 0.704 -.0047728 .0070696 avgcumdosew2 | -.2667926 .1232968 -2.16 0.030 -.5084499 -.0251353 bf1 | -.0183931 .0079003 -2.33 0.020 -.0338774 -.0029088 bf4 | -.2337773 .0416245 -5.62 0.000 -.3153598 -.1521948 bf6 | .0040038 .0067939 0.59 0.556 -.009312 .0173196 bf7 | -.126659 .0709704 -1.78 0.074 -.2657584 .0124404 bf14 | -.0000228 .0000659 -0.35 0.729 -.0001521 .0001064 bf15 | 0 (omitted) bf40 | .0786288 .0758899 1.04 0.300 -.0701127 .2273704 deaw2 | .6463714 .2506264 2.58 0.010 .1551526 1.13759 dvcew2 | 1.46465 1.066188 1.37 0.170 -.6250398 3.554339 sepaw2 | -1.747364 1.628008 -1.07 0.283 -4.938201 1.443472 accdw2 | -.6760904 .5387942 -1.25 0.210 -1.732108 .3799268 movew2 | -.5261615 .493185 -1.07 0.286 -1.492786 .4404633 illw2 | -.1619986 .1844507 -0.88 0.380 -.5235154 .1995182 shfamw2 | -.0039886 .0060041 -0.66 0.506 -.0157565 .0077793 shhlw2 | -.0091905 .0062486 -1.47 0.141 -.0214375 .0030565 shjobw2 | .0003458 .0057176 0.06 0.952 -.0108605 .011552 shrelaw2 | -.0091776 .006756 -1.36 0.174 -.0224192 .0040639 suprtw2 | -.0077623 .0046946 -1.65 0.098 -.0169635 .0014389 suchrw2 | .0040413 .0050755 0.80 0.426 -.0059065 .013989 havmilsq | -1.23e-06 2.83e-06 -0.44 0.664 -6.79e-06 4.32e-06 _cons | 12.31935 1273.659 0.01 0.992 -2484.005 2508.644 ------------------------------------------------------------------------------ Logistic model for HP2hmcare -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 85 27 | 112 - | 39 211 | 250 -----------+--------------------------+----------- Total | 124 238 | 362 Classified + if predicted Pr(D) >= .5 True D defined as HP2hmcare != 0 -------------------------------------------------- Sensitivity Pr( +| D) 68.55% Specificity Pr( -|~D) 88.66% Positive predictive value Pr( D| +) 75.89% Negative predictive value Pr(~D| -) 84.40% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 11.34% False - rate for true D Pr( -| D) 31.45% False + rate for classified + Pr(~D| +) 24.11% False - rate for classified - Pr( D| -) 15.60% -------------------------------------------------- Correctly classified 81.77% -------------------------------------------------- Logistic model for HP2hmcare, goodness-of-fit test number of observations = 362 number of covariate patterns = 362 Pearson chi2(316) = 339.77 Prob > chi2 = 0.1713 Measures of Fit for logistic of HP2hmcare Log-Lik Intercept Only: -232.660 Log-Lik Full Model: -144.488 D(313): 288.975 LR(45): 176.345 Prob > LR: 0.000 McFadden's R2: 0.379 McFadden's Adj R2: 0.168 Maximum Likelihood R2: 0.386 Cragg & Uhler's R2: 0.533 McKelvey and Zavoina's R2: 0.660 Efron's R2: 0.429 Variance of y*: 9.672 Variance of error: 3.290 Count R2: 0.818 Adj Count R2: 0.468 AIC: 1.069 AIC*n: 386.975 BIC: -1555.109 BIC': 88.779 Full main model for HP2probsoc for wave= 2 chunk 2 H1 test:Gender= 1 model Wave = 2 for HP2hmcare ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Full Nottingham Part 2 HP2probsoc subscale models ***** ***** wave 2 for gender==1 ***** ***** ***** ***** ***** ***** 16 Jun 2012 21:51:27 ***** ******************************************************************************* ******************************************************************************* i.educ _Ieduc_1-8 (naturally coded; _Ieduc_1 omitted) note: _Ieduc_4 != 0 predicts failure perfectly _Ieduc_4 dropped and 12 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: occ6w2 != 0 predicts failure perfectly occ6w2 dropped and 4 obs not used note: occ7w2 != 0 predicts failure perfectly occ7w2 dropped and 14 obs not used note: occ8w2 != 0 predicts failure perfectly occ8w2 dropped and 43 obs not used note: marrw22 != 0 predicts failure perfectly marrw22 dropped and 7 obs not used note: marrw25 != 0 predicts failure perfectly marrw25 dropped and 4 obs not used note: marrw26 != 0 predicts failure perfectly marrw26 dropped and 1 obs not used note: inc4w2 != 0 predicts failure perfectly inc4w2 dropped and 9 obs not used note: dvcew2 != 0 predicts failure perfectly dvcew2 dropped and 3 obs not used note: sepaw2 != 0 predicts failure perfectly sepaw2 dropped and 1 obs not used note: _Ieduc_6 omitted because of collinearity note: bf15 omitted because of collinearity Logistic regression Number of obs = 228 LR chi2(34) = 103.91 Prob > chi2 = 0.0000 Log likelihood = -52.36582 Pseudo R2 = 0.4980 ------------------------------------------------------------------------------ HP2probsoc | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0906854 .0339814 2.67 0.008 .0240831 .1572876 _Ieduc_2 | -.0346926 1.161856 -0.03 0.976 -2.311888 2.242503 _Ieduc_3 | -.6886648 .7207042 -0.96 0.339 -2.101219 .7238895 _Ieduc_4 | 0 (omitted) _Ieduc_5 | .9759744 1.063631 0.92 0.359 -1.108703 3.060652 _Ieduc_6 | 0 (omitted) _Ieduc_7 | 0 (omitted) _Ieduc_8 | 0 (omitted) occ1w2 | -.9172264 10.67202 -0.09 0.932 -21.83401 19.99955 occ2w2 | -.7254984 10.66823 -0.07 0.946 -21.63485 20.18385 occ3w2 | -.6714679 10.68886 -0.06 0.950 -21.62126 20.27832 occ4w2 | -2.239171 10.70842 -0.21 0.834 -23.22728 18.74894 occ5w2 | -.9195542 10.71455 -0.09 0.932 -21.91968 20.08057 occ6w2 | 0 (omitted) occ7w2 | 0 (omitted) occ8w2 | 0 (omitted) marrw21 | 11.0684 1379.375 0.01 0.994 -2692.457 2714.594 marrw22 | 0 (omitted) marrw23 | 8.945925 1379.375 0.01 0.995 -2694.579 2712.471 marrw25 | 0 (omitted) marrw26 | 0 (omitted) inc1w2 | .3641243 10.76623 0.03 0.973 -20.7373 21.46555 inc2w2 | 1.742499 10.67327 0.16 0.870 -19.17672 22.66172 inc3w2 | 3.371881 10.68463 0.32 0.752 -17.56961 24.31337 inc4w2 | 0 (omitted) radhlw2 | .0085407 .0114129 0.75 0.454 -.0138281 .0309095 havmil | -.0006807 .0078287 -0.09 0.931 -.0160246 .0146632 avgcumdosew2 | .099739 .0947343 1.05 0.292 -.0859367 .2854148 bf1 | .0048596 .0179991 0.27 0.787 -.0304181 .0401372 bf4 | -.3368708 .0845017 -3.99 0.000 -.5024911 -.1712504 bf6 | .0294921 .0150976 1.95 0.051 -.0000987 .0590829 bf7 | .2107792 .1280115 1.65 0.100 -.0401186 .4616771 bf14 | -.0000508 .0001111 -0.46 0.648 -.0002685 .0001669 bf15 | 0 (omitted) bf40 | .3587504 .202109 1.78 0.076 -.0373759 .7548768 deaw2 | -.2425986 .5320938 -0.46 0.648 -1.285483 .8002861 dvcew2 | 0 (omitted) sepaw2 | 0 (omitted) accdw2 | -.0583869 .772113 -0.08 0.940 -1.571701 1.454927 movew2 | .534895 .8346364 0.64 0.522 -1.100962 2.170752 illw2 | .3093012 .430894 0.72 0.473 -.5352355 1.153838 shfamw2 | -.0138199 .0107438 -1.29 0.198 -.0348774 .0072375 shhlw2 | -.0108054 .0127581 -0.85 0.397 -.0358108 .0141999 shjobw2 | .024033 .0121387 1.98 0.048 .0002416 .0478244 shrelaw2 | -.0263531 .0111814 -2.36 0.018 -.0482683 -.0044379 suprtw2 | .0130386 .0099595 1.31 0.190 -.0064816 .0325589 suchrw2 | .0121677 .0099924 1.22 0.223 -.007417 .0317524 havmilsq | 4.68e-06 9.92e-06 0.47 0.637 -.0000148 .0000241 _cons | -18.63366 1379.378 -0.01 0.989 -2722.164 2684.897 ------------------------------------------------------------------------------ Logistic model for HP2probsoc -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 27 4 | 31 - | 12 185 | 197 -----------+--------------------------+----------- Total | 39 189 | 228 Classified + if predicted Pr(D) >= .5 True D defined as HP2probsoc != 0 -------------------------------------------------- Sensitivity Pr( +| D) 69.23% Specificity Pr( -|~D) 97.88% Positive predictive value Pr( D| +) 87.10% Negative predictive value Pr(~D| -) 93.91% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 2.12% False - rate for true D Pr( -| D) 30.77% False + rate for classified + Pr(~D| +) 12.90% False - rate for classified - Pr( D| -) 6.09% -------------------------------------------------- Correctly classified 92.98% -------------------------------------------------- Logistic model for HP2probsoc, goodness-of-fit test number of observations = 228 number of covariate patterns = 228 Pearson chi2(193) = 730.19 Prob > chi2 = 0.0000 Measures of Fit for logistic of HP2probsoc Log-Lik Intercept Only: -104.322 Log-Lik Full Model: -52.366 D(179): 104.732 LR(34): 103.912 Prob > LR: 0.000 McFadden's R2: 0.498 McFadden's Adj R2: 0.028 Maximum Likelihood R2: 0.366 Cragg & Uhler's R2: 0.611 McKelvey and Zavoina's R2: 0.779 Efron's R2: 0.554 Variance of y*: 14.912 Variance of error: 3.290 Count R2: 0.930 Adj Count R2: 0.590 AIC: 0.889 AIC*n: 202.732 BIC: -867.121 BIC': 80.686 Full main model for HP2probsoc for wave= 2 chunk 2 H1 test:Gender= 2 model Wave = 2 for HP2probsoc ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Full Nottingham Part 2 HP2probsoc subscale models ***** ***** wave 2 for gender==2 ***** ***** ***** ***** ***** ***** 16 Jun 2012 21:51:29 ***** ******************************************************************************* ******************************************************************************* i.educ _Ieduc_1-8 (naturally coded; _Ieduc_1 omitted) note: occ6w2 != 0 predicts failure perfectly occ6w2 dropped and 9 obs not used note: _Ieduc_8 omitted because of collinearity note: marrw26 omitted because of collinearity note: bf15 omitted because of collinearity Logistic regression Number of obs = 353 LR chi2(44) = 173.44 Prob > chi2 = 0.0000 Log likelihood = -93.198778 Pseudo R2 = 0.4820 ------------------------------------------------------------------------------ HP2probsoc | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .1045505 .025349 4.12 0.000 .0548673 .1542337 _Ieduc_2 | -12.29812 1030.765 -0.01 0.990 -2032.56 2007.964 _Ieduc_3 | -12.54704 1030.765 -0.01 0.990 -2032.809 2007.715 _Ieduc_4 | -11.69817 1030.765 -0.01 0.991 -2031.96 2008.564 _Ieduc_5 | -11.74738 1030.765 -0.01 0.991 -2032.009 2008.515 _Ieduc_6 | -12.89754 1030.765 -0.01 0.990 -2033.159 2007.364 _Ieduc_7 | -14.11644 1030.817 -0.01 0.989 -2034.481 2006.248 _Ieduc_8 | 0 (omitted) occ1w2 | -1.104757 3.60974 -0.31 0.760 -8.179718 5.970203 occ2w2 | -1.202019 3.652886 -0.33 0.742 -8.361544 5.957506 occ3w2 | .0703933 3.628444 0.02 0.985 -7.041227 7.182014 occ4w2 | -1.52192 3.712086 -0.41 0.682 -8.797475 5.753635 occ5w2 | -2.24588 3.84541 -0.58 0.559 -9.782745 5.290985 occ6w2 | 0 (omitted) occ7w2 | -.4840598 3.61697 -0.13 0.894 -7.573191 6.605072 occ8w2 | 2.167215 3.89814 0.56 0.578 -5.472999 9.807428 marrw21 | -.4201784 1.629029 -0.26 0.796 -3.613016 2.772659 marrw22 | 1.086175 1.72569 0.63 0.529 -2.296115 4.468466 marrw23 | .7750978 .9250885 0.84 0.402 -1.038042 2.588238 marrw25 | .532399 1.287582 0.41 0.679 -1.991215 3.056013 marrw26 | 0 (omitted) inc1w2 | .0603839 3.624166 0.02 0.987 -7.042851 7.163619 inc2w2 | .8383333 3.595272 0.23 0.816 -6.20827 7.884937 inc3w2 | .536243 3.60018 0.15 0.882 -6.519981 7.592467 inc4w2 | .2312155 3.842475 0.06 0.952 -7.299898 7.762329 radhlw2 | .0147911 .0081819 1.81 0.071 -.0012451 .0308272 havmil | .0022418 .0072934 0.31 0.759 -.0120531 .0165366 avgcumdosew2 | .4925829 .2091227 2.36 0.018 .0827098 .9024559 bf1 | -.0161664 .0113442 -1.43 0.154 -.0384006 .0060677 bf4 | -.2331375 .0505589 -4.61 0.000 -.332231 -.1340439 bf6 | .0021871 .0094776 0.23 0.817 -.0163887 .0207629 bf7 | -.0615381 .1064342 -0.58 0.563 -.2701454 .1470692 bf14 | 8.31e-06 .0000929 0.09 0.929 -.0001737 .0001903 bf15 | 0 (omitted) bf40 | -.005756 .0971846 -0.06 0.953 -.1962344 .1847223 deaw2 | -.0331928 .2378427 -0.14 0.889 -.499356 .4329704 dvcew2 | 1.930249 1.72923 1.12 0.264 -1.45898 5.319477 sepaw2 | -1.211648 2.172861 -0.56 0.577 -5.470378 3.047082 accdw2 | -.6584952 .7729357 -0.85 0.394 -2.173421 .8564309 movew2 | -.3688091 .9599148 -0.38 0.701 -2.250208 1.512589 illw2 | .0217672 .2703514 0.08 0.936 -.5081118 .5516462 shfamw2 | -.0185511 .0084341 -2.20 0.028 -.0350816 -.0020206 shhlw2 | .0005321 .0080879 0.07 0.948 -.0153199 .0163841 shjobw2 | -.0024716 .0076938 -0.32 0.748 -.0175512 .0126079 shrelaw2 | -.0052827 .0086543 -0.61 0.542 -.0222447 .0116794 suprtw2 | .0005602 .0066528 0.08 0.933 -.012479 .0135994 suchrw2 | -.0036935 .00718 -0.51 0.607 -.017766 .0103791 havmilsq | -8.46e-06 .0000154 -0.55 0.582 -.0000386 .0000217 _cons | 6.917383 1030.768 0.01 0.995 -2013.35 2027.185 ------------------------------------------------------------------------------ Note: 3 failures and 0 successes completely determined. Logistic model for HP2probsoc -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 53 11 | 64 - | 20 269 | 289 -----------+--------------------------+----------- Total | 73 280 | 353 Classified + if predicted Pr(D) >= .5 True D defined as HP2probsoc != 0 -------------------------------------------------- Sensitivity Pr( +| D) 72.60% Specificity Pr( -|~D) 96.07% Positive predictive value Pr( D| +) 82.81% Negative predictive value Pr(~D| -) 93.08% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 3.93% False - rate for true D Pr( -| D) 27.40% False + rate for classified + Pr(~D| +) 17.19% False - rate for classified - Pr( D| -) 6.92% -------------------------------------------------- Correctly classified 91.22% -------------------------------------------------- Logistic model for HP2probsoc, goodness-of-fit test number of observations = 353 number of covariate patterns = 353 Pearson chi2(308) = 419.21 Prob > chi2 = 0.0000 Measures of Fit for logistic of HP2probsoc Log-Lik Intercept Only: -179.919 Log-Lik Full Model: -93.199 D(304): 186.398 LR(44): 173.440 Prob > LR: 0.000 McFadden's R2: 0.482 McFadden's Adj R2: 0.210 Maximum Likelihood R2: 0.388 Cragg & Uhler's R2: 0.607 McKelvey and Zavoina's R2: 0.892 Efron's R2: 0.528 Variance of y*: 30.526 Variance of error: 3.290 Count R2: 0.912 Adj Count R2: 0.575 AIC: 0.806 AIC*n: 284.398 BIC: -1597.009 BIC': 84.685 Full main model for HP2pbfhm for wave= 2 chunk 2 H1 test:Gender= 1 model Wave = 2 for HP2probsoc ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Full Nottingham Part 2 HP2pbfhm subscale models ***** ***** wave 2 for gender==1 ***** ***** ***** ***** ***** ***** 16 Jun 2012 21:51:30 ***** ******************************************************************************* ******************************************************************************* 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 12 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: occ5w2 != 0 predicts failure perfectly occ5w2 dropped and 17 obs not used note: occ6w2 != 0 predicts failure perfectly occ6w2 dropped and 4 obs not used note: occ8w2 != 0 predicts failure perfectly occ8w2 dropped and 43 obs not used note: marrw22 != 0 predicts failure perfectly marrw22 dropped and 7 obs not used note: marrw25 != 0 predicts failure perfectly marrw25 dropped and 4 obs not used note: marrw26 != 0 predicts failure perfectly marrw26 dropped and 3 obs not used note: inc1w2 != 0 predicts failure perfectly inc1w2 dropped and 13 obs not used note: inc4w2 != 0 predicts failure perfectly inc4w2 dropped and 9 obs not used note: dvcew2 != 0 predicts failure perfectly dvcew2 dropped and 2 obs not used note: sepaw2 != 0 predicts failure perfectly sepaw2 dropped and 1 obs not used note: _Ieduc_6 omitted because of collinearity note: bf15 omitted because of collinearity Logistic regression Number of obs = 201 LR chi2(32) = 57.01 Prob > chi2 = 0.0042 Log likelihood = -38.789787 Pseudo R2 = 0.4236 ------------------------------------------------------------------------------ HP2pbfhm | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0838902 .0451044 1.86 0.063 -.0045127 .1722932 _Ieduc_2 | 0 (omitted) _Ieduc_3 | -1.068513 .9797271 -1.09 0.275 -2.988743 .851717 _Ieduc_4 | 0 (omitted) _Ieduc_5 | -.7464993 1.30613 -0.57 0.568 -3.306468 1.813469 _Ieduc_6 | 0 (omitted) _Ieduc_7 | 0 (omitted) _Ieduc_8 | 0 (omitted) occ1w2 | 1.365472 9.739165 0.14 0.888 -17.72294 20.45389 occ2w2 | .1388058 9.737518 0.01 0.989 -18.94638 19.22399 occ3w2 | 1.99317 9.743118 0.20 0.838 -17.10299 21.08933 occ4w2 | 2.351827 9.813506 0.24 0.811 -16.88229 21.58595 occ5w2 | 0 (omitted) occ6w2 | 0 (omitted) occ7w2 | .8526169 9.853293 0.09 0.931 -18.45948 20.16472 occ8w2 | 0 (omitted) marrw21 | 9.450183 1628.316 0.01 0.995 -3181.99 3200.891 marrw22 | 0 (omitted) marrw23 | 8.041239 1628.316 0.00 0.996 -3183.4 3199.482 marrw25 | 0 (omitted) marrw26 | 0 (omitted) inc1w2 | 0 (omitted) inc2w2 | -.2472615 9.778068 -0.03 0.980 -19.41192 18.9174 inc3w2 | .4803685 9.779356 0.05 0.961 -18.68682 19.64755 inc4w2 | 0 (omitted) radhlw2 | .0219991 .0174949 1.26 0.209 -.0122902 .0562884 havmil | -.0118024 .0110278 -1.07 0.285 -.0334164 .0098117 avgcumdosew2 | -.108206 .7718766 -0.14 0.889 -1.621056 1.404644 bf1 | -.0239769 .0247822 -0.97 0.333 -.0725492 .0245953 bf4 | -.1619124 .088191 -1.84 0.066 -.3347635 .0109388 bf6 | .0726065 .0265235 2.74 0.006 .0206214 .1245916 bf7 | .5947613 .2273662 2.62 0.009 .1491317 1.040391 bf14 | -.0000762 .0001284 -0.59 0.553 -.0003279 .0001756 bf15 | 0 (omitted) bf40 | .1113503 .2734738 0.41 0.684 -.4246485 .6473491 deaw2 | .5485131 .536457 1.02 0.307 -.5029234 1.59995 dvcew2 | 0 (omitted) sepaw2 | 0 (omitted) accdw2 | .185387 1.066161 0.17 0.862 -1.904251 2.275025 movew2 | -.6539417 1.506102 -0.43 0.664 -3.605848 2.297965 illw2 | 1.606215 .6542566 2.46 0.014 .3238954 2.888534 shfamw2 | -.0092438 .0132973 -0.70 0.487 -.0353061 .0168184 shhlw2 | -.031707 .0186076 -1.70 0.088 -.0681771 .0047632 shjobw2 | .0258976 .0158492 1.63 0.102 -.0051662 .0569614 shrelaw2 | -.0153159 .0142321 -1.08 0.282 -.0432103 .0125785 suprtw2 | -.0315277 .0143652 -2.19 0.028 -.059683 -.0033724 suchrw2 | .0165746 .0112144 1.48 0.139 -.0054051 .0385544 havmilsq | .0000128 .0000121 1.06 0.291 -.000011 .0000367 _cons | -18.46331 1628.32 -0.01 0.991 -3209.912 3172.985 ------------------------------------------------------------------------------ Logistic model for HP2pbfhm -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 6 2 | 8 - | 15 178 | 193 -----------+--------------------------+----------- Total | 21 180 | 201 Classified + if predicted Pr(D) >= .5 True D defined as HP2pbfhm != 0 -------------------------------------------------- Sensitivity Pr( +| D) 28.57% Specificity Pr( -|~D) 98.89% Positive predictive value Pr( D| +) 75.00% Negative predictive value Pr(~D| -) 92.23% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 1.11% False - rate for true D Pr( -| D) 71.43% False + rate for classified + Pr(~D| +) 25.00% False - rate for classified - Pr( D| -) 7.77% -------------------------------------------------- Correctly classified 91.54% -------------------------------------------------- Logistic model for HP2pbfhm, goodness-of-fit test number of observations = 201 number of covariate patterns = 201 Pearson chi2(168) = 94.58 Prob > chi2 = 1.0000 Measures of Fit for logistic of HP2pbfhm Log-Lik Intercept Only: -67.297 Log-Lik Full Model: -38.790 D(152): 77.580 LR(32): 57.015 Prob > LR: 0.004 McFadden's R2: 0.424 McFadden's Adj R2: -0.305 Maximum Likelihood R2: 0.247 Cragg & Uhler's R2: 0.506 McKelvey and Zavoina's R2: 0.804 Efron's R2: 0.348 Variance of y*: 16.822 Variance of error: 3.290 Count R2: 0.915 Adj Count R2: 0.190 AIC: 0.874 AIC*n: 175.580 BIC: -728.523 BIC': 112.691 Full main model for HP2pbfhm for wave= 2 chunk 2 H1 test:Gender= 2 model Wave = 2 for HP2pbfhm ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Full Nottingham Part 2 HP2pbfhm subscale models ***** ***** wave 2 for gender==2 ***** ***** ***** ***** ***** ***** 16 Jun 2012 21:51:32 ***** ******************************************************************************* ******************************************************************************* i.educ _Ieduc_1-8 (naturally coded; _Ieduc_1 omitted) note: occ6w2 != 0 predicts failure perfectly occ6w2 dropped and 9 obs not used note: marrw22 != 0 predicts failure perfectly marrw22 dropped and 8 obs not used note: inc4w2 != 0 predicts failure perfectly inc4w2 dropped and 9 obs not used note: sepaw2 != 0 predicts failure perfectly sepaw2 dropped and 6 obs not used note: movew2 != 0 predicts failure perfectly movew2 dropped and 39 obs not used note: _Ieduc_8 omitted because of collinearity note: marrw26 omitted because of collinearity note: bf15 omitted because of collinearity convergence not achieved Logistic regression Number of obs = 291 LR chi2(39) = 121.44 Prob > chi2 = 0.0000 Log likelihood = -67.950854 Pseudo R2 = 0.4719 ------------------------------------------------------------------------------ HP2pbfhm | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0675647 .0282471 2.39 0.017 .0122015 .1229279 _Ieduc_2 | 22.46198 4.286253 5.24 0.000 14.06108 30.86288 _Ieduc_3 | 22.06025 4.212008 5.24 0.000 13.80487 30.31564 _Ieduc_4 | 22.4092 4.348301 5.15 0.000 13.88669 30.93171 _Ieduc_5 | 22.32965 4.28528 5.21 0.000 13.93065 30.72864 _Ieduc_6 | 22.02862 4.22306 5.22 0.000 13.75158 30.30567 _Ieduc_7 | 21.12883 . . . . . _Ieduc_8 | 0 (omitted) occ1w2 | .9568844 2.829891 0.34 0.735 -4.5896 6.503369 occ2w2 | -2.026671 3.019495 -0.67 0.502 -7.944772 3.891431 occ3w2 | 1.405631 2.856151 0.49 0.623 -4.192322 7.003584 occ4w2 | -1.270684 3.036271 -0.42 0.676 -7.221665 4.680297 occ5w2 | 2.733135 3.099019 0.88 0.378 -3.340831 8.8071 occ6w2 | 0 (omitted) occ7w2 | 2.390639 2.797142 0.85 0.393 -3.091658 7.872935 occ8w2 | 1.799797 3.171082 0.57 0.570 -4.415409 8.015004 marrw21 | 1.863442 1.565893 1.19 0.234 -1.205651 4.932536 marrw22 | 0 (omitted) marrw23 | 1.299753 1.073276 1.21 0.226 -.8038291 3.403334 marrw25 | 1.783742 1.600693 1.11 0.265 -1.353558 4.921042 marrw26 | 0 (omitted) inc1w2 | -1.338762 2.877886 -0.47 0.642 -6.979314 4.301791 inc2w2 | .7251666 2.789285 0.26 0.795 -4.741732 6.192065 inc3w2 | .4037645 2.828422 0.14 0.886 -5.13984 5.947369 inc4w2 | 0 (omitted) radhlw2 | .0119256 .0102886 1.16 0.246 -.0082396 .0320909 havmil | -.0040139 .0172972 -0.23 0.816 -.0379157 .0298879 avgcumdosew2 | .2722171 .2230232 1.22 0.222 -.1649004 .7093346 bf1 | -.0267246 .0134298 -1.99 0.047 -.0530465 -.0004027 bf4 | -.3567161 .0758997 -4.70 0.000 -.5054767 -.2079554 bf6 | .0040524 .0115093 0.35 0.725 -.0185053 .0266102 bf7 | -.087478 .1503624 -0.58 0.561 -.382183 .2072269 bf14 | -.0003779 .0001483 -2.55 0.011 -.0006686 -.0000872 bf15 | 0 (omitted) bf40 | -.3388161 .1424322 -2.38 0.017 -.6179782 -.0596541 deaw2 | -.0547509 .2551957 -0.21 0.830 -.5549253 .4454235 dvcew2 | -1.224029 2.015285 -0.61 0.544 -5.173916 2.725858 sepaw2 | 0 (omitted) accdw2 | -2.829263 1.402671 -2.02 0.044 -5.578447 -.0800779 movew2 | 0 (omitted) illw2 | .0637667 .2827466 0.23 0.822 -.4904064 .6179399 shfamw2 | .0166332 .00908 1.83 0.067 -.0011633 .0344296 shhlw2 | .0127805 .0100076 1.28 0.202 -.006834 .0323949 shjobw2 | -.0073866 .0092188 -0.80 0.423 -.0254551 .0106818 shrelaw2 | -.0222876 .0112977 -1.97 0.049 -.0444307 -.0001445 suprtw2 | -.0213951 .0081927 -2.61 0.009 -.0374524 -.0053378 suchrw2 | -.0010257 .0080813 -0.13 0.899 -.0168647 .0148133 havmilsq | -6.28e-06 .0000546 -0.12 0.908 -.0001132 .0001006 _cons | -23.95744 5.116815 -4.68 0.000 -33.98621 -13.92866 ------------------------------------------------------------------------------ Note: 2 failures and 0 successes completely determined. Warning: convergence not achieved Logistic model for HP2pbfhm -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 27 8 | 35 - | 20 236 | 256 -----------+--------------------------+----------- Total | 47 244 | 291 Classified + if predicted Pr(D) >= .5 True D defined as HP2pbfhm != 0 -------------------------------------------------- Sensitivity Pr( +| D) 57.45% Specificity Pr( -|~D) 96.72% Positive predictive value Pr( D| +) 77.14% Negative predictive value Pr(~D| -) 92.19% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 3.28% False - rate for true D Pr( -| D) 42.55% False + rate for classified + Pr(~D| +) 22.86% False - rate for classified - Pr( D| -) 7.81% -------------------------------------------------- Correctly classified 90.38% -------------------------------------------------- Logistic model for HP2pbfhm, goodness-of-fit test number of observations = 291 number of covariate patterns = 291 Pearson chi2(250) = 231.07 Prob > chi2 = 0.7993 Measures of Fit for logistic of HP2pbfhm Log-Lik Intercept Only: -128.671 Log-Lik Full Model: -67.951 D(242): 135.902 LR(39): 121.440 Prob > LR: 0.000 McFadden's R2: 0.472 McFadden's Adj R2: 0.091 Maximum Likelihood R2: 0.341 Cragg & Uhler's R2: 0.581 McKelvey and Zavoina's R2: 0.819 Efron's R2: 0.487 Variance of y*: 18.199 Variance of error: 3.290 Count R2: 0.904 Adj Count R2: 0.404 AIC: 0.804 AIC*n: 233.902 BIC: -1237.043 BIC': 99.819 Full main model for HP2sxlife for wave= 2 chunk 2 H1 test:Gender= 1 model Wave = 2 for HP2pbfhm ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Full Nottingham Part 2 HP2sxlife subscale models ***** ***** wave 2 for gender==1 ***** ***** ***** ***** ***** ***** 16 Jun 2012 21:51:34 ***** ******************************************************************************* ******************************************************************************* i.educ _Ieduc_1-8 (naturally coded; _Ieduc_1 omitted) note: _Ieduc_4 != 0 predicts failure perfectly _Ieduc_4 dropped and 12 obs not used note: _Ieduc_7 != 0 predicts failure perfectly _Ieduc_7 dropped and 4 obs not used note: occ8w2 != 0 predicts failure perfectly occ8w2 dropped and 43 obs not used note: marrw22 != 0 predicts failure perfectly marrw22 dropped and 8 obs not used note: marrw25 != 0 predicts failure perfectly marrw25 dropped and 4 obs not used note: inc4w2 != 0 predicts failure perfectly inc4w2 dropped and 9 obs not used note: dvcew2 != 0 predicts failure perfectly dvcew2 dropped and 3 obs not used note: sepaw2 != 0 predicts failure perfectly sepaw2 dropped and 1 obs not used note: _Ieduc_8 omitted because of collinearity note: bf15 omitted because of collinearity Logistic regression Number of obs = 248 LR chi2(38) = 124.45 Prob > chi2 = 0.0000 Log likelihood = -81.459667 Pseudo R2 = 0.4331 ------------------------------------------------------------------------------ HP2sxlife | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .045416 .0245513 1.85 0.064 -.0027037 .0935357 _Ieduc_2 | -.0646877 2.529828 -0.03 0.980 -5.02306 4.893684 _Ieduc_3 | -.2043117 2.425172 -0.08 0.933 -4.957562 4.548938 _Ieduc_4 | 0 (omitted) _Ieduc_5 | .5468814 2.47638 0.22 0.825 -4.306734 5.400497 _Ieduc_6 | -.5396204 2.395021 -0.23 0.822 -5.233776 4.154535 _Ieduc_7 | 0 (omitted) _Ieduc_8 | 0 (omitted) occ1w2 | -.914781 4.041769 -0.23 0.821 -8.836503 7.006941 occ2w2 | -1.085289 4.050896 -0.27 0.789 -9.024899 6.854322 occ3w2 | -2.01676 4.099586 -0.49 0.623 -10.0518 6.018282 occ4w2 | -1.281739 4.07837 -0.31 0.753 -9.275197 6.711719 occ5w2 | -2.386463 4.187943 -0.57 0.569 -10.59468 5.821754 occ6w2 | 1.041656 4.356584 0.24 0.811 -7.497091 9.580403 occ7w2 | -.2042994 4.128602 -0.05 0.961 -8.296212 7.887613 occ8w2 | 0 (omitted) marrw21 | 11.19923 1268.681 0.01 0.993 -2475.369 2497.767 marrw22 | 0 (omitted) marrw23 | 11.00787 1268.681 0.01 0.993 -2475.56 2497.576 marrw25 | 0 (omitted) marrw26 | 9.989133 1268.682 0.01 0.994 -2476.582 2496.56 inc1w2 | 2.592204 4.16321 0.62 0.534 -5.567537 10.75195 inc2w2 | 3.029964 4.086266 0.74 0.458 -4.978969 11.0389 inc3w2 | 2.803138 4.089233 0.69 0.493 -5.211611 10.81789 inc4w2 | 0 (omitted) radhlw2 | .0158792 .0090915 1.75 0.081 -.0019397 .0336982 havmil | -.0002765 .0085069 -0.03 0.974 -.0169497 .0163966 avgcumdosew2 | -.0370642 .0826057 -0.45 0.654 -.1989685 .1248401 bf1 | .0019651 .0129727 0.15 0.880 -.0234608 .0273911 bf4 | -.2487796 .05911 -4.21 0.000 -.3646331 -.1329261 bf6 | .0163867 .0108586 1.51 0.131 -.0048957 .0376692 bf7 | .0671464 .105745 0.63 0.525 -.1401099 .2744028 bf14 | -.0000488 .0000798 -0.61 0.541 -.0002053 .0001076 bf15 | 0 (omitted) bf40 | .3417099 .1521463 2.25 0.025 .0435086 .6399112 deaw2 | .0342021 .3561465 0.10 0.923 -.6638321 .7322364 dvcew2 | 0 (omitted) sepaw2 | 0 (omitted) accdw2 | -.0684013 .5282538 -0.13 0.897 -1.10376 .9669571 movew2 | .1688384 .5667796 0.30 0.766 -.9420292 1.279706 illw2 | .2358444 .3235455 0.73 0.466 -.398293 .8699819 shfamw2 | -.0126799 .0083767 -1.51 0.130 -.0290979 .0037381 shhlw2 | -.01343 .0100141 -1.34 0.180 -.0330573 .0061973 shjobw2 | .0172317 .0096379 1.79 0.074 -.0016582 .0361216 shrelaw2 | -.0093206 .0085022 -1.10 0.273 -.0259847 .0073434 suprtw2 | .0077123 .0077451 1.00 0.319 -.0074679 .0228925 suchrw2 | .0029045 .0070402 0.41 0.680 -.0108941 .016703 havmilsq | -1.32e-06 .0000139 -0.10 0.924 -.0000286 .0000259 _cons | -16.32451 1268.684 -0.01 0.990 -2502.9 2470.251 ------------------------------------------------------------------------------ Logistic model for HP2sxlife -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 47 15 | 62 - | 19 167 | 186 -----------+--------------------------+----------- Total | 66 182 | 248 Classified + if predicted Pr(D) >= .5 True D defined as HP2sxlife != 0 -------------------------------------------------- Sensitivity Pr( +| D) 71.21% Specificity Pr( -|~D) 91.76% Positive predictive value Pr( D| +) 75.81% Negative predictive value Pr(~D| -) 89.78% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 8.24% False - rate for true D Pr( -| D) 28.79% False + rate for classified + Pr(~D| +) 24.19% False - rate for classified - Pr( D| -) 10.22% -------------------------------------------------- Correctly classified 86.29% -------------------------------------------------- Logistic model for HP2sxlife, goodness-of-fit test number of observations = 248 number of covariate patterns = 248 Pearson chi2(209) = 320.07 Prob > chi2 = 0.0000 Measures of Fit for logistic of HP2sxlife Log-Lik Intercept Only: -143.684 Log-Lik Full Model: -81.460 D(199): 162.919 LR(38): 124.448 Prob > LR: 0.000 McFadden's R2: 0.433 McFadden's Adj R2: 0.092 Maximum Likelihood R2: 0.395 Cragg & Uhler's R2: 0.575 McKelvey and Zavoina's R2: 0.701 Efron's R2: 0.489 Variance of y*: 11.005 Variance of error: 3.290 Count R2: 0.863 Adj Count R2: 0.485 AIC: 1.052 AIC*n: 260.919 BIC: -934.253 BIC': 85.062 Full main model for HP2sxlife for wave= 2 chunk 2 H1 test:Gender= 2 model Wave = 2 for HP2sxlife ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Full Nottingham Part 2 HP2sxlife subscale models ***** ***** wave 2 for gender==2 ***** ***** ***** ***** ***** ***** 16 Jun 2012 21:51:35 ***** ******************************************************************************* ******************************************************************************* i.educ _Ieduc_1-8 (naturally coded; _Ieduc_1 omitted) note: _Ieduc_8 omitted because of collinearity note: marrw26 omitted because of collinearity note: bf15 omitted because of collinearity Logistic regression Number of obs = 362 LR chi2(45) = 172.53 Prob > chi2 = 0.0000 Log likelihood = -119.99963 Pseudo R2 = 0.4182 ------------------------------------------------------------------------------ HP2sxlife | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0946676 .020348 4.65 0.000 .0547862 .1345489 _Ieduc_2 | -12.06916 856.9725 -0.01 0.989 -1691.704 1667.566 _Ieduc_3 | -10.96566 856.9724 -0.01 0.990 -1690.601 1668.669 _Ieduc_4 | -10.2721 856.9727 -0.01 0.990 -1689.908 1669.364 _Ieduc_5 | -11.78295 856.9726 -0.01 0.989 -1691.418 1667.853 _Ieduc_6 | -10.87488 856.9725 -0.01 0.990 -1690.51 1668.76 _Ieduc_7 | -10.54712 856.9809 -0.01 0.990 -1690.199 1669.105 _Ieduc_8 | 0 (omitted) occ1w2 | -1.924676 1.67129 -1.15 0.249 -5.200344 1.350992 occ2w2 | -1.071334 1.695639 -0.63 0.528 -4.394725 2.252058 occ3w2 | -.4988122 1.696518 -0.29 0.769 -3.823926 2.826301 occ4w2 | -.6837643 1.779367 -0.38 0.701 -4.171259 2.803731 occ5w2 | -.8653809 1.874647 -0.46 0.644 -4.539621 2.80886 occ6w2 | -1.70777 1.969995 -0.87 0.386 -5.568889 2.153348 occ7w2 | -.9209399 1.641247 -0.56 0.575 -4.137725 2.295845 occ8w2 | -.5235734 1.936624 -0.27 0.787 -4.319287 3.272141 marrw21 | -.4474367 1.15873 -0.39 0.699 -2.718505 1.823632 marrw22 | -.2713813 1.430959 -0.19 0.850 -3.07601 2.533247 marrw23 | -.6859987 .8247327 -0.83 0.406 -2.302445 .9304478 marrw25 | -1.534831 1.287976 -1.19 0.233 -4.059218 .9895558 marrw26 | 0 (omitted) inc1w2 | .1793057 1.714781 0.10 0.917 -3.181602 3.540214 inc2w2 | .5322943 1.648367 0.32 0.747 -2.698446 3.763035 inc3w2 | -.4148838 1.696991 -0.24 0.807 -3.740924 2.911157 inc4w2 | -.3610821 2.088477 -0.17 0.863 -4.454421 3.732257 radhlw2 | .0084415 .0066869 1.26 0.207 -.0046645 .0215475 havmil | -.0012719 .0033206 -0.38 0.702 -.0077802 .0052364 avgcumdosew2 | .131101 .1238204 1.06 0.290 -.1115826 .3737846 bf1 | -.0011966 .0090476 -0.13 0.895 -.0189295 .0165364 bf4 | -.1626538 .0410542 -3.96 0.000 -.2431185 -.0821891 bf6 | -.0040259 .0075131 -0.54 0.592 -.0187513 .0106995 bf7 | -.07395 .0811067 -0.91 0.362 -.2329163 .0850162 bf14 | -.000028 .0000759 -0.37 0.712 -.0001769 .0001208 bf15 | 0 (omitted) bf40 | .0142117 .0784184 0.18 0.856 -.1394855 .1679089 deaw2 | .0365782 .2150994 0.17 0.865 -.3850089 .4581654 dvcew2 | -.8025004 1.585115 -0.51 0.613 -3.909268 2.304268 sepaw2 | -.5574826 2.582905 -0.22 0.829 -5.619883 4.504918 accdw2 | -.5477504 .6503834 -0.84 0.400 -1.822478 .7269777 movew2 | .1966685 .5120534 0.38 0.701 -.8069378 1.200275 illw2 | .5493357 .2439985 2.25 0.024 .0711074 1.027564 shfamw2 | .0017721 .0066016 0.27 0.788 -.0111667 .0147109 shhlw2 | .0069859 .006691 1.04 0.296 -.0061281 .0201 shjobw2 | -.0075261 .0063225 -1.19 0.234 -.019918 .0048658 shrelaw2 | -.0137558 .0073868 -1.86 0.063 -.0282337 .000722 suprtw2 | -.0141433 .0055222 -2.56 0.010 -.0249667 -.0033199 suchrw2 | .0162332 .0063006 2.58 0.010 .0038842 .0285821 havmilsq | -1.92e-07 2.92e-06 -0.07 0.948 -5.91e-06 5.53e-06 _cons | 7.796544 856.9744 0.01 0.993 -1671.842 1687.436 ------------------------------------------------------------------------------ Logistic model for HP2sxlife -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 59 19 | 78 - | 34 250 | 284 -----------+--------------------------+----------- Total | 93 269 | 362 Classified + if predicted Pr(D) >= .5 True D defined as HP2sxlife != 0 -------------------------------------------------- Sensitivity Pr( +| D) 63.44% Specificity Pr( -|~D) 92.94% Positive predictive value Pr( D| +) 75.64% Negative predictive value Pr(~D| -) 88.03% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 7.06% False - rate for true D Pr( -| D) 36.56% False + rate for classified + Pr(~D| +) 24.36% False - rate for classified - Pr( D| -) 11.97% -------------------------------------------------- Correctly classified 85.36% -------------------------------------------------- Logistic model for HP2sxlife, goodness-of-fit test number of observations = 362 number of covariate patterns = 362 Pearson chi2(316) = 350.60 Prob > chi2 = 0.0877 Measures of Fit for logistic of HP2sxlife Log-Lik Intercept Only: -206.266 Log-Lik Full Model: -120.000 D(313): 239.999 LR(45): 172.533 Prob > LR: 0.000 McFadden's R2: 0.418 McFadden's Adj R2: 0.181 Maximum Likelihood R2: 0.379 Cragg & Uhler's R2: 0.557 McKelvey and Zavoina's R2: 0.643 Efron's R2: 0.461 Variance of y*: 9.209 Variance of error: 3.290 Count R2: 0.854 Adj Count R2: 0.430 AIC: 0.934 AIC*n: 337.999 BIC: -1604.085 BIC': 92.591 Full main model for HP2inthob for wave= 2 chunk 2 H1 test:Gender= 1 model Wave = 2 for HP2sxlife ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Full Nottingham Part 2 HP2inthob subscale models ***** ***** wave 2 for gender==1 ***** ***** ***** ***** ***** ***** 16 Jun 2012 21:51:37 ***** ******************************************************************************* ******************************************************************************* i.educ _Ieduc_1-8 (naturally coded; _Ieduc_1 omitted) note: _Ieduc_4 != 0 predicts failure perfectly _Ieduc_4 dropped and 12 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: occ6w2 != 0 predicts failure perfectly occ6w2 dropped and 4 obs not used note: occ8w2 != 0 predicts failure perfectly occ8w2 dropped and 43 obs not used note: marrw22 != 0 predicts failure perfectly marrw22 dropped and 7 obs not used note: marrw25 != 0 predicts failure perfectly marrw25 dropped and 4 obs not used note: marrw26 != 0 predicts failure perfectly marrw26 dropped and 3 obs not used note: inc4w2 != 0 predicts failure perfectly inc4w2 dropped and 9 obs not used note: dvcew2 != 0 predicts failure perfectly dvcew2 dropped and 3 obs not used note: sepaw2 != 0 predicts failure perfectly sepaw2 dropped and 1 obs not used note: _Ieduc_6 omitted because of collinearity note: bf15 omitted because of collinearity Logistic regression Number of obs = 240 LR chi2(35) = 92.50 Prob > chi2 = 0.0000 Log likelihood = -55.199011 Pseudo R2 = 0.4559 ------------------------------------------------------------------------------ HP2inthob | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0625698 .0339541 1.84 0.065 -.0039791 .1291186 _Ieduc_2 | -1.043358 1.579537 -0.66 0.509 -4.139194 2.052478 _Ieduc_3 | -1.383026 .8161024 -1.69 0.090 -2.982558 .216505 _Ieduc_4 | 0 (omitted) _Ieduc_5 | -.3882601 .890757 -0.44 0.663 -2.134112 1.357591 _Ieduc_6 | 0 (omitted) _Ieduc_7 | 0 (omitted) _Ieduc_8 | 0 (omitted) occ1w2 | -1.033982 5.222537 -0.20 0.843 -11.26997 9.202003 occ2w2 | -2.764859 5.282979 -0.52 0.601 -13.11931 7.58959 occ3w2 | -1.159373 5.266774 -0.22 0.826 -11.48206 9.163314 occ4w2 | -1.475817 5.272908 -0.28 0.780 -11.81053 8.858893 occ5w2 | .6777917 5.260041 0.13 0.897 -9.631698 10.98728 occ6w2 | 0 (omitted) occ7w2 | -.3442089 5.327123 -0.06 0.948 -10.78518 10.09676 occ8w2 | 0 (omitted) marrw21 | 13.93224 1621.282 0.01 0.993 -3163.721 3191.586 marrw22 | 0 (omitted) marrw23 | 11.47436 1621.282 0.01 0.994 -3166.179 3189.128 marrw25 | 0 (omitted) marrw26 | 0 (omitted) inc1w2 | -2.09725 5.429773 -0.39 0.699 -12.73941 8.544909 inc2w2 | -.9256519 5.257192 -0.18 0.860 -11.22956 9.378255 inc3w2 | .0745765 5.245026 0.01 0.989 -10.20548 10.35464 inc4w2 | 0 (omitted) radhlw2 | .0364231 .0131057 2.78 0.005 .0107363 .0621099 havmil | .0020332 .0091412 0.22 0.824 -.0158833 .0199497 avgcumdosew2 | -.2023055 .3376483 -0.60 0.549 -.8640841 .4594731 bf1 | .0108557 .0182727 0.59 0.552 -.0249582 .0466696 bf4 | -.290932 .0816796 -3.56 0.000 -.4510211 -.1308428 bf6 | .0111353 .0131635 0.85 0.398 -.0146647 .0369353 bf7 | .0337038 .1171208 0.29 0.774 -.1958487 .2632562 bf14 | -.000219 .0001127 -1.94 0.052 -.0004398 1.92e-06 bf15 | 0 (omitted) bf40 | .490857 .2032201 2.42 0.016 .0925529 .889161 deaw2 | .006222 .5178905 0.01 0.990 -1.008825 1.021269 dvcew2 | 0 (omitted) sepaw2 | 0 (omitted) accdw2 | 1.036869 .5663339 1.83 0.067 -.0731249 2.146863 movew2 | .7948452 .8450104 0.94 0.347 -.8613447 2.451035 illw2 | -.8262786 .5178561 -1.60 0.111 -1.841258 .1887007 shfamw2 | -.003778 .0101348 -0.37 0.709 -.0236419 .0160858 shhlw2 | -.0014472 .0125099 -0.12 0.908 -.0259662 .0230717 shjobw2 | .0044446 .012101 0.37 0.713 -.0192728 .0281621 shrelaw2 | -.0158848 .0098629 -1.61 0.107 -.0352157 .0034461 suprtw2 | -.0048211 .0089741 -0.54 0.591 -.0224099 .0127678 suchrw2 | .016543 .008867 1.87 0.062 -.0008361 .033922 havmilsq | -2.84e-06 .0000159 -0.18 0.858 -.000034 .0000283 _cons | -16.47971 1621.283 -0.01 0.992 -3194.136 3161.177 ------------------------------------------------------------------------------ Note: 1 failure and 0 successes completely determined. Logistic model for HP2inthob -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 20 6 | 26 - | 16 198 | 214 -----------+--------------------------+----------- Total | 36 204 | 240 Classified + if predicted Pr(D) >= .5 True D defined as HP2inthob != 0 -------------------------------------------------- Sensitivity Pr( +| D) 55.56% Specificity Pr( -|~D) 97.06% Positive predictive value Pr( D| +) 76.92% Negative predictive value Pr(~D| -) 92.52% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 2.94% False - rate for true D Pr( -| D) 44.44% False + rate for classified + Pr(~D| +) 23.08% False - rate for classified - Pr( D| -) 7.48% -------------------------------------------------- Correctly classified 90.83% -------------------------------------------------- Logistic model for HP2inthob, goodness-of-fit test number of observations = 240 number of covariate patterns = 240 Pearson chi2(204) = 545.84 Prob > chi2 = 0.0000 Measures of Fit for logistic of HP2inthob Log-Lik Intercept Only: -101.450 Log-Lik Full Model: -55.199 D(191): 110.398 LR(35): 92.502 Prob > LR: 0.000 McFadden's R2: 0.456 McFadden's Adj R2: -0.027 Maximum Likelihood R2: 0.320 Cragg & Uhler's R2: 0.561 McKelvey and Zavoina's R2: 0.776 Efron's R2: 0.482 Variance of y*: 14.694 Variance of error: 3.290 Count R2: 0.908 Adj Count R2: 0.389 AIC: 0.868 AIC*n: 208.398 BIC: -936.404 BIC': 99.320 Full main model for HP2inthob for wave= 2 chunk 2 H1 test:Gender= 2 model Wave = 2 for HP2inthob ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Full Nottingham Part 2 HP2inthob subscale models ***** ***** wave 2 for gender==2 ***** ***** ***** ***** ***** ***** 16 Jun 2012 21:51:38 ***** ******************************************************************************* ******************************************************************************* i.educ _Ieduc_1-8 (naturally coded; _Ieduc_1 omitted) note: sepaw2 != 0 predicts failure perfectly sepaw2 dropped and 8 obs not used note: _Ieduc_8 omitted because of collinearity note: marrw26 omitted because of collinearity note: bf15 omitted because of collinearity Logistic regression Number of obs = 354 LR chi2(44) = 115.47 Prob > chi2 = 0.0000 Log likelihood = -111.06431 Pseudo R2 = 0.3420 ------------------------------------------------------------------------------ HP2inthob | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .079863 .021131 3.78 0.000 .0384469 .121279 _Ieduc_2 | -12.93831 1490.754 -0.01 0.993 -2934.762 2908.885 _Ieduc_3 | -12.4076 1490.754 -0.01 0.993 -2934.231 2909.416 _Ieduc_4 | -11.72169 1490.754 -0.01 0.994 -2933.546 2910.102 _Ieduc_5 | -12.09518 1490.754 -0.01 0.994 -2933.919 2909.728 _Ieduc_6 | -12.44516 1490.754 -0.01 0.993 -2934.269 2909.378 _Ieduc_7 | -12.06531 1490.757 -0.01 0.994 -2933.895 2909.764 _Ieduc_8 | 0 (omitted) occ1w2 | -1.681778 1.842381 -0.91 0.361 -5.292779 1.929222 occ2w2 | -2.066763 1.905083 -1.08 0.278 -5.800657 1.66713 occ3w2 | -.925484 1.867622 -0.50 0.620 -4.585956 2.734988 occ4w2 | -1.837685 1.997812 -0.92 0.358 -5.753324 2.077954 occ5w2 | -1.808015 2.160492 -0.84 0.403 -6.042501 2.426471 occ6w2 | -.7980572 2.0458 -0.39 0.696 -4.807751 3.211637 occ7w2 | -.6513668 1.8133 -0.36 0.719 -4.205369 2.902636 occ8w2 | -.7497523 2.02704 -0.37 0.711 -4.722678 3.223174 marrw21 | 1.330155 1.130799 1.18 0.239 -.8861701 3.546479 marrw22 | .1433998 1.421047 0.10 0.920 -2.641801 2.9286 marrw23 | .3124211 .8029396 0.39 0.697 -1.261312 1.886154 marrw25 | .2321157 1.213839 0.19 0.848 -2.146964 2.611196 marrw26 | 0 (omitted) inc1w2 | 1.002608 1.857433 0.54 0.589 -2.637893 4.643109 inc2w2 | 1.21648 1.809887 0.67 0.502 -2.330833 4.763793 inc3w2 | .8716928 1.845137 0.47 0.637 -2.744709 4.488095 inc4w2 | 2.25991 2.119136 1.07 0.286 -1.893519 6.41334 radhlw2 | .0169047 .0075432 2.24 0.025 .0021202 .0316892 havmil | .0026206 .00401 0.65 0.513 -.0052388 .0104801 avgcumdosew2 | .1098391 .1075167 1.02 0.307 -.1008897 .3205679 bf1 | -.0101735 .0098443 -1.03 0.301 -.029468 .0091209 bf4 | -.160166 .0433489 -3.69 0.000 -.2451282 -.0752038 bf6 | -.0029228 .0086097 -0.34 0.734 -.0197974 .0139519 bf7 | -.0201783 .0882604 -0.23 0.819 -.1931656 .152809 bf14 | -.0000789 .0000837 -0.94 0.346 -.000243 .0000853 bf15 | 0 (omitted) bf40 | -.0387073 .0922777 -0.42 0.675 -.2195682 .1421537 deaw2 | .1202612 .2113024 0.57 0.569 -.2938838 .5344063 dvcew2 | .0143372 1.477099 0.01 0.992 -2.880724 2.909399 sepaw2 | 0 (omitted) accdw2 | .4772298 .6036102 0.79 0.429 -.7058243 1.660284 movew2 | -.5141092 .7928535 -0.65 0.517 -2.068073 1.039855 illw2 | .1586699 .2249295 0.71 0.481 -.2821838 .5995235 shfamw2 | -.0005225 .0071722 -0.07 0.942 -.0145799 .0135348 shhlw2 | .0069143 .0072142 0.96 0.338 -.0072252 .0210539 shjobw2 | -.0096031 .0066833 -1.44 0.151 -.0227021 .003496 shrelaw2 | -.011349 .0077316 -1.47 0.142 -.0265027 .0038047 suprtw2 | -.01257 .0057932 -2.17 0.030 -.0239246 -.0012155 suchrw2 | .000171 .0063873 0.03 0.979 -.0123478 .0126898 havmilsq | -2.75e-06 5.84e-06 -0.47 0.638 -.0000142 8.69e-06 _cons | 8.21905 1490.755 0.01 0.996 -2913.607 2930.045 ------------------------------------------------------------------------------ Note: 1 failure and 0 successes completely determined. Logistic model for HP2inthob -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 35 12 | 47 - | 30 277 | 307 -----------+--------------------------+----------- Total | 65 289 | 354 Classified + if predicted Pr(D) >= .5 True D defined as HP2inthob != 0 -------------------------------------------------- Sensitivity Pr( +| D) 53.85% Specificity Pr( -|~D) 95.85% Positive predictive value Pr( D| +) 74.47% Negative predictive value Pr(~D| -) 90.23% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 4.15% False - rate for true D Pr( -| D) 46.15% False + rate for classified + Pr(~D| +) 25.53% False - rate for classified - Pr( D| -) 9.77% -------------------------------------------------- Correctly classified 88.14% -------------------------------------------------- Logistic model for HP2inthob, goodness-of-fit test number of observations = 354 number of covariate patterns = 354 Pearson chi2(309) = 384.69 Prob > chi2 = 0.0022 Measures of Fit for logistic of HP2inthob Log-Lik Intercept Only: -168.799 Log-Lik Full Model: -111.064 D(305): 222.129 LR(44): 115.469 Prob > LR: 0.000 McFadden's R2: 0.342 McFadden's Adj R2: 0.052 Maximum Likelihood R2: 0.278 Cragg & Uhler's R2: 0.453 McKelvey and Zavoina's R2: 0.619 Efron's R2: 0.372 Variance of y*: 8.629 Variance of error: 3.290 Count R2: 0.881 Adj Count R2: 0.354 AIC: 0.904 AIC*n: 320.129 BIC: -1568.007 BIC': 142.780 Full main model for HP2vacatn for wave= 2 chunk 2 H1 test:Gender= 1 model Wave = 2 for HP2inthob ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Full Nottingham Part 2 HP2vacatn subscale models ***** ***** wave 2 for gender==1 ***** ***** ***** ***** ***** ***** 16 Jun 2012 21:51:40 ***** ******************************************************************************* ******************************************************************************* i.educ _Ieduc_1-8 (naturally coded; _Ieduc_1 omitted) note: _Ieduc_4 != 0 predicts failure perfectly _Ieduc_4 dropped and 12 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: occ6w2 != 0 predicts failure perfectly occ6w2 dropped and 4 obs not used note: occ8w2 != 0 predicts failure perfectly occ8w2 dropped and 43 obs not used note: marrw22 != 0 predicts failure perfectly marrw22 dropped and 7 obs not used note: marrw26 != 0 predicts failure perfectly marrw26 dropped and 3 obs not used note: inc1w2 != 0 predicts failure perfectly inc1w2 dropped and 15 obs not used note: inc4w2 != 0 predicts failure perfectly inc4w2 dropped and 10 obs not used note: sepaw2 != 0 predicts failure perfectly sepaw2 dropped and 3 obs not used note: marrw25 != 0 predicts success perfectly marrw25 dropped and 1 obs not used note: dvcew2 != 0 predicts failure perfectly dvcew2 dropped and 2 obs not used note: _Ieduc_6 omitted because of collinearity note: bf15 omitted because of collinearity Logistic regression Number of obs = 226 LR chi2(34) = 89.37 Prob > chi2 = 0.0000 Log likelihood = -56.061123 Pseudo R2 = 0.4435 ------------------------------------------------------------------------------ HP2vacatn | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0518481 .0320007 1.62 0.105 -.0108721 .1145682 _Ieduc_2 | -.8995561 1.385138 -0.65 0.516 -3.614377 1.815265 _Ieduc_3 | -.9705268 .7645926 -1.27 0.204 -2.469101 .5280471 _Ieduc_4 | 0 (omitted) _Ieduc_5 | .2832276 .9129115 0.31 0.756 -1.506046 2.072501 _Ieduc_6 | 0 (omitted) _Ieduc_7 | 0 (omitted) _Ieduc_8 | 0 (omitted) occ1w2 | .8106927 4.39778 0.18 0.854 -7.808798 9.430184 occ2w2 | .6920438 4.410202 0.16 0.875 -7.951794 9.335881 occ3w2 | .1305127 4.486304 0.03 0.977 -8.662482 8.923507 occ4w2 | .89698 4.456507 0.20 0.840 -7.837613 9.631573 occ5w2 | 2.521801 4.487812 0.56 0.574 -6.274149 11.31775 occ6w2 | 0 (omitted) occ7w2 | -.3588464 4.557173 -0.08 0.937 -9.290741 8.573048 occ8w2 | 0 (omitted) marrw21 | -2.421712 1.8269 -1.33 0.185 -6.002369 1.158946 marrw22 | 0 (omitted) marrw23 | -3.630848 1.854766 -1.96 0.050 -7.266123 .0044279 marrw25 | 0 (omitted) marrw26 | 0 (omitted) inc1w2 | 0 (omitted) inc2w2 | 1.85842 4.404089 0.42 0.673 -6.773436 10.49027 inc3w2 | 2.742231 4.406664 0.62 0.534 -5.894672 11.37913 inc4w2 | 0 (omitted) radhlw2 | .0040453 .0113057 0.36 0.720 -.0181135 .0262041 havmil | .0057124 .0149305 0.38 0.702 -.0235508 .0349756 avgcumdosew2 | -.2290056 .2971244 -0.77 0.441 -.8113587 .3533474 bf1 | -.0014462 .0165487 -0.09 0.930 -.0338809 .0309886 bf4 | -.3542988 .0849763 -4.17 0.000 -.5208492 -.1877483 bf6 | .0330318 .0142347 2.32 0.020 .0051324 .0609312 bf7 | .138525 .1284222 1.08 0.281 -.1131778 .3902278 bf14 | -.0001823 .0001057 -1.72 0.085 -.0003895 .0000249 bf15 | 0 (omitted) bf40 | .7151656 .2261712 3.16 0.002 .2718781 1.158453 deaw2 | -.1293481 .4547459 -0.28 0.776 -1.020634 .7619374 dvcew2 | 0 (omitted) sepaw2 | 0 (omitted) accdw2 | .6561002 .566831 1.16 0.247 -.4548681 1.767069 movew2 | .8988969 .8083424 1.11 0.266 -.6854251 2.483219 illw2 | -.1907347 .4011558 -0.48 0.634 -.9769857 .5955162 shfamw2 | .0075499 .0104385 0.72 0.470 -.0129092 .0280089 shhlw2 | -.0086364 .01369 -0.63 0.528 -.0354682 .0181955 shjobw2 | -.0142832 .0135576 -1.05 0.292 -.0408556 .0122892 shrelaw2 | -.0233172 .0117345 -1.99 0.047 -.0463164 -.000318 suprtw2 | .0076256 .010193 0.75 0.454 -.0123524 .0276036 suchrw2 | -.0031525 .0091098 -0.35 0.729 -.0210073 .0147023 havmilsq | -.00002 .0000344 -0.58 0.560 -.0000874 .0000473 _cons | -2.643954 3.239572 -0.82 0.414 -8.993397 3.70549 ------------------------------------------------------------------------------ Note: 1 failure and 0 successes completely determined. Logistic model for HP2vacatn -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 23 5 | 28 - | 14 184 | 198 -----------+--------------------------+----------- Total | 37 189 | 226 Classified + if predicted Pr(D) >= .5 True D defined as HP2vacatn != 0 -------------------------------------------------- Sensitivity Pr( +| D) 62.16% Specificity Pr( -|~D) 97.35% Positive predictive value Pr( D| +) 82.14% Negative predictive value Pr(~D| -) 92.93% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 2.65% False - rate for true D Pr( -| D) 37.84% False + rate for classified + Pr(~D| +) 17.86% False - rate for classified - Pr( D| -) 7.07% -------------------------------------------------- Correctly classified 91.59% -------------------------------------------------- Logistic model for HP2vacatn, goodness-of-fit test number of observations = 226 number of covariate patterns = 226 Pearson chi2(191) = 516.74 Prob > chi2 = 0.0000 Measures of Fit for logistic of HP2vacatn Log-Lik Intercept Only: -100.747 Log-Lik Full Model: -56.061 D(177): 112.122 LR(34): 89.371 Prob > LR: 0.000 McFadden's R2: 0.444 McFadden's Adj R2: -0.043 Maximum Likelihood R2: 0.327 Cragg & Uhler's R2: 0.554 McKelvey and Zavoina's R2: 0.764 Efron's R2: 0.489 Variance of y*: 13.933 Variance of error: 3.290 Count R2: 0.916 Adj Count R2: 0.486 AIC: 0.930 AIC*n: 210.122 BIC: -847.312 BIC': 94.927 Full main model for HP2vacatn for wave= 2 chunk 2 H1 test:Gender= 2 model Wave = 2 for HP2vacatn ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Full Nottingham Part 2 HP2vacatn subscale models ***** ***** wave 2 for gender==2 ***** ***** ***** ***** ***** ***** 16 Jun 2012 21:51:41 ***** ******************************************************************************* ******************************************************************************* i.educ _Ieduc_1-8 (naturally coded; _Ieduc_1 omitted) note: sepaw2 != 0 predicts failure perfectly sepaw2 dropped and 8 obs not used note: _Ieduc_8 omitted because of collinearity note: marrw26 omitted because of collinearity note: bf15 omitted because of collinearity Logistic regression Number of obs = 354 LR chi2(44) = 111.91 Prob > chi2 = 0.0000 Log likelihood = -108.2809 Pseudo R2 = 0.3407 ------------------------------------------------------------------------------ HP2vacatn | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0893137 .0216493 4.13 0.000 .0468818 .1317456 _Ieduc_2 | -14.53546 998.8236 -0.01 0.988 -1972.194 1943.123 _Ieduc_3 | -14.6778 998.8236 -0.01 0.988 -1972.336 1942.981 _Ieduc_4 | -12.98634 998.8239 -0.01 0.990 -1970.645 1944.672 _Ieduc_5 | -14.15108 998.8238 -0.01 0.989 -1971.81 1943.508 _Ieduc_6 | -14.14507 998.8236 -0.01 0.989 -1971.803 1943.513 _Ieduc_7 | -14.60252 998.8256 -0.01 0.988 -1972.265 1943.06 _Ieduc_8 | 0 (omitted) occ1w2 | -.862164 2.392979 -0.36 0.719 -5.552316 3.827988 occ2w2 | .000175 2.407446 0.00 1.000 -4.718332 4.718682 occ3w2 | .0954163 2.407091 0.04 0.968 -4.622395 4.813227 occ4w2 | -.7520064 2.479333 -0.30 0.762 -5.61141 4.107398 occ5w2 | -.8008531 2.678457 -0.30 0.765 -6.050532 4.448826 occ6w2 | -.120062 2.547159 -0.05 0.962 -5.112401 4.872278 occ7w2 | .0075488 2.349651 0.00 0.997 -4.597682 4.61278 occ8w2 | 1.363519 2.668018 0.51 0.609 -3.8657 6.592739 marrw21 | .0044997 1.254312 0.00 0.997 -2.453907 2.462906 marrw22 | -.1027305 1.362298 -0.08 0.940 -2.772785 2.567324 marrw23 | .1467459 .8080411 0.18 0.856 -1.436986 1.730477 marrw25 | .0219803 1.235341 0.02 0.986 -2.399244 2.443205 marrw26 | 0 (omitted) inc1w2 | -.4927145 2.398088 -0.21 0.837 -5.192881 4.207452 inc2w2 | .280804 2.359963 0.12 0.905 -4.344638 4.906246 inc3w2 | .1828947 2.366651 0.08 0.938 -4.455656 4.821445 inc4w2 | -.2400624 2.690874 -0.09 0.929 -5.514079 5.033954 radhlw2 | .0222207 .0077189 2.88 0.004 .0070919 .0373496 havmil | .0004923 .0030889 0.16 0.873 -.0055619 .0065465 avgcumdosew2 | .0521813 .1224679 0.43 0.670 -.1878514 .2922141 bf1 | -.0290072 .0107044 -2.71 0.007 -.0499874 -.0080269 bf4 | -.1358474 .0436692 -3.11 0.002 -.2214376 -.0502573 bf6 | .0008464 .0089639 0.09 0.925 -.0167225 .0184153 bf7 | .091511 .0838763 1.09 0.275 -.0728836 .2559055 bf14 | -.0001329 .0000932 -1.43 0.154 -.0003155 .0000496 bf15 | 0 (omitted) bf40 | -.088322 .1002957 -0.88 0.379 -.2848979 .1082539 deaw2 | .2253226 .214436 1.05 0.293 -.1949642 .6456094 dvcew2 | 1.943345 1.290529 1.51 0.132 -.5860453 4.472735 sepaw2 | 0 (omitted) accdw2 | -.5786213 .7839833 -0.74 0.460 -2.1152 .9579576 movew2 | .0523756 .7206426 0.07 0.942 -1.360058 1.464809 illw2 | .3527103 .2271102 1.55 0.120 -.0924176 .7978382 shfamw2 | .0116122 .0069058 1.68 0.093 -.001923 .0251474 shhlw2 | .0049385 .0075176 0.66 0.511 -.0097958 .0196728 shjobw2 | -.0062545 .006891 -0.91 0.364 -.0197605 .0072516 shrelaw2 | -.0200226 .0083906 -2.39 0.017 -.0364678 -.0035773 suprtw2 | -.0064369 .005962 -1.08 0.280 -.0181221 .0052483 suchrw2 | .0058273 .0067013 0.87 0.385 -.0073069 .0189615 havmilsq | -8.06e-07 2.86e-06 -0.28 0.778 -6.41e-06 4.80e-06 _cons | 9.013612 998.8259 0.01 0.993 -1948.649 1966.676 ------------------------------------------------------------------------------ Logistic model for HP2vacatn -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 31 10 | 41 - | 31 282 | 313 -----------+--------------------------+----------- Total | 62 292 | 354 Classified + if predicted Pr(D) >= .5 True D defined as HP2vacatn != 0 -------------------------------------------------- Sensitivity Pr( +| D) 50.00% Specificity Pr( -|~D) 96.58% Positive predictive value Pr( D| +) 75.61% Negative predictive value Pr(~D| -) 90.10% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 3.42% False - rate for true D Pr( -| D) 50.00% False + rate for classified + Pr(~D| +) 24.39% False - rate for classified - Pr( D| -) 9.90% -------------------------------------------------- Correctly classified 88.42% -------------------------------------------------- Logistic model for HP2vacatn, goodness-of-fit test number of observations = 354 number of covariate patterns = 354 Pearson chi2(309) = 372.41 Prob > chi2 = 0.0077 Measures of Fit for logistic of HP2vacatn Log-Lik Intercept Only: -164.237 Log-Lik Full Model: -108.281 D(305): 216.562 LR(44): 111.912 Prob > LR: 0.000 McFadden's R2: 0.341 McFadden's Adj R2: 0.042 Maximum Likelihood R2: 0.271 Cragg & Uhler's R2: 0.448 McKelvey and Zavoina's R2: 0.585 Efron's R2: 0.371 Variance of y*: 7.926 Variance of error: 3.290 Count R2: 0.884 Adj Count R2: 0.339 AIC: 0.889 AIC*n: 314.562 BIC: -1573.574 BIC': 146.338 118 . 119 . set more off 120 . *-----Chunk 2 dosew2 moderator paid employment impact------------------------ > --- 121 . title "1. Hp2work H1 pt2 wv 2 male rad dose and HP2work impact " ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** 1. Hp2work H1 pt2 wv 2 male rad dose and HP2work impact ***** ***** ***** ***** ***** ***** 16 Jun 2012 21:51:43 ***** ******************************************************************************* ******************************************************************************* 122 . * male models 123 . forvalues j = 2/2 { 2. title3 "trimmed HP2work main effects models wave 1 for H1 part 2 with dose > ns" 3. title "Wave `j' dose HP2work relationship but avgcumdosew`j': Dose not sig > nif" 4. di _skip(2) 5. di as input "Gender =1 HP2work model" 6. logit HP2work age bf4 bf40 illw`j' movew`j' shrelaw`j' /// > avgcumdosew`j' radhlw`j' if gender==1 7. estat class 8. estat gof 9. fitstat 10. } ------------------------------------------------------------------------------- title3 : trimmed HP2work main effects models wave 1 for H1 part 2 with dose ns 16 Jun 2012 21:51:43 computer Macintosh (Intel 64-bit) folder /Users/robertyaffee/Documents/data/research/chwk/phase3/Htests/h1tests/ > h1pt2 Data file chwide16june2012.dta currrently has 2374 variables and 703 obse > rvations ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Wave 2 dose HP2work relationship but avgcumdosew2: Dose not signif ***** ***** ***** ***** ***** ***** 16 Jun 2012 21:51:43 ***** ******************************************************************************* ******************************************************************************* Gender =1 HP2work model Iteration 0: log likelihood = -172.64201 Iteration 1: log likelihood = -143.10953 Iteration 2: log likelihood = -140.75282 Iteration 3: log likelihood = -140.73717 Iteration 4: log likelihood = -140.73717 Logistic regression Number of obs = 339 LR chi2(8) = 63.81 Prob > chi2 = 0.0000 Log likelihood = -140.73717 Pseudo R2 = 0.1848 ------------------------------------------------------------------------------ HP2work | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0047169 .0143138 0.33 0.742 -.0233376 .0327714 bf4 | -.1503587 .0356506 -4.22 0.000 -.2202327 -.0804848 bf40 | .3523359 .1019141 3.46 0.001 .1525879 .5520839 illw2 | -.0335556 .2419386 -0.14 0.890 -.5077465 .4406354 movew2 | .5741457 .3222115 1.78 0.075 -.0573772 1.205669 shrelaw2 | -.007559 .0045614 -1.66 0.097 -.0164991 .0013811 avgcumdosew2 | .0038936 .0526483 0.07 0.941 -.0992953 .1070824 radhlw2 | .00178 .0052528 0.34 0.735 -.0085154 .0120754 _cons | -.7511547 .9928636 -0.76 0.449 -2.697132 1.194822 ------------------------------------------------------------------------------ Logistic model for HP2work -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 21 13 | 34 - | 49 256 | 305 -----------+--------------------------+----------- Total | 70 269 | 339 Classified + if predicted Pr(D) >= .5 True D defined as HP2work != 0 -------------------------------------------------- Sensitivity Pr( +| D) 30.00% Specificity Pr( -|~D) 95.17% Positive predictive value Pr( D| +) 61.76% Negative predictive value Pr(~D| -) 83.93% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 4.83% False - rate for true D Pr( -| D) 70.00% False + rate for classified + Pr(~D| +) 38.24% False - rate for classified - Pr( D| -) 16.07% -------------------------------------------------- Correctly classified 81.71% -------------------------------------------------- Logistic model for HP2work, goodness-of-fit test number of observations = 339 number of covariate patterns = 334 Pearson chi2(325) = 305.63 Prob > chi2 = 0.7731 Measures of Fit for logit of HP2work Log-Lik Intercept Only: -172.642 Log-Lik Full Model: -140.737 D(330): 281.474 LR(8): 63.810 Prob > LR: 0.000 McFadden's R2: 0.185 McFadden's Adj R2: 0.133 Maximum Likelihood R2: 0.172 Cragg & Uhler's R2: 0.269 McKelvey and Zavoina's R2: 0.282 Efron's R2: 0.184 Variance of y*: 4.584 Variance of error: 3.290 Count R2: 0.817 Adj Count R2: 0.114 AIC: 0.883 AIC*n: 299.474 BIC: -1641.106 BIC': -17.202 124 . 125 . title4 "Tests for male moderators in wave 2 for HP2work" ------------------------------------------------------------------------------- Tests for male moderators in wave 2 for HP2work ------------------------------------------------------------------------------- 126 . * construction of potential moderators 127 . 128 . 129 . foreach var in bf4 bf40 { 2. cap gen `var'Xd2 = `var'*avgcumdosew2 3. label var `var'Xd2 "interaction of avgcumdosew2 and `var'" 4. } 130 . 131 . 132 . 133 . 134 . 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) 135 . forvalues j = 2/2 { 2. title4 "trimmed HP2work main effects models wave `j' " "male model for H1 > part 2 with dose ns" 3. title2 "Wave `j dose HP2work relationship but avgcumdosew`j': Dose not sig > nif" 4. } ------------------------------------------------------------------------------- trimmed HP2work main effects models wave 2 ------------------------------------------------------------------------------- ------------------------------------------------------------------------------- title2: Wave `j dose HP2work relationship but avgcumdosew2: Dose not signif Date and time: 16 Jun 2012 21:51:44 Working directory: /Users/robertyaffee/ > Documents/data/research/chwk/phase3/Htests/h1tests/h1pt2 Stata data file: chwide16june2012.dta > has 2376 variables and 703 observations Wave `j dose HP2work relationship but avgcumdosew2: Dose not signif ------------------------------------------------------------------------------- 136 . 137 . 138 . set more off 139 . 140 . forvalues j = 2/2 { 2. sw, pr(.1):logistic HP2work age bf4 bf40 movew`j' shrelaw` > j' /// > avgcumdosew`j' illw2 radhlw`j' bf4Xd2 bf40Xd2 if gender==1, c > oef 3. estat class 4. estat gof 5. fitstat 6. } begin with full model p = 0.9757 >= 0.1000 removing illw2 p = 0.7795 >= 0.1000 removing radhlw2 p = 0.7737 >= 0.1000 removing avgcumdosew2 p = 0.6592 >= 0.1000 removing age p = 0.3222 >= 0.1000 removing bf40Xd2 p = 0.8752 >= 0.1000 removing bf4Xd2 Logistic regression Number of obs = 339 LR chi2(4) = 63.51 Prob > chi2 = 0.0000 Log likelihood = -140.88616 Pseudo R2 = 0.1839 ------------------------------------------------------------------------------ HP2work | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- shrelaw2 | -.0075236 .0045549 -1.65 0.099 -.016451 .0014037 bf4 | -.1587735 .0291898 -5.44 0.000 -.2159845 -.1015625 bf40 | .3608735 .0919302 3.93 0.000 .1806936 .5410534 movew2 | .5377149 .3084581 1.74 0.081 -.0668519 1.142282 _cons | -.3430408 .4475445 -0.77 0.443 -1.220212 .5341304 ------------------------------------------------------------------------------ Logistic model for HP2work -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 21 15 | 36 - | 49 254 | 303 -----------+--------------------------+----------- Total | 70 269 | 339 Classified + if predicted Pr(D) >= .5 True D defined as HP2work != 0 -------------------------------------------------- Sensitivity Pr( +| D) 30.00% Specificity Pr( -|~D) 94.42% Positive predictive value Pr( D| +) 58.33% Negative predictive value Pr(~D| -) 83.83% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 5.58% False - rate for true D Pr( -| D) 70.00% False + rate for classified + Pr(~D| +) 41.67% False - rate for classified - Pr( D| -) 16.17% -------------------------------------------------- Correctly classified 81.12% -------------------------------------------------- Logistic model for HP2work, goodness-of-fit test number of observations = 339 number of covariate patterns = 210 Pearson chi2(205) = 208.24 Prob > chi2 = 0.4238 Measures of Fit for logistic of HP2work Log-Lik Intercept Only: -172.642 Log-Lik Full Model: -140.886 D(334): 281.772 LR(4): 63.512 Prob > LR: 0.000 McFadden's R2: 0.184 McFadden's Adj R2: 0.155 Maximum Likelihood R2: 0.171 Cragg & Uhler's R2: 0.267 McKelvey and Zavoina's R2: 0.279 Efron's R2: 0.182 Variance of y*: 4.565 Variance of error: 3.290 Count R2: 0.811 Adj Count R2: 0.086 AIC: 0.861 AIC*n: 291.772 BIC: -1664.112 BIC': -40.208 141 . 142 . set more off 143 . forvalues j = 2/2 { 2. local w2bf bf1 bf4 bf6 bf7 bf14 bf15 bf40 3. di as input "For male moderator search with HP2work on Wave2" 4. des age occ1w`j'-occ8w`j' inc1w`j'-inc4w`j' avgcumdosew`j' /// > marrw`j'1-marrw`j'6 `w2bf' 5. sw, pr(.1): logistic HP2work marrw`j'3-marrw`j'6 age havmilsq /// > avgcumdosew1 bf4 bf40 illw`j' shjobw`j' suprtw`j' if gender== > 1, coef 6. estat gof 7. estat class 8. fitstat 9. } For male moderator search with HP2work on Wave2 storage display value variable name type format label variable label ------------------------------------------------------------------------------- age double %8.0g * Respondent's age occ1w2 double %15.0g LABJ profess executive administration in 1996 occ2w2 double %15.0g LABJ technical sales admin support in 1996 occ3w2 double %15.0g LABJ service occup protective services in 1996 occ4w2 double %15.0g LABJ precision prod mechan craft construction in 1996 occ5w2 double %15.0g LABJ factory laborer machinist transp cleaner in 1996 occ6w2 double %15.0g LABJ farming agricul forestry fishing trapping logging in 1996 occ7w2 double %15.0g LABJ homemaking caregiving in 1996 occ8w2 double %15.0g LABJ student in 1996 inc1w2 double %15.0g LABJ Income is not sufficient for basic neccessities in 1996 inc2w2 double %15.0g LABJ Income is just sufficient for basic neccessities in 1996 inc3w2 double %15.0g LABJ Income is sufficient for basics plus extra purchases/savings in 1996 inc4w2 double %15.0g LABJ Income allows to comfortably afford luxury items in 1996 avgcumdosew2 double %8.0g Average mean dose CS1337 in mGy for wave 2 marrw21 byte %8.0g marrw2==1. single marrw22 byte %8.0g marrw2==2. cohabitating marrw23 byte %8.0g marrw2==3. married marrw24 byte %8.0g marrw2==4. separated marrw25 byte %8.0g marrw2==5. divorced marrw26 byte %8.0g marrw2==6. widowed bf1 float %9.0g bf1 = max(0, kzchorn - 40) bf4 float %9.0g bf4 = max(0, 24 - BSIsoma) bf6 float %9.0g bf6= max(0, radtlw2 - 10) bf7 float %9.0g bf7= max(0, 10 - radtlw2) bf14 float %9.0g bf14= max(0, radw2 - 10) * bf12 bf15 float %9.0g bf15= max(0, 10 - radw2) * bf12 bf40 float %9.0g bf40 = max(0, icdxcnt - 1.01635E-007) note: marrw24 dropped because of estimability note: o.marrw24 dropped because of estimability note: 3 obs. dropped because of estimability begin with full model p = 0.9642 >= 0.1000 removing suprtw2 p = 0.9463 >= 0.1000 removing avgcumdosew1 p = 0.9274 >= 0.1000 removing illw2 p = 0.8655 >= 0.1000 removing havmilsq p = 0.7150 >= 0.1000 removing marrw26 p = 0.6480 >= 0.1000 removing marrw25 p = 0.6130 >= 0.1000 removing shjobw2 p = 0.3503 >= 0.1000 removing age Logistic regression Number of obs = 337 LR chi2(3) = 60.28 Prob > chi2 = 0.0000 Log likelihood = -142.03958 Pseudo R2 = 0.1750 ------------------------------------------------------------------------------ HP2work | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- marrw23 | -.6438264 .3522685 -1.83 0.068 -1.33426 .0466072 bf40 | .3619031 .0883528 4.10 0.000 .1887349 .5350714 bf4 | -.158784 .0297196 -5.34 0.000 -.2170333 -.1005347 _cons | -.0210934 .5108383 -0.04 0.967 -1.022318 .9801314 ------------------------------------------------------------------------------ Logistic model for HP2work, goodness-of-fit test number of observations = 337 number of covariate patterns = 122 Pearson chi2(118) = 128.59 Prob > chi2 = 0.2380 Logistic model for HP2work -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 20 16 | 36 - | 50 251 | 301 -----------+--------------------------+----------- Total | 70 267 | 337 Classified + if predicted Pr(D) >= .5 True D defined as HP2work != 0 -------------------------------------------------- Sensitivity Pr( +| D) 28.57% Specificity Pr( -|~D) 94.01% Positive predictive value Pr( D| +) 55.56% Negative predictive value Pr(~D| -) 83.39% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 5.99% False - rate for true D Pr( -| D) 71.43% False + rate for classified + Pr(~D| +) 44.44% False - rate for classified - Pr( D| -) 16.61% -------------------------------------------------- Correctly classified 80.42% -------------------------------------------------- Measures of Fit for logistic of HP2work Log-Lik Intercept Only: -172.178 Log-Lik Full Model: -142.040 D(333): 284.079 LR(3): 60.277 Prob > LR: 0.000 McFadden's R2: 0.175 McFadden's Adj R2: 0.152 Maximum Likelihood R2: 0.164 Cragg & Uhler's R2: 0.256 McKelvey and Zavoina's R2: 0.265 Efron's R2: 0.167 Variance of y*: 4.478 Variance of error: 3.290 Count R2: 0.804 Adj Count R2: 0.057 AIC: 0.867 AIC*n: 292.079 BIC: -1654.008 BIC': -42.816 144 . 145 . 146 . 147 . * capturing significant vars from last analysis 148 . local cn1: colnames(e(b)) 149 . di "`cn1'" marrw23 bf40 bf4 _cons 150 . local leng1 = length( "`cn1'") 151 . di `leng1' 22 152 . local leng1b `leng1'-6 153 . di `leng1b' 16 154 . local nuvlist = substr("`cn1'",1,`leng1b') 155 . di "`nuvlist'" marrw23 bf40 bf4 156 . local rhsvars = "`nuvlist'" 157 . local nuvlist= "`nuvlist'" 158 . local nuvlist= substr("`cn1'",1,`leng1b') 159 . di "`nuvlist'" marrw23 bf40 bf4 160 . sw, pr(.1):logit hp2hmcare `nuvlist' if gender==1 begin with full model p < 0.1000 for all terms in model Logistic regression Number of obs = 340 LR chi2(3) = 84.90 Prob > chi2 = 0.0000 Log likelihood = -130.42276 Pseudo R2 = 0.2456 ------------------------------------------------------------------------------ hp2hmcare | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- marrw23 | -.7016868 .3725356 -1.88 0.060 -1.431843 .0284696 bf40 | .2035085 .092586 2.20 0.028 .0220432 .3849737 bf4 | -.2435381 .0332335 -7.33 0.000 -.3086747 -.1784016 _cons | 1.305526 .5487119 2.38 0.017 .2300707 2.380982 ------------------------------------------------------------------------------ 161 . di "`rhsvars'" marrw23 bf40 bf4 162 . matrix define c=e(b) 163 . local cn2: colnames(c) 164 . di "`cn2'" marrw23 bf40 bf4 _cons 165 . local leng2 = length("`cn2'") 166 . local leng2b = `leng2'-6 167 . local rhsvars = substr("`cn2'",1,`leng2b') 168 . logit hp2work `rhsvars' if gender==1 Iteration 0: log likelihood = -172.87291 Iteration 1: log likelihood = -144.68077 Iteration 2: log likelihood = -142.54462 Iteration 3: log likelihood = -142.5291 Iteration 4: log likelihood = -142.52909 Logistic regression Number of obs = 340 LR chi2(3) = 60.69 Prob > chi2 = 0.0000 Log likelihood = -142.52909 Pseudo R2 = 0.1755 ------------------------------------------------------------------------------ hp2work | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- marrw23 | -.6166354 .3516015 -1.75 0.079 -1.305762 .072491 bf40 | .3614005 .0884291 4.09 0.000 .1880826 .5347184 bf4 | -.1595762 .0297217 -5.37 0.000 -.2178297 -.1013227 _cons | -.0395903 .511037 -0.08 0.938 -1.041204 .9620238 ------------------------------------------------------------------------------ 169 . 170 . 171 . 172 . di "`rhsvars'" marrw23 bf40 bf4 173 . local varlist2 =substr("`rhsvars'",1,9) 174 . di "`varlist2'" marrw23 b 175 . 176 . * constructing potential moderators 177 . foreach var in age illw2 { 2. cap gen `var'Xd2 = `var'* avgcumdosew2 3. } 178 . 179 . *x no signif male moderators for paid employment 180 . set more off 181 . sw, pr(.1): logistic hp2work `rhsvars' illw2Xd2 if gender==1, coef begin with full model p = 0.3768 >= 0.1000 removing illw2Xd2 Logistic regression Number of obs = 340 LR chi2(3) = 60.69 Prob > chi2 = 0.0000 Log likelihood = -142.52909 Pseudo R2 = 0.1755 ------------------------------------------------------------------------------ hp2work | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- marrw23 | -.6166354 .3516015 -1.75 0.079 -1.305762 .072491 bf40 | .3614005 .0884291 4.09 0.000 .1880826 .5347184 bf4 | -.1595762 .0297217 -5.37 0.000 -.2178297 -.1013227 _cons | -.0395903 .511037 -0.08 0.938 -1.041204 .9620238 ------------------------------------------------------------------------------ 182 . fitstat Measures of Fit for logistic of hp2work Log-Lik Intercept Only: -172.873 Log-Lik Full Model: -142.529 D(336): 285.058 LR(3): 60.688 Prob > LR: 0.000 McFadden's R2: 0.176 McFadden's Adj R2: 0.152 Maximum Likelihood R2: 0.163 Cragg & Uhler's R2: 0.256 McKelvey and Zavoina's R2: 0.265 Efron's R2: 0.168 Variance of y*: 4.477 Variance of error: 3.290 Count R2: 0.806 Adj Count R2: 0.057 AIC: 0.862 AIC*n: 293.058 BIC: -1673.468 BIC': -43.201 183 . 184 . scalar wkModMw2 = "none" 185 . di _skip(2) 186 . title4 "testing the female moderator models Hp2work H1 Pt 2 wave 2" ------------------------------------------------------------------------------- testing the female moderator models Hp2work H1 Pt 2 wave 2 ------------------------------------------------------------------------------- 187 . * Testing female moderator model xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx > xxx 188 . 189 . title4 "testing general female moderator model for hp2work" ------------------------------------------------------------------------------- testing general female moderator model for hp2work ------------------------------------------------------------------------------- 190 . local w2bf bf1 bf4 bf6 bf7 bf14 bf15 bf40 191 . di _skip(4) 192 . 193 . di _skip(4) 194 . 195 . forvalues j = 2/2 { 2. di _skip(4) 3. di as input "For females hp2work on wave 1 with dose ns" 4. des age occ1w`j'-occ8w`j' inc1w`j'-inc4w`j' avgcumdosew`j' `w2bf' 5. sw, pr(.1): logistic HP2work age havmilsq /// > avgcumdosew2 illw`j' shjobw`j' suprtw`j' radhlw`j' if gender==2, coef 6. estat gof 7. estat class 8. fitstat 9. } For females hp2work on wave 1 with dose ns storage display value variable name type format label variable label ------------------------------------------------------------------------------- age double %8.0g * Respondent's age occ1w2 double %15.0g LABJ profess executive administration in 1996 occ2w2 double %15.0g LABJ technical sales admin support in 1996 occ3w2 double %15.0g LABJ service occup protective services in 1996 occ4w2 double %15.0g LABJ precision prod mechan craft construction in 1996 occ5w2 double %15.0g LABJ factory laborer machinist transp cleaner in 1996 occ6w2 double %15.0g LABJ farming agricul forestry fishing trapping logging in 1996 occ7w2 double %15.0g LABJ homemaking caregiving in 1996 occ8w2 double %15.0g LABJ student in 1996 inc1w2 double %15.0g LABJ Income is not sufficient for basic neccessities in 1996 inc2w2 double %15.0g LABJ Income is just sufficient for basic neccessities in 1996 inc3w2 double %15.0g LABJ Income is sufficient for basics plus extra purchases/savings in 1996 inc4w2 double %15.0g LABJ Income allows to comfortably afford luxury items in 1996 avgcumdosew2 double %8.0g Average mean dose CS1337 in mGy for wave 2 bf1 float %9.0g bf1 = max(0, kzchorn - 40) bf4 float %9.0g bf4 = max(0, 24 - BSIsoma) bf6 float %9.0g bf6= max(0, radtlw2 - 10) bf7 float %9.0g bf7= max(0, 10 - radtlw2) bf14 float %9.0g bf14= max(0, radw2 - 10) * bf12 bf15 float %9.0g bf15= max(0, 10 - radw2) * bf12 bf40 float %9.0g bf40 = max(0, icdxcnt - 1.01635E-007) begin with full model p = 0.9490 >= 0.1000 removing shjobw2 p = 0.5496 >= 0.1000 removing havmilsq p = 0.4955 >= 0.1000 removing suprtw2 p = 0.2666 >= 0.1000 removing avgcumdosew2 p = 0.1232 >= 0.1000 removing illw2 Logistic regression Number of obs = 363 LR chi2(2) = 49.29 Prob > chi2 = 0.0000 Log likelihood = -181.91527 Pseudo R2 = 0.1193 ------------------------------------------------------------------------------ HP2work | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0632993 .0119444 5.30 0.000 .0398887 .08671 radhlw2 | .010972 .0040298 2.72 0.006 .0030737 .0188703 _cons | -5.088259 .6777663 -7.51 0.000 -6.416656 -3.759861 ------------------------------------------------------------------------------ Logistic model for HP2work, goodness-of-fit test number of observations = 363 number of covariate patterns = 219 Pearson chi2(216) = 254.55 Prob > chi2 = 0.0370 Logistic model for HP2work -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 20 7 | 27 - | 73 263 | 336 -----------+--------------------------+----------- Total | 93 270 | 363 Classified + if predicted Pr(D) >= .5 True D defined as HP2work != 0 -------------------------------------------------- Sensitivity Pr( +| D) 21.51% Specificity Pr( -|~D) 97.41% Positive predictive value Pr( D| +) 74.07% Negative predictive value Pr(~D| -) 78.27% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 2.59% False - rate for true D Pr( -| D) 78.49% False + rate for classified + Pr(~D| +) 25.93% False - rate for classified - Pr( D| -) 21.73% -------------------------------------------------- Correctly classified 77.96% -------------------------------------------------- Measures of Fit for logistic of HP2work Log-Lik Intercept Only: -206.563 Log-Lik Full Model: -181.915 D(360): 363.831 LR(2): 49.295 Prob > LR: 0.000 McFadden's R2: 0.119 McFadden's Adj R2: 0.105 Maximum Likelihood R2: 0.127 Cragg & Uhler's R2: 0.187 McKelvey and Zavoina's R2: 0.205 Efron's R2: 0.150 Variance of y*: 4.139 Variance of error: 3.290 Count R2: 0.780 Adj Count R2: 0.140 AIC: 1.019 AIC*n: 369.831 BIC: -1758.154 BIC': -37.506 196 . 197 . replace ageXd2 = age*avgcumdosew2 (0 real changes made) 198 . 199 . * capturing significant vars 200 . local cn3: colnames(e(b)) 201 . di "`cn3'" age radhlw2 _cons 202 . local leng1 = length( "`cn3'") 203 . di `leng3' 204 . local leng1b `leng1'-6 205 . di `leng3b' 206 . local nuvlist3 = substr("`cn1'",1,`leng1b') 207 . di "`nuvlist3'" marrw23 bf4 208 . local rhsvars3 = "`nuvlist3'" 209 . local nuvlist3= "`nuvlist3'" 210 . local nuvlist3= substr("`cn1'",1,`leng1b') 211 . di "`nuvlist3'" marrw23 bf4 212 . 213 . * moderators for hp2work female and male are saved as scalars: 214 . scalar wkModFw2="none" 215 . scalar wkModMw2="none" 216 . cap gen ageXd2 = age*avgcumdosew2 217 . 218 . *x no significant female moderator for paid employment 219 . forvalues j = 2/2 { 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' 4. sw, pr(.1): logistic HP2work bf4 bf14 age havmil /// > avgcumdosew2 ageXd2 illw`j' accdw`j' suprtw`j' if gender==2, coef 5. estat gof 6. estat class 7. fitstat 8. } 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 occ1w2 double %15.0g LABJ profess executive administration in 1996 occ2w2 double %15.0g LABJ technical sales admin support in 1996 occ3w2 double %15.0g LABJ service occup protective services in 1996 occ4w2 double %15.0g LABJ precision prod mechan craft construction in 1996 occ5w2 double %15.0g LABJ factory laborer machinist transp cleaner in 1996 occ6w2 double %15.0g LABJ farming agricul forestry fishing trapping logging in 1996 occ7w2 double %15.0g LABJ homemaking caregiving in 1996 occ8w2 double %15.0g LABJ student in 1996 inc1w2 double %15.0g LABJ Income is not sufficient for basic neccessities in 1996 inc2w2 double %15.0g LABJ Income is just sufficient for basic neccessities in 1996 inc3w2 double %15.0g LABJ Income is sufficient for basics plus extra purchases/savings in 1996 inc4w2 double %15.0g LABJ Income allows to comfortably afford luxury items in 1996 avgcumdosew2 double %8.0g Average mean dose CS1337 in mGy for wave 2 begin with full model p = 0.9295 >= 0.1000 removing suprtw2 p = 0.8298 >= 0.1000 removing ageXd2 p = 0.3867 >= 0.1000 removing havmil p = 0.4373 >= 0.1000 removing accdw2 p = 0.3450 >= 0.1000 removing illw2 p = 0.1908 >= 0.1000 removing bf14 p = 0.2277 >= 0.1000 removing avgcumdosew2 Logistic regression Number of obs = 363 LR chi2(2) = 60.00 Prob > chi2 = 0.0000 Log likelihood = -176.56392 Pseudo R2 = 0.1452 ------------------------------------------------------------------------------ HP2work | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- bf4 | -.111911 .026544 -4.22 0.000 -.1639364 -.0598857 age | .0513174 .012385 4.14 0.000 .0270434 .0755915 _cons | -2.690984 .784746 -3.43 0.001 -4.229058 -1.152911 ------------------------------------------------------------------------------ Logistic model for HP2work, goodness-of-fit test number of observations = 363 number of covariate patterns = 275 Pearson chi2(272) = 304.33 Prob > chi2 = 0.0864 Logistic model for HP2work -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 31 18 | 49 - | 62 252 | 314 -----------+--------------------------+----------- Total | 93 270 | 363 Classified + if predicted Pr(D) >= .5 True D defined as HP2work != 0 -------------------------------------------------- Sensitivity Pr( +| D) 33.33% Specificity Pr( -|~D) 93.33% Positive predictive value Pr( D| +) 63.27% Negative predictive value Pr(~D| -) 80.25% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 6.67% False - rate for true D Pr( -| D) 66.67% False + rate for classified + Pr(~D| +) 36.73% False - rate for classified - Pr( D| -) 19.75% -------------------------------------------------- Correctly classified 77.96% -------------------------------------------------- Measures of Fit for logistic of HP2work Log-Lik Intercept Only: -206.563 Log-Lik Full Model: -176.564 D(360): 353.128 LR(2): 59.997 Prob > LR: 0.000 McFadden's R2: 0.145 McFadden's Adj R2: 0.131 Maximum Likelihood R2: 0.152 Cragg & Uhler's R2: 0.224 McKelvey and Zavoina's R2: 0.236 Efron's R2: 0.175 Variance of y*: 4.304 Variance of error: 3.290 Count R2: 0.780 Adj Count R2: 0.140 AIC: 0.989 AIC*n: 359.128 BIC: -1768.857 BIC': -48.208 220 . 221 . scalar SigDoseFw2 = "no" 222 . scalar MainEffwkFw2 = "bf4 age" 223 . ****** Moderator analysis for Dose=>paid employment wave two 224 . * testing potential moderators for women in wave 2 225 . set more off 226 . forvalues j = 2/2 { 2. sw, pr(.1):logistic HP2work age bf8 illw`j' shjobw`j' havm > ilsq /// > avgcumdosew`j' ageXd2 if gender==2, coef 3. estat class 4. estat gof 5. fitstat 6. } begin with full model p = 0.9982 >= 0.1000 removing shjobw2 p = 0.9722 >= 0.1000 removing bf8 p = 0.9439 >= 0.1000 removing ageXd2 p = 0.5143 >= 0.1000 removing havmilsq p = 0.1897 >= 0.1000 removing avgcumdosew2 Logistic regression Number of obs = 363 LR chi2(2) = 45.10 Prob > chi2 = 0.0000 Log likelihood = -184.01432 Pseudo R2 = 0.1092 ------------------------------------------------------------------------------ HP2work | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0669548 .0117179 5.71 0.000 .0439882 .0899214 illw2 | .251976 .1395285 1.81 0.071 -.0214949 .5254469 _cons | -4.695017 .6467006 -7.26 0.000 -5.962527 -3.427507 ------------------------------------------------------------------------------ Logistic model for HP2work -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 22 8 | 30 - | 71 262 | 333 -----------+--------------------------+----------- Total | 93 270 | 363 Classified + if predicted Pr(D) >= .5 True D defined as HP2work != 0 -------------------------------------------------- Sensitivity Pr( +| D) 23.66% Specificity Pr( -|~D) 97.04% Positive predictive value Pr( D| +) 73.33% Negative predictive value Pr(~D| -) 78.68% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 2.96% False - rate for true D Pr( -| D) 76.34% False + rate for classified + Pr(~D| +) 26.67% False - rate for classified - Pr( D| -) 21.32% -------------------------------------------------- Correctly classified 78.24% -------------------------------------------------- Logistic model for HP2work, goodness-of-fit test number of observations = 363 number of covariate patterns = 109 Pearson chi2(106) = 105.02 Prob > chi2 = 0.5087 Measures of Fit for logistic of HP2work Log-Lik Intercept Only: -206.563 Log-Lik Full Model: -184.014 D(360): 368.029 LR(2): 45.096 Prob > LR: 0.000 McFadden's R2: 0.109 McFadden's Adj R2: 0.095 Maximum Likelihood R2: 0.117 Cragg & Uhler's R2: 0.172 McKelvey and Zavoina's R2: 0.184 Efron's R2: 0.141 Variance of y*: 4.033 Variance of error: 3.290 Count R2: 0.782 Adj Count R2: 0.151 AIC: 1.030 AIC*n: 374.029 BIC: -1753.956 BIC': -33.308 227 . 228 . * capturing significant vars 229 . local cn2: colnames(e(b)) 230 . di "`cn2'" age illw2 _cons 231 . local leng2 = length( "`cn2'") 232 . di `leng2' 15 233 . local leng2b `leng1'-6 234 . di `leng2b' 11 235 . local nuvlist2 = substr("`cn2'",1,`leng2b') 236 . di "`nuvlist2'" age illw2 _ 237 . local rhsvars2 = "`nuvlist2'" 238 . local nuvlist2= "`nuvlist2'" 239 . local nuvlist2= substr("`cn1'",1,`leng2b') 240 . di "`nuvlist2'" marrw23 bf4 241 . 242 . foreach varx in `nuvlist2' { 2. gen `varx'X`vary' = `varx'*avgcumdosew2 3. } 243 . 244 . 245 . sw, pr(.1): regress hp2hmcare age illw2 ageXd2 illw2Xd2 begin with full model p = 0.5620 >= 0.1000 removing illw2Xd2 p = 0.2023 >= 0.1000 removing illw2 p = 0.2166 >= 0.1000 removing ageXd2 Source | SS df MS Number of obs = 703 -------------+------------------------------ F( 1, 701) = 108.10 Model | 18.8264108 1 18.8264108 Prob > F = 0.0000 Residual | 122.083973 701 .174156881 R-squared = 0.1336 -------------+------------------------------ Adj R-squared = 0.1324 Total | 140.910384 702 .200727043 Root MSE = .41732 ------------------------------------------------------------------------------ hp2hmcare | Coef. Std. Err. t P>|t| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0135982 .0013079 10.40 0.000 .0110304 .0161661 _cons | -.3986595 .0668999 -5.96 0.000 -.5300077 -.2673114 ------------------------------------------------------------------------------ 246 . 247 . 248 . scalar SigDoseWkFw2 = "no" 249 . scalar SigDoseWkMw2 = "no" 250 . 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) 251 . scalar MainEffwkMw2 = "bf4 bf40" 252 . scalar MainEffwkFw2 = "age " 253 . scalar WKModMw2 = "none" 254 . scalar WkModFw2 = "none" 255 . 256 . 257 . * male sign main effects in main effects model: 2- bf4, bf40 258 . * male and female main effects model avgcumdosew2 were not signif. 259 . * male hp2wk w2 mediators: bf4 and bf40 260 . * female signif main effects in main effects model 261 . 262 . title4 "H1 pt 2 wave 2 Mediation testing for male and females " ------------------------------------------------------------------------------- H1 pt 2 wave 2 Mediation testing for male and females ------------------------------------------------------------------------------- 263 . 264 . * male hp2wk w2 mediators: testing b4 and b40 265 . 266 . cap gen ageXillw2 = age*illw2 267 . correlate bf4 age if gender==1 (obs=340) | bf4 age -------------+------------------ bf4 | 1.0000 age | -0.4041 1.0000 268 . 269 . local k 1 270 . title "Possible male mediators in wave 2" "bf4 can be a male mediator in wave > 2" ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Possible male mediators in wave 2 ***** ***** bf4 can be a male mediator in wave 2 ***** ***** ***** ***** ***** ***** 16 Jun 2012 21:52:47 ***** ******************************************************************************* ******************************************************************************* 271 . glm bf4 age avgcumdosew2 if gender==`k', fam(gauss) link(identity) Iteration 0: log likelihood = -996.64953 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 337 Scale parameter = 20.7725 Deviance = 7000.331927 (1/df) Deviance = 20.7725 Pearson = 7000.331927 (1/df) Pearson = 20.7725 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 5.880291 Log likelihood = -996.6495299 BIC = 5035.977 ------------------------------------------------------------------------------ | OIM bf4 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | -.1659274 .0203994 -8.13 0.000 -.2059095 -.1259453 avgcumdosew2 | .0636104 .0995687 0.64 0.523 -.1315406 .2587614 _cons | 20.59657 1.026594 20.06 0.000 18.58448 22.60866 ------------------------------------------------------------------------------ 272 . glm hp2hmcare bf4 age if gender==`k', fam(binomial) link(probit) irls scale(d > ev) Iteration 1: deviance = 265.85 Iteration 2: deviance = 261.7102 Iteration 3: deviance = 261.5892 Iteration 4: deviance = 261.5887 Iteration 5: deviance = 261.5887 Iteration 6: deviance = 261.5887 Generalized linear models No. of obs = 340 Optimization : MQL Fisher scoring Residual df = 337 (IRLS EIM) Scale parameter = 1 Deviance = 261.5886708 (1/df) Deviance = .7762275 Pearson = 284.8259081 (1/df) Pearson = .8451807 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1702.766 ------------------------------------------------------------------------------ | EIM hp2hmcare | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- bf4 | -.1318123 .0159309 -8.27 0.000 -.1630363 -.1005883 age | .0141501 .0068474 2.07 0.039 .0007294 .0275707 _cons | -.0621746 .4509187 -0.14 0.890 -.945959 .8216099 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 273 . title4 "bf4 can be a mediator for men" ------------------------------------------------------------------------------- bf4 can be a mediator for men ------------------------------------------------------------------------------- 274 . 275 . local k 1 276 . title "Age can be a male mediator in wave 2" ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Age can be a male mediator in wave 2 ***** ***** ***** ***** ***** ***** 16 Jun 2012 21:52:50 ***** ******************************************************************************* ******************************************************************************* 277 . glm age avgcumdosew2 if gender==`k', fam(gauss) link(identity) Iteration 0: log likelihood = -1330.6004 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = 147.6853 Deviance = 49917.64009 (1/df) Deviance = 147.6853 Pearson = 49917.64009 (1/df) Pearson = 147.6853 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 7.838826 Log likelihood = -1330.6004 BIC = 47947.46 ------------------------------------------------------------------------------ | OIM age | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew2 | .5832314 .2635871 2.21 0.027 .0666101 1.099853 _cons | 48.62133 .7061562 68.85 0.000 47.23729 50.00537 ------------------------------------------------------------------------------ 278 . glm hp2hmcare age if gender==`k', fam(binomial) link(probit) irls scale(dev) 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.) 279 . title4 "age could be a mediator for men in wave 2" ------------------------------------------------------------------------------- age could be a mediator for men in wave 2 ------------------------------------------------------------------------------- 280 . 281 . local k 1 282 . title "Age can be a male mediator in wave 2" ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Age can be a male mediator in wave 2 ***** ***** ***** ***** ***** ***** 16 Jun 2012 21:52:53 ***** ******************************************************************************* ******************************************************************************* 283 . glm age bf4 avgcumdosew2 if gender==`k', fam(gauss) link(identity) Iteration 0: log likelihood = -1300.1274 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 337 Scale parameter = 123.8157 Deviance = 41725.88285 (1/df) Deviance = 123.8157 Pearson = 41725.88285 (1/df) Pearson = 123.8157 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 7.665455 Log likelihood = -1300.127421 BIC = 39761.53 ------------------------------------------------------------------------------ | OIM age | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- bf4 | -.9890198 .1215918 -8.13 0.000 -1.227335 -.7507042 avgcumdosew2 | .5504319 .2413815 2.28 0.023 .0773329 1.023531 _cons | 61.01272 1.654952 36.87 0.000 57.76907 64.25636 ------------------------------------------------------------------------------ 284 . glm hp2hmcare bf4 age if gender==`k', fam(binomial) link(probit) irls scale(d > ev) Iteration 1: deviance = 265.85 Iteration 2: deviance = 261.7102 Iteration 3: deviance = 261.5892 Iteration 4: deviance = 261.5887 Iteration 5: deviance = 261.5887 Iteration 6: deviance = 261.5887 Generalized linear models No. of obs = 340 Optimization : MQL Fisher scoring Residual df = 337 (IRLS EIM) Scale parameter = 1 Deviance = 261.5886708 (1/df) Deviance = .7762275 Pearson = 284.8259081 (1/df) Pearson = .8451807 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1702.766 ------------------------------------------------------------------------------ | EIM hp2hmcare | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- bf4 | -.1318123 .0159309 -8.27 0.000 -.1630363 -.1005883 age | .0141501 .0068474 2.07 0.039 .0007294 .0275707 _cons | -.0621746 .4509187 -0.14 0.890 -.945959 .8216099 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 285 . title4 "age is not likely to be a male mediator with bf4 in wave 2" ------------------------------------------------------------------------------- age is not likely to be a male mediator with bf4 in wave 2 ------------------------------------------------------------------------------- 286 . 287 . 288 . local g 1 289 . des bf4 storage display value variable name type format label variable label ------------------------------------------------------------------------------- bf4 float %9.0g bf4 = max(0, 24 - BSIsoma) 290 . title "bf4 is not likely to be a male mediator in wave 2" ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** bf4 is not likely to be a male mediator in wave 2 ***** ***** ***** ***** ***** ***** 16 Jun 2012 21:52:56 ***** ******************************************************************************* ******************************************************************************* 291 . mvreg age bf4 bf40 illw2 ageXillw2 = avgcumdosew2 if gender==`g' Equation Obs Parms RMSE "R-sq" F P ---------------------------------------------------------------------- age 340 2 12.15259 0.0143 4.89591 0.0276 bf4 340 2 4.97766 0.0003 .0943548 0.7589 bf40 340 2 1.686178 0.0051 1.736932 0.1884 illw2 340 2 .5927047 0.0013 .4415312 0.5068 ageXillw2 340 2 32.91663 0.0022 .7442227 0.3889 ------------------------------------------------------------------------------ | Coef. Std. Err. t P>|t| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | avgcumdosew2 | .5832314 .2635871 2.21 0.028 .0647536 1.101709 _cons | 48.62133 .7061562 68.85 0.000 47.23231 50.01034 -------------+---------------------------------------------------------------- bf4 | avgcumdosew2 | -.0331637 .1079644 -0.31 0.759 -.2455305 .1792032 _cons | 12.52896 .2892393 43.32 0.000 11.96002 13.0979 -------------+---------------------------------------------------------------- bf40 | avgcumdosew2 | .0482004 .0365729 1.32 0.188 -.0237387 .1201394 _cons | 2.097753 .0979795 21.41 0.000 1.905026 2.290479 -------------+---------------------------------------------------------------- illw2 | avgcumdosew2 | .0085423 .0128556 0.66 0.507 -.0167449 .0338294 _cons | .2741359 .0344406 7.96 0.000 .206391 .3418808 -------------+---------------------------------------------------------------- ageXillw2 | avgcumdosew2 | .6159172 .7139551 0.86 0.389 -.7884376 2.020272 _cons | 14.92518 1.912703 7.80 0.000 11.16288 18.68748 ------------------------------------------------------------------------------ 292 . glm hp2hmcare bf40 ageXillw2 age illw2 if gender==`g', fam(binomial) link(pro > bit) irls scale(dev) Iteration 1: deviance = 311.1636 Iteration 2: deviance = 310.2586 Iteration 3: deviance = 310.2568 Iteration 4: deviance = 310.2568 Generalized linear models No. of obs = 340 Optimization : MQL Fisher scoring Residual df = 335 (IRLS EIM) Scale parameter = 1 Deviance = 310.2568213 (1/df) Deviance = .9261398 Pearson = 340.3888599 (1/df) Pearson = 1.016086 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1642.44 ------------------------------------------------------------------------------ | EIM hp2hmcare | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- bf40 | .1066983 .0502474 2.12 0.034 .0082152 .2051813 ageXillw2 | .0205084 .0129801 1.58 0.114 -.0049321 .0459489 age | .0211195 .0074403 2.84 0.005 .0065368 .0357022 illw2 | -1.017511 .7203558 -1.41 0.158 -2.429383 .3943602 _cons | -2.194473 .3787582 -5.79 0.000 -2.936825 -1.45212 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 293 . title4 "only age is a mediator for men whe b4 b40 and age are together" ------------------------------------------------------------------------------- only age is a mediator for men whe b4 b40 and age are together ------------------------------------------------------------------------------- 294 . 295 . 296 . * interaction of ageXillw2 impacts paid employment as mediator and moderator 297 . glm ageXillw2 illw2 age avgcumdosew2 if gender==2, fam(gaussian) link(identit > y) Iteration 0: log likelihood = -1294.7181 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 359 Scale parameter = 74.19052 Deviance = 26634.39748 (1/df) Deviance = 74.19052 Pearson = 26634.39748 (1/df) Pearson = 74.19052 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 7.155472 Log likelihood = -1294.718095 BIC = 24518.31 ------------------------------------------------------------------------------ | OIM ageXillw2 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- illw2 | 54.68229 .5267404 103.81 0.000 53.6499 55.71468 age | .3241144 .0391633 8.28 0.000 .2473557 .4008731 avgcumdosew2 | -.3918044 .3378743 -1.16 0.246 -1.054026 .270417 _cons | -15.93368 1.972299 -8.08 0.000 -19.79932 -12.06805 ------------------------------------------------------------------------------ 298 . glm hp2hmcare ageXillw2 age illw2 avgcumdosew2 if gender==2, fam(binomial) ir > ls scale(dev) link(probit) Iteration 1: deviance = 386.6115 Iteration 2: deviance = 385.6203 Iteration 3: deviance = 385.5944 Iteration 4: deviance = 385.5944 Iteration 5: deviance = 385.5944 Generalized linear models No. of obs = 363 Optimization : MQL Fisher scoring Residual df = 358 (IRLS EIM) Scale parameter = 1 Deviance = 385.5943633 (1/df) Deviance = 1.077079 Pearson = 371.857587 (1/df) Pearson = 1.038708 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1724.602 ------------------------------------------------------------------------------ | EIM hp2hmcare | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- ageXillw2 | .0260371 .0127399 2.04 0.041 .0010674 .0510068 age | .0485475 .0076115 6.38 0.000 .0336292 .0634658 illw2 | -1.454103 .7330667 -1.98 0.047 -2.890887 -.0173185 avgcumdosew2 | -.0898482 .0614809 -1.46 0.144 -.2103484 .0306521 _cons | -2.815361 .3933028 -7.16 0.000 -3.586221 -2.044502 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 299 . 300 . scalar WkMedMw2 = "age ageXillw2 " 301 . * moderate negative correlation between bf4 and age generates /// > * annihilation of effect among men in wave 2" 302 . 303 . 304 . 305 . 306 . local g 2 307 . title "Test of female mediation in wave 2" ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Test of female mediation in wave 2 ***** ***** ***** ***** ***** ***** 16 Jun 2012 21:53:01 ***** ******************************************************************************* ******************************************************************************* 308 . glm age avgcumdosew2 if gender==`g', fam(gauss) link(identity) Iteration 0: log likelihood = -1406.9403 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = 136.9184 Deviance = 49427.52828 (1/df) Deviance = 136.9184 Pearson = 49427.52828 (1/df) Pearson = 136.9184 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 7.762756 Log likelihood = -1406.940271 BIC = 47299.65 ------------------------------------------------------------------------------ | OIM age | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew2 | 1.502324 .4454009 3.37 0.001 .6293547 2.375294 _cons | 48.86944 .7323225 66.73 0.000 47.43412 50.30477 ------------------------------------------------------------------------------ 309 . glm hp2hmcare age if gender==`g', fam(binomial) link(probit) irls scale(dev) 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.) 310 . title4 "age is a mediator for women" ------------------------------------------------------------------------------- age is a mediator for women ------------------------------------------------------------------------------- 311 . 312 . local k 1 313 . title "Test of male mediation in wave 2" ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Test of male mediation in wave 2 ***** ***** ***** ***** ***** ***** 16 Jun 2012 21:53:04 ***** ******************************************************************************* ******************************************************************************* 314 . glm bf40 age avgcumdosew2 if gender==`k', fam(gauss) link(identity) Iteration 0: log likelihood = -636.12361 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 337 Scale parameter = 2.491511 Deviance = 839.6390875 (1/df) Deviance = 2.491511 Pearson = 839.6390875 (1/df) Pearson = 2.491511 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 3.759551 Log likelihood = -636.1236104 BIC = -1124.716 ------------------------------------------------------------------------------ | OIM bf40 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0493074 .0070649 6.98 0.000 .0354605 .0631543 avgcumdosew2 | .0194427 .0344834 0.56 0.573 -.0481434 .0870289 _cons | -.2996387 .3555379 -0.84 0.399 -.9964801 .3972028 ------------------------------------------------------------------------------ 315 . glm hp2hmcare bf40 age if gender==`k', fam(binomial) link(probit) irls scale > (dev) Iteration 1: deviance = 314.3473 Iteration 2: deviance = 313.2347 Iteration 3: deviance = 313.2327 Iteration 4: deviance = 313.2327 Generalized linear models No. of obs = 340 Optimization : MQL Fisher scoring Residual df = 337 (IRLS EIM) Scale parameter = 1 Deviance = 313.2326581 (1/df) Deviance = .9294738 Pearson = 344.2579037 (1/df) Pearson = 1.021537 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1651.122 ------------------------------------------------------------------------------ | EIM hp2hmcare | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- bf40 | .1280268 .0466576 2.74 0.006 .0365795 .2194741 age | .0267014 .0067374 3.96 0.000 .0134964 .0399064 _cons | -2.486219 .3459069 -7.19 0.000 -3.164184 -1.808254 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 316 . title4 "b40 with age is a mediator for women" ------------------------------------------------------------------------------- b40 with age is a mediator for women ------------------------------------------------------------------------------- 317 . 318 . local g 2 319 . title "Test of female mediation in wave 2" ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Test of female mediation in wave 2 ***** ***** ***** ***** ***** ***** 16 Jun 2012 21:53:07 ***** ******************************************************************************* ******************************************************************************* 320 . glm bf40 avgcumdosew2 if gender==`g', fam(gauss) link(identity) Iteration 0: log likelihood = -818.51169 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = 5.351378 Deviance = 1931.847477 (1/df) Deviance = 5.351378 Pearson = 1931.847477 (1/df) Pearson = 5.351378 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 4.520726 Log likelihood = -818.5116931 BIC = -196.0319 ------------------------------------------------------------------------------ | OIM bf40 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew2 | .1794903 .0880548 2.04 0.042 .0069061 .3520745 _cons | 3.004543 .1447786 20.75 0.000 2.720783 3.288304 ------------------------------------------------------------------------------ 321 . glm hp2hmcare bf40 if gender==`g', fam(binomial) link(probit) irls scale(dev) Iteration 1: deviance = 462.764 Iteration 2: deviance = 462.2054 Iteration 3: deviance = 462.2053 Iteration 4: deviance = 462.2053 Generalized linear models No. of obs = 363 Optimization : MQL Fisher scoring Residual df = 361 (IRLS EIM) Scale parameter = 1 Deviance = 462.2053395 (1/df) Deviance = 1.280347 Pearson = 362.3613268 (1/df) Pearson = 1.003771 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1665.674 ------------------------------------------------------------------------------ | EIM hp2hmcare | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- bf40 | .0666058 .0327979 2.03 0.042 .0023231 .1308886 _cons | -.6159451 .1313241 -4.69 0.000 -.8733356 -.3585546 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 322 . title4 "bf40 alone is a mediator for women" ------------------------------------------------------------------------------- bf40 alone is a mediator for women ------------------------------------------------------------------------------- 323 . 324 . local g 2 325 . title "Test of female mediation in wave 2" ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Test of female mediation in wave 2 ***** ***** ***** ***** ***** ***** 16 Jun 2012 21:53:10 ***** ******************************************************************************* ******************************************************************************* 326 . glm bf4 avgcumdosew2 if gender==`g', fam(gauss) link(identity) Iteration 0: log likelihood = -1109.0983 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = 26.53281 Deviance = 9578.344971 (1/df) Deviance = 26.53281 Pearson = 9578.344971 (1/df) Pearson = 26.53281 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 6.121754 Log likelihood = -1109.098281 BIC = 7450.466 ------------------------------------------------------------------------------ | OIM bf4 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew2 | -.595012 .1960703 -3.03 0.002 -.9793027 -.2107212 _cons | 11.02048 .3223763 34.19 0.000 10.38863 11.65232 ------------------------------------------------------------------------------ 327 . glm hp2hmcare bf4 if gender==`g', fam(binomial) link(probit) irls scale(dev) Iteration 1: deviance = 410.1424 Iteration 2: deviance = 410.1166 Iteration 3: deviance = 410.1166 Iteration 4: deviance = 410.1166 Generalized linear models No. of obs = 363 Optimization : MQL Fisher scoring Residual df = 361 (IRLS EIM) Scale parameter = 1 Deviance = 410.1166157 (1/df) Deviance = 1.136057 Pearson = 357.1140873 (1/df) Pearson = .9892357 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1717.763 ------------------------------------------------------------------------------ | EIM hp2hmcare | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- bf4 | -.1024685 .0149808 -6.84 0.000 -.1318304 -.0731067 _cons | .6214741 .1665648 3.73 0.000 .295013 .9479351 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 328 . title4 "bf4 alone is a mediator for women" ------------------------------------------------------------------------------- bf4 alone is a mediator for women ------------------------------------------------------------------------------- 329 . 330 . 331 . local g 2 332 . title "Test of female mediation in wave 2" ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Test of female mediation in wave 2 ***** ***** ***** ***** ***** ***** 16 Jun 2012 21:53:12 ***** ******************************************************************************* ******************************************************************************* 333 . glm illw2 avgcumdosew2 if gender==`g', fam(gauss) link(identity) Iteration 0: log likelihood = -463.51524 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = .756881 Deviance = 273.2340487 (1/df) Deviance = .756881 Pearson = 273.2340487 (1/df) Pearson = .756881 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 2.564822 Log likelihood = -463.5152411 BIC = -1854.645 ------------------------------------------------------------------------------ | OIM illw2 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew2 | .1249912 .0331157 3.77 0.000 .0600856 .1898968 _cons | .301285 .0544484 5.53 0.000 .194568 .4080019 ------------------------------------------------------------------------------ 334 . glm hp2hmcare illw2 if gender==`g', fam(binomial) link(probit) irls scale(dev > ) Iteration 1: deviance = 466.1156 Iteration 2: deviance = 465.4957 Iteration 3: deviance = 465.4956 Iteration 4: deviance = 465.4956 Generalized linear models No. of obs = 363 Optimization : MQL Fisher scoring Residual df = 361 (IRLS EIM) Scale parameter = 1 Deviance = 465.4955997 (1/df) Deviance = 1.289461 Pearson = 362.823507 (1/df) Pearson = 1.005051 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1662.384 ------------------------------------------------------------------------------ | EIM hp2hmcare | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- illw2 | .1070451 .0863777 1.24 0.215 -.0622522 .2763423 _cons | -.4461214 .0854256 -5.22 0.000 -.6135525 -.2786904 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 335 . title4 "illw2 alone is a mediator for women" ------------------------------------------------------------------------------- illw2 alone is a mediator for women ------------------------------------------------------------------------------- 336 . 337 . 338 . 339 . local g 2 340 . title "Test of female mediation in wave 2" ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Test of female mediation in wave 2 ***** ***** ***** ***** ***** ***** 16 Jun 2012 21:53:15 ***** ******************************************************************************* ******************************************************************************* 341 . mvreg bf4 age bf40 = avgcumdosew2 if gender==`g' Equation Obs Parms RMSE "R-sq" F P ---------------------------------------------------------------------- bf4 363 2 5.151001 0.0249 9.209323 0.0026 age 363 2 11.70121 0.0306 11.37694 0.0008 bf40 363 2 2.313305 0.0114 4.155047 0.0422 ------------------------------------------------------------------------------ | Coef. Std. Err. t P>|t| [95% Conf. Interval] -------------+---------------------------------------------------------------- bf4 | avgcumdosew2 | -.595012 .1960703 -3.03 0.003 -.9805954 -.2094285 _cons | 11.02048 .3223763 34.19 0.000 10.38651 11.65445 -------------+---------------------------------------------------------------- age | avgcumdosew2 | 1.502324 .4454009 3.37 0.001 .6264181 2.378231 _cons | 48.86944 .7323225 66.73 0.000 47.42929 50.3096 -------------+---------------------------------------------------------------- bf40 | avgcumdosew2 | .1794903 .0880548 2.04 0.042 .0063255 .3526551 _cons | 3.004543 .1447786 20.75 0.000 2.719828 3.289259 ------------------------------------------------------------------------------ 342 . glm hp2hmcare bf4 age bf40 if gender==`g', fam(binomial) link(probit) irls sc > ale(dev) Iteration 1: deviance = 373.2413 Iteration 2: deviance = 372.8437 Iteration 3: deviance = 372.8436 Iteration 4: deviance = 372.8436 Generalized linear models No. of obs = 363 Optimization : MQL Fisher scoring Residual df = 359 (IRLS EIM) Scale parameter = 1 Deviance = 372.8435707 (1/df) Deviance = 1.038561 Pearson = 384.2294832 (1/df) Pearson = 1.070277 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1743.247 ------------------------------------------------------------------------------ | EIM hp2hmcare | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- bf4 | -.0701088 .0159082 -4.41 0.000 -.1012882 -.0389293 age | .0419129 .007264 5.77 0.000 .0276756 .0561501 bf40 | -.0040389 .0340124 -0.12 0.905 -.070702 .0626242 _cons | -1.841186 .4704258 -3.91 0.000 -2.763204 -.9191686 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 343 . title4 "When bf4 bf40 and age are together only age and b4 are a wave 2 media > tors for women" ------------------------------------------------------------------------------- When bf4 bf40 and age are together only age and b4 are a wave 2 mediators for w > omen ------------------------------------------------------------------------------- 344 . 345 . 346 . 347 . local g 2 348 . title "Test of female mediation in wave 2" ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Test of female mediation in wave 2 ***** ***** ***** ***** ***** ***** 16 Jun 2012 21:53:18 ***** ******************************************************************************* ******************************************************************************* 349 . mvreg bf4 age bf40 illw2 = avgcumdosew2 if gender==`g' Equation Obs Parms RMSE "R-sq" F P ---------------------------------------------------------------------- bf4 363 2 5.151001 0.0249 9.209323 0.0026 age 363 2 11.70121 0.0306 11.37694 0.0008 bf40 363 2 2.313305 0.0114 4.155047 0.0422 illw2 363 2 .8699891 0.0380 14.24594 0.0002 ------------------------------------------------------------------------------ | Coef. Std. Err. t P>|t| [95% Conf. Interval] -------------+---------------------------------------------------------------- bf4 | avgcumdosew2 | -.595012 .1960703 -3.03 0.003 -.9805954 -.2094285 _cons | 11.02048 .3223763 34.19 0.000 10.38651 11.65445 -------------+---------------------------------------------------------------- age | avgcumdosew2 | 1.502324 .4454009 3.37 0.001 .6264181 2.378231 _cons | 48.86944 .7323225 66.73 0.000 47.42929 50.3096 -------------+---------------------------------------------------------------- bf40 | avgcumdosew2 | .1794903 .0880548 2.04 0.042 .0063255 .3526551 _cons | 3.004543 .1447786 20.75 0.000 2.719828 3.289259 -------------+---------------------------------------------------------------- illw2 | avgcumdosew2 | .1249912 .0331157 3.77 0.000 .0598673 .1901152 _cons | .301285 .0544484 5.53 0.000 .1942091 .4083609 ------------------------------------------------------------------------------ 350 . glm hp2hmcare bf4 age bf40 illw2 if gender==`g', fam(binomial) link(probit) i > rls scale(dev) Iteration 1: deviance = 371.4357 Iteration 2: deviance = 371.0168 Iteration 3: deviance = 371.0167 Iteration 4: deviance = 371.0167 Generalized linear models No. of obs = 363 Optimization : MQL Fisher scoring Residual df = 358 (IRLS EIM) Scale parameter = 1 Deviance = 371.0167043 (1/df) Deviance = 1.03636 Pearson = 385.0960041 (1/df) Pearson = 1.075687 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1739.18 ------------------------------------------------------------------------------ | EIM hp2hmcare | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- bf4 | -.0756726 .0166172 -4.55 0.000 -.1082417 -.0431034 age | .04214 .0072721 5.79 0.000 .0278868 .0563931 bf40 | .0027501 .0343366 0.08 0.936 -.0645483 .0700486 illw2 | -.1146115 .0858363 -1.34 0.182 -.2828475 .0536245 _cons | -1.768282 .4754356 -3.72 0.000 -2.700118 -.8364451 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 351 . qui: { When all are together only age and b4 are a wave 2 mediators for women 352 . 353 . 354 . scalar WkMedFw2 = "age bf4" 355 . 356 . scalar SigDoseWKMw2 = "no" 357 . scalar MainEffwkMw2 = "workM: age" 358 . scalar MainEffwkFw2 = "age" 359 . scalar WkModFw2 = "none" 360 . 361 . 362 . 363 . 364 . 365 . 366 . title4 "*---1.- Summary matrix construction Paid employment partition: first > two rows" ------------------------------------------------------------------------------- *---1.- Summary matrix construction Paid employment partition: first two rows ------------------------------------------------------------------------------- 367 . 368 . matrix define wkMw2 = J(1,8, 0) 369 . matrix define wkFw2 = J(1,8, 0) 370 . matrix colnames wkMw2= hypnum ptnum wave gender medsig numMAsig numModsig n > umMed 371 . matrix colnames wkFw2= hypnum ptnum wave gender medsig numMAsig numModsig n > umMed 372 . matrix rownames wkMw2 = workMw2 373 . matrix rownames wkFw2 = workFw2 374 . matrix define wkMw2= (1, 2, 2, 1, 0 ,2, 0 , 2 ) 375 . matrix define wkFw2= (1, 2, 2, 2, 0, 1, 0 , 2 ) 376 . 377 . matrix define H1pt2w2 = ( wkMw2 \ wkFw2) 378 . matrix colnames H1pt2w2 = hypnum ptnum wave medsig numMAsig numModsig n > umMed 379 . matrix rownames H1pt2w2 = wkMw2 wkFw2 380 . matlist H1pt2w2 | hypnum ptnum wave medsig numMAsig numModsig > numMed numMed -------------+----------------------------------------------------------------- ----------------------- wkMw2 | 1 2 2 1 0 2 > 0 2 wkFw2 | 1 2 2 2 0 1 > 0 2 381 . 382 . 383 . scalar list MainEffwkFw2 = age MainEffwkMw2 = workM: age ProbsocMedFw2 = age radhlw2 ProbsocMedMw2 = age ProbsocModFw2 = none MainEffProbSocFw2 = age avgcomdosew2 radhlw2 avgcumodsew2 b4 SigDoseProbsocFw2 = yes ProbSocModMw2 = none SigDoseProbsocMw2 = no PrbsocModMw2 = none MainEffPrbsocMw2 = age radhlw2 shjobw2 SigdoseMw2 = none hmcareMedFw2 = age hmcareMedMw2 = age hmcareModFw2 = none MainEffhmcarew2 = age SigdoseHmcareFw2 = no hmcareModMw2 = none MainEffhmcareMw2 = b4 SigDoseHmcareMw2 = no wkMedFw2 = radhlw2 age bf40 bf4m bf1 NameMedMw2 = age ageXillw2 NumModMw2 = none SigDosehmcareMw2 = no SigDoseWKMw2 = no WkMedFw2 = age bf4 WkMedMw2 = age ageXillw2 WkModFw2 = none WKModMw2 = none SigDoseWkMw2 = no SigDoseWkFw2 = no SigDoseFw2 = no wkModFw2 = none wkModMw2 = none 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 384 . * moderator construction 385 . * none ussed because basic dose work relationship washes out 386 . 387 . title "2. Hyp 1 pt 2 wave 2 dose Hp2hmcare impact explored" ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** 2. Hyp 1 pt 2 wave 2 dose Hp2hmcare impact explored ***** ***** ***** ***** ***** ***** 16 Jun 2012 21:53:21 ***** ******************************************************************************* ******************************************************************************* 388 . 389 . * ------- testing male and female moderators-wave 2 for hmcare-------------- > --- 390 . 391 . cap gen hp2hmcare=HP2hmcare 392 . 393 . forvalues j = 2/2 { 2. set more off 3. local w2bf bf1 bf4 bf6 bf7 bf14 bf15 bf40 4. di as input "For females hp2hmcare on Wave 2 with dose ns" 5. des age occ1w`j'-occ8w`j' inc1w`j'-inc4w`j' avgcumdosew`j' bf8 // > / > marrw`j'1-marrw`j'6 `w2bf' radhlw`j' 6. sw, pr(.1): logistic hp2hmcare marrw`j'3-marrw`j'6 age havmilsq / > // > avgcumdosew1 bf8 illw`j' shjobw`j' suprtw`j' if gender==1, co > ef 7. estat gof 8. estat class 9. fitstat 10. } For females hp2hmcare on Wave 2 with dose ns storage display value variable name type format label variable label ------------------------------------------------------------------------------- age double %8.0g * Respondent's age occ1w2 double %15.0g LABJ profess executive administration in 1996 occ2w2 double %15.0g LABJ technical sales admin support in 1996 occ3w2 double %15.0g LABJ service occup protective services in 1996 occ4w2 double %15.0g LABJ precision prod mechan craft construction in 1996 occ5w2 double %15.0g LABJ factory laborer machinist transp cleaner in 1996 occ6w2 double %15.0g LABJ farming agricul forestry fishing trapping logging in 1996 occ7w2 double %15.0g LABJ homemaking caregiving in 1996 occ8w2 double %15.0g LABJ student in 1996 inc1w2 double %15.0g LABJ Income is not sufficient for basic neccessities in 1996 inc2w2 double %15.0g LABJ Income is just sufficient for basic neccessities in 1996 inc3w2 double %15.0g LABJ Income is sufficient for basics plus extra purchases/savings in 1996 inc4w2 double %15.0g LABJ Income allows to comfortably afford luxury items in 1996 avgcumdosew2 double %8.0g Average mean dose CS1337 in mGy for wave 2 bf8 float %9.0g bf8 = max(0, radtlw3 - 40) * bf5m marrw21 byte %8.0g marrw2==1. single marrw22 byte %8.0g marrw2==2. cohabitating marrw23 byte %8.0g marrw2==3. married marrw24 byte %8.0g marrw2==4. separated marrw25 byte %8.0g marrw2==5. divorced marrw26 byte %8.0g marrw2==6. widowed bf1 float %9.0g bf1 = max(0, kzchorn - 40) bf4 float %9.0g bf4 = max(0, 24 - BSIsoma) bf6 float %9.0g bf6= max(0, radtlw2 - 10) bf7 float %9.0g bf7= max(0, 10 - radtlw2) bf14 float %9.0g bf14= max(0, radw2 - 10) * bf12 bf15 float %9.0g bf15= max(0, 10 - radw2) * bf12 bf40 float %9.0g bf40 = max(0, icdxcnt - 1.01635E-007) radhlw2 double %8.0g how much believed personal health is affected by radiation in 1996 begin with full model p = 0.7326 >= 0.1000 removing marrw25 p = 0.6899 >= 0.1000 removing avgcumdosew1 p = 0.5598 >= 0.1000 removing marrw24 p = 0.5279 >= 0.1000 removing havmilsq p = 0.4308 >= 0.1000 removing suprtw2 p = 0.3812 >= 0.1000 removing bf8 p = 0.3963 >= 0.1000 removing marrw26 p = 0.1763 >= 0.1000 removing shjobw2 p = 0.2257 >= 0.1000 removing marrw23 Logistic regression Number of obs = 340 LR chi2(2) = 28.54 Prob > chi2 = 0.0000 Log likelihood = -158.60117 Pseudo R2 = 0.0826 ------------------------------------------------------------------------------ hp2hmcare | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0538093 .0119121 4.52 0.000 .030462 .0771566 illw2 | .347449 .2097345 1.66 0.098 -.063623 .7585211 _cons | -4.244759 .6492495 -6.54 0.000 -5.517264 -2.972253 ------------------------------------------------------------------------------ Logistic model for hp2hmcare, goodness-of-fit test number of observations = 340 number of covariate patterns = 91 Pearson chi2(88) = 90.18 Prob > chi2 = 0.4155 Logistic model for hp2hmcare -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 3 2 | 5 - | 67 268 | 335 -----------+--------------------------+----------- Total | 70 270 | 340 Classified + if predicted Pr(D) >= .5 True D defined as hp2hmcare != 0 -------------------------------------------------- Sensitivity Pr( +| D) 4.29% Specificity Pr( -|~D) 99.26% Positive predictive value Pr( D| +) 60.00% Negative predictive value Pr(~D| -) 80.00% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 0.74% False - rate for true D Pr( -| D) 95.71% False + rate for classified + Pr(~D| +) 40.00% False - rate for classified - Pr( D| -) 20.00% -------------------------------------------------- Correctly classified 79.71% -------------------------------------------------- Measures of Fit for logistic of hp2hmcare Log-Lik Intercept Only: -172.873 Log-Lik Full Model: -158.601 D(337): 317.202 LR(2): 28.543 Prob > LR: 0.000 McFadden's R2: 0.083 McFadden's Adj R2: 0.065 Maximum Likelihood R2: 0.081 Cragg & Uhler's R2: 0.126 McKelvey and Zavoina's R2: 0.140 Efron's R2: 0.094 Variance of y*: 3.826 Variance of error: 3.290 Count R2: 0.797 Adj Count R2: 0.014 AIC: 0.951 AIC*n: 323.202 BIC: -1647.152 BIC': -16.886 394 . 395 . scalar SigDosehmcareMw2 = "no" 396 . scalar MainEffhmcareMw2 = "age" 397 . 398 . title4 "Trimmed male Hp2hmcare moderator model" ------------------------------------------------------------------------------- Trimmed male Hp2hmcare moderator model ------------------------------------------------------------------------------- 399 . 400 . cap gen ageXd2= age*avgcumdosew2 401 . 402 . forvalues j = 2/2 { 2. set more off 3. local w2bf bf1 bf4 bf6 bf7 bf14 bf15 bf40 4. di as input "For females HP2hmcare on Wave 2 with dose ns" 5. des age avgcumdosew`j' /// > marrw`j'1-marrw`j'6 `w2bf' radhlw`j' 6. sw, pr(.1): logistic hp2hmcare marrw`j'3-marrw`j'6 age havmilsq / > // > avgcumdosew1 bf8 illw`j' ageXd2 if gender==2, coef 7. estat gof 8. estat class 9. fitstat 10. } For females HP2hmcare on Wave 2 with dose ns storage display value variable name type format label variable label ------------------------------------------------------------------------------- age double %8.0g * Respondent's age avgcumdosew2 double %8.0g Average mean dose CS1337 in mGy for wave 2 marrw21 byte %8.0g marrw2==1. single marrw22 byte %8.0g marrw2==2. cohabitating marrw23 byte %8.0g marrw2==3. married marrw24 byte %8.0g marrw2==4. separated marrw25 byte %8.0g marrw2==5. divorced marrw26 byte %8.0g marrw2==6. widowed bf1 float %9.0g bf1 = max(0, kzchorn - 40) bf4 float %9.0g bf4 = max(0, 24 - BSIsoma) bf6 float %9.0g bf6= max(0, radtlw2 - 10) bf7 float %9.0g bf7= max(0, 10 - radtlw2) bf14 float %9.0g bf14= max(0, radw2 - 10) * bf12 bf15 float %9.0g bf15= max(0, 10 - radw2) * bf12 bf40 float %9.0g bf40 = max(0, icdxcnt - 1.01635E-007) radhlw2 double %8.0g how much believed personal health is affected by radiation in 1996 note: marrw24 dropped because of estimability note: o.marrw24 dropped because of estimability note: 1 obs. dropped because of estimability begin with full model p = 0.9951 >= 0.1000 removing illw2 p = 0.9258 >= 0.1000 removing ageXd2 p = 0.7659 >= 0.1000 removing marrw26 p = 0.5841 >= 0.1000 removing marrw25 p = 0.4120 >= 0.1000 removing havmilsq p = 0.1534 >= 0.1000 removing avgcumdosew1 Logistic regression Number of obs = 362 LR chi2(3) = 86.32 Prob > chi2 = 0.0000 Log likelihood = -189.50071 Pseudo R2 = 0.1855 ------------------------------------------------------------------------------ hp2hmcare | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- marrw23 | .7505039 .3256256 2.30 0.021 .1122894 1.388718 age | .0908699 .0124059 7.32 0.000 .0665547 .115185 bf8 | -.0000294 .0000124 -2.36 0.018 -.0000538 -5.02e-06 _cons | -5.778428 .7158956 -8.07 0.000 -7.181557 -4.375298 ------------------------------------------------------------------------------ Logistic model for hp2hmcare, goodness-of-fit test number of observations = 362 number of covariate patterns = 194 Pearson chi2(190) = 202.83 Prob > chi2 = 0.2490 Logistic model for hp2hmcare -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 62 31 | 93 - | 62 207 | 269 -----------+--------------------------+----------- Total | 124 238 | 362 Classified + if predicted Pr(D) >= .5 True D defined as hp2hmcare != 0 -------------------------------------------------- Sensitivity Pr( +| D) 50.00% Specificity Pr( -|~D) 86.97% Positive predictive value Pr( D| +) 66.67% Negative predictive value Pr(~D| -) 76.95% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 13.03% False - rate for true D Pr( -| D) 50.00% False + rate for classified + Pr(~D| +) 33.33% False - rate for classified - Pr( D| -) 23.05% -------------------------------------------------- Correctly classified 74.31% -------------------------------------------------- Measures of Fit for logistic of hp2hmcare Log-Lik Intercept Only: -232.660 Log-Lik Full Model: -189.501 D(358): 379.001 LR(3): 86.318 Prob > LR: 0.000 McFadden's R2: 0.186 McFadden's Adj R2: 0.168 Maximum Likelihood R2: 0.212 Cragg & Uhler's R2: 0.293 McKelvey and Zavoina's R2: 0.312 Efron's R2: 0.229 Variance of y*: 4.782 Variance of error: 3.290 Count R2: 0.743 Adj Count R2: 0.250 AIC: 1.069 AIC*n: 387.001 BIC: -1730.207 BIC': -68.643 403 . 404 . 405 . 406 . 407 . scalar NumModMw2 = "none" 408 . 409 . 410 . title4 "age is a male mediator in wave 2" ------------------------------------------------------------------------------- age is a male mediator in wave 2 ------------------------------------------------------------------------------- 411 . glm age avgcumdosew2 if gender==1, fam(gaussian) link(identity) Iteration 0: log likelihood = -1330.6004 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = 147.6853 Deviance = 49917.64009 (1/df) Deviance = 147.6853 Pearson = 49917.64009 (1/df) Pearson = 147.6853 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 7.838826 Log likelihood = -1330.6004 BIC = 47947.46 ------------------------------------------------------------------------------ | OIM age | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew2 | .5832314 .2635871 2.21 0.027 .0666101 1.099853 _cons | 48.62133 .7061562 68.85 0.000 47.23729 50.00537 ------------------------------------------------------------------------------ 412 . 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.) 413 . 414 . scalar NameMedMw2 = "age ageXillw2" 415 . 416 . di as input "age is a possible male mediator for home care in wave 2" age is a possible male mediator for home care in wave 2 417 . 418 . 419 . di as input "age and illw2 as main effects together suppress illw2" age and illw2 as main effects together suppress illw2 420 . glm illw2 age avgcumdosew2 if gender==1, family(gaussian) link(identity) Iteration 0: log likelihood = -294.89214 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 337 Scale parameter = .3347555 Deviance = 112.812617 (1/df) Deviance = .3347555 Pearson = 112.812617 (1/df) Pearson = .3347555 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 1.752307 Log likelihood = -294.8921379 BIC = -1851.542 ------------------------------------------------------------------------------ | OIM illw2 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .010896 .0025896 4.21 0.000 .0058205 .0159716 avgcumdosew2 | .0021874 .0126399 0.17 0.863 -.0225863 .0269611 _cons | -.2556434 .1303222 -1.96 0.050 -.5110702 -.0002165 ------------------------------------------------------------------------------ 421 . glm hp2hmcare illw2 age if gender==1, family(binomial) irls scale(dev) link( > probit) Iteration 1: deviance = 318.4593 Iteration 2: deviance = 317.6467 Iteration 3: deviance = 317.6458 Iteration 4: deviance = 317.6458 Generalized linear models No. of obs = 340 Optimization : MQL Fisher scoring Residual df = 337 (IRLS EIM) Scale parameter = 1 Deviance = 317.6458464 (1/df) Deviance = .9425693 Pearson = 345.1774401 (1/df) Pearson = 1.024265 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1646.709 ------------------------------------------------------------------------------ | EIM hp2hmcare | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- illw2 | .1994222 .1221622 1.63 0.103 -.0400114 .4388557 age | .0303611 .0065398 4.64 0.000 .0175433 .043179 _cons | -2.436578 .3445976 -7.07 0.000 -3.111977 -1.761179 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 422 . 423 . 424 . di as input "Interaction of age and wave 2 illness for males is mediator-mode > rator on hmcare" Interaction of age and wave 2 illness for males is mediator-moderator on hmcare 425 . 426 . cap gen ageXillw2 = age*illw2 427 . glm illw2 avgcumdosew2 if gender==1, family(gaussian) link(identity) Iteration 0: log likelihood = -303.59609 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = .3512988 Deviance = 118.7390083 (1/df) Deviance = .3512988 Pearson = 118.7390083 (1/df) Pearson = .3512988 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 1.797624 Log likelihood = -303.5960853 BIC = -1851.445 ------------------------------------------------------------------------------ | OIM illw2 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew2 | .0085423 .0128556 0.66 0.506 -.0166543 .0337389 _cons | .2741359 .0344406 7.96 0.000 .2066336 .3416382 ------------------------------------------------------------------------------ 428 . glm hp2hmcare illw2 avgcumdosew2 ageXillw2 if gender==1, family(binomial) /// > irls scale(dev) link(probit) Iteration 1: deviance = 325.2943 Iteration 2: deviance = 325.0754 Iteration 3: deviance = 325.0739 Iteration 4: deviance = 325.0739 Iteration 5: deviance = 325.0739 Generalized linear models No. of obs = 340 Optimization : MQL Fisher scoring Residual df = 336 (IRLS EIM) Scale parameter = 1 Deviance = 325.0738987 (1/df) Deviance = .9674818 Pearson = 337.8592784 (1/df) Pearson = 1.005534 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1633.452 ------------------------------------------------------------------------------ | EIM hp2hmcare | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- illw2 | -2.019327 .7153941 -2.82 0.005 -3.421474 -.6171808 avgcumdosew2 | -.000217 .0298223 -0.01 0.994 -.0586676 .0582336 ageXillw2 | .0422954 .0126323 3.35 0.001 .0175365 .0670543 _cons | -.9410134 .0916093 -10.27 0.000 -1.120564 -.7614625 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 429 . 430 . 431 . 432 . * Saving mediators as scalars for Dose=work relationship 433 . **** female mediators of dose-paid employment: radhlw2, age, bf40, bf4m, bf4, > bf1 434 . scalar wkMedFw2 = "radhlw2 age bf40 bf4m bf1" 435 . scalar list MainEffhmcareMw2 = age MainEffwkFw2 = age MainEffwkMw2 = workM: age ProbsocMedFw2 = age radhlw2 ProbsocMedMw2 = age ProbsocModFw2 = none MainEffProbSocFw2 = age avgcomdosew2 radhlw2 avgcumodsew2 b4 SigDoseProbsocFw2 = yes ProbSocModMw2 = none SigDoseProbsocMw2 = no PrbsocModMw2 = none MainEffPrbsocMw2 = age radhlw2 shjobw2 SigdoseMw2 = none hmcareMedFw2 = age hmcareMedMw2 = age hmcareModFw2 = none MainEffhmcarew2 = age SigdoseHmcareFw2 = no hmcareModMw2 = none SigDoseHmcareMw2 = no wkMedFw2 = radhlw2 age bf40 bf4m bf1 NameMedMw2 = age ageXillw2 NumModMw2 = none SigDosehmcareMw2 = no SigDoseWKMw2 = no WkMedFw2 = age bf4 WkMedMw2 = age ageXillw2 WkModFw2 = none WKModMw2 = none SigDoseWkMw2 = no SigDoseWkFw2 = no SigDoseFw2 = no wkModFw2 = none wkModMw2 = none 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 436 . 437 . 438 . cap gen hp2vacatn = HP2vacatn 439 . 440 . 441 . *xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx > xxx 442 . *------ Chunk 3 Dose=> hp2hmcare impact for males and females 443 . *xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx > xxx 444 . 445 . title "2. H1 pt2 wave 2 Dose Homecare impact " ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** 2. H1 pt2 wave 2 Dose Homecare impact ***** ***** ***** ***** ***** ***** 16 Jun 2012 21:53:54 ***** ******************************************************************************* ******************************************************************************* 446 . 447 . 448 . * review of general model for men and women 449 . 450 . forvalues j = 2/2 { 2. set more off 3. 451 . des age educ1-educ7 marrw`j'1-marrw`j'6 inc1w`j'-inc4w`j' /// > bf1 bf4 bf9 bf11 bf4m bf15m bf30 bf40 4. 452 . foreach var in HP2hmcare { 5. 453 . forvalues k=1/2 { 6. local w2bf bf1 bf4 bf6 bf7 bf14 bf15 bf40 7. title "chunk 3 H1 test pt 2 :Gender= `k' model Wave = `j' for `e(dep > var)' " 8. di _skip(4) 9. 454 . 455 . 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' radhlw2 /// > illw`j' shfamw`j' shhlw`j' shjobw`j' shrelaw`j' suprtw`j' suc > hrw`j' /// > havmilsq if gender==`k', coef 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 marrw21 byte %8.0g marrw2==1. single marrw22 byte %8.0g marrw2==2. cohabitating marrw23 byte %8.0g marrw2==3. married marrw24 byte %8.0g marrw2==4. separated marrw25 byte %8.0g marrw2==5. divorced marrw26 byte %8.0g marrw2==6. widowed inc1w2 double %15.0g LABJ Income is not sufficient for basic neccessities in 1996 inc2w2 double %15.0g LABJ Income is just sufficient for basic neccessities in 1996 inc3w2 double %15.0g LABJ Income is sufficient for basics plus extra purchases/savings in 1996 inc4w2 double %15.0g LABJ Income allows to comfortably afford luxury items in 1996 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 = 2 for hp2hmcare ***** ***** ***** ***** ***** ***** 16 Jun 2012 21:53:54 ***** ******************************************************************************* ******************************************************************************* i.educ _Ieduc_1-8 (naturally coded; _Ieduc_1 omitted) note: _Ieduc_4 != 0 predicts failure perfectly _Ieduc_4 dropped and 12 obs not used note: _Ieduc_8 != 0 predicts failure perfectly _Ieduc_8 dropped and 2 obs not used note: occ8w2 != 0 predicts failure perfectly occ8w2 dropped and 43 obs not used note: sepaw2 != 0 predicts failure perfectly sepaw2 dropped and 6 obs not used note: _Ieduc_7 omitted because of collinearity note: bf15 omitted because of collinearity note: radhlw2 omitted because of collinearity Logistic regression Number of obs = 269 LR chi2(42) = 109.76 Prob > chi2 = 0.0000 Log likelihood = -97.204962 Pseudo R2 = 0.3609 ------------------------------------------------------------------------------ HP2hmcare | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0338165 .0226356 1.49 0.135 -.0105484 .0781815 _Ieduc_2 | -4.276213 1.974151 -2.17 0.030 -8.145479 -.406947 _Ieduc_3 | -2.496446 1.569642 -1.59 0.112 -5.572887 .579995 _Ieduc_4 | 0 (omitted) _Ieduc_5 | -1.933257 1.595074 -1.21 0.226 -5.059545 1.193031 _Ieduc_6 | -2.731404 1.5115 -1.81 0.071 -5.693888 .2310807 _Ieduc_7 | 0 (omitted) _Ieduc_8 | 0 (omitted) occ1w2 | .447866 3.337423 0.13 0.893 -6.093362 6.989094 occ2w2 | -.0398 3.356232 -0.01 0.991 -6.617893 6.538293 occ3w2 | .5016738 3.37088 0.15 0.882 -6.105129 7.108476 occ4w2 | .4812856 3.378935 0.14 0.887 -6.141306 7.103877 occ5w2 | 1.51252 3.404132 0.44 0.657 -5.159455 8.184496 occ6w2 | 2.9603 3.825064 0.77 0.439 -4.536687 10.45729 occ7w2 | .5681102 3.446364 0.16 0.869 -6.186638 7.322859 occ8w2 | 0 (omitted) marrw21 | -1.554879 1.682488 -0.92 0.355 -4.852495 1.742737 marrw22 | -3.80953 2.028746 -1.88 0.060 -7.785799 .1667393 marrw23 | -3.665421 1.71283 -2.14 0.032 -7.022506 -.3083347 marrw25 | -1.481731 4.126728 -0.36 0.720 -9.56997 6.606508 marrw26 | -2.880741 2.479902 -1.16 0.245 -7.741261 1.979778 inc1w2 | 2.844486 3.430733 0.83 0.407 -3.879627 9.568599 inc2w2 | 2.655327 3.349177 0.79 0.428 -3.908939 9.219593 inc3w2 | 3.052721 3.355091 0.91 0.363 -3.523137 9.628579 inc4w2 | 1.171678 3.639724 0.32 0.748 -5.96205 8.305406 radhlw2 | -.0026842 .0077227 -0.35 0.728 -.0178205 .0124521 havmil | .002871 .0081498 0.35 0.725 -.0131023 .0188444 avgcumdosew2 | -.0220473 .0954292 -0.23 0.817 -.2090852 .1649906 bf1 | -.0176257 .0110209 -1.60 0.110 -.0392262 .0039748 bf4 | -.3209329 .0601062 -5.34 0.000 -.4387388 -.203127 bf6 | .0142094 .0096047 1.48 0.139 -.0046155 .0330342 bf7 | .1041093 .0843677 1.23 0.217 -.0612484 .269467 bf14 | 5.78e-06 .0000736 0.08 0.937 -.0001386 .0001501 bf15 | 0 (omitted) bf40 | .3500268 .1396049 2.51 0.012 .0764063 .6236473 deaw2 | .0522034 .3200036 0.16 0.870 -.5749921 .6793989 dvcew2 | -.370905 3.78656 -0.10 0.922 -7.792426 7.050615 sepaw2 | 0 (omitted) accdw2 | .1929199 .4604851 0.42 0.675 -.7096143 1.095454 movew2 | .2586331 .5214207 0.50 0.620 -.7633328 1.280599 radhlw2 | 0 (omitted) illw2 | -.1291222 .3453441 -0.37 0.708 -.8059842 .5477398 shfamw2 | -.0123461 .0080757 -1.53 0.126 -.0281741 .0034819 shhlw2 | -.0067088 .0095447 -0.70 0.482 -.0254161 .0119985 shjobw2 | -.0001525 .009703 -0.02 0.987 -.0191701 .018865 shrelaw2 | .0044873 .0074837 0.60 0.549 -.0101805 .0191551 suprtw2 | .0138227 .0067373 2.05 0.040 .0006178 .0270276 suchrw2 | -.0024443 .0059474 -0.41 0.681 -.0141011 .0092124 havmilsq | -7.11e-06 .0000151 -0.47 0.639 -.0000368 .0000226 _cons | 1.915103 3.160353 0.61 0.545 -4.279075 8.109282 ------------------------------------------------------------------------------ Logistic model for HP2hmcare -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 38 14 | 52 - | 30 187 | 217 -----------+--------------------------+----------- Total | 68 201 | 269 Classified + if predicted Pr(D) >= .5 True D defined as HP2hmcare != 0 -------------------------------------------------- Sensitivity Pr( +| D) 55.88% Specificity Pr( -|~D) 93.03% Positive predictive value Pr( D| +) 73.08% Negative predictive value Pr(~D| -) 86.18% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 6.97% False - rate for true D Pr( -| D) 44.12% False + rate for classified + Pr(~D| +) 26.92% False - rate for classified - Pr( D| -) 13.82% -------------------------------------------------- Correctly classified 83.64% -------------------------------------------------- Logistic model for HP2hmcare, goodness-of-fit test number of observations = 269 number of covariate patterns = 269 Pearson chi2(226) = 228.79 Prob > chi2 = 0.4356 Measures of Fit for logistic of HP2hmcare Log-Lik Intercept Only: -152.087 Log-Lik Full Model: -97.205 D(219): 194.410 LR(42): 109.763 Prob > LR: 0.000 McFadden's R2: 0.361 McFadden's Adj R2: 0.032 Maximum Likelihood R2: 0.335 Cragg & Uhler's R2: 0.495 McKelvey and Zavoina's R2: 0.599 Efron's R2: 0.381 Variance of y*: 8.208 Variance of error: 3.290 Count R2: 0.836 Adj Count R2: 0.353 AIC: 1.094 AIC*n: 294.410 BIC: -1030.832 BIC': 125.215 ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** chunk 3 H1 test pt 2 :Gender= 2 model Wave = 2 for HP2hmcare ***** ***** ***** ***** ***** ***** 16 Jun 2012 21:53:56 ***** ******************************************************************************* ******************************************************************************* i.educ _Ieduc_1-8 (naturally coded; _Ieduc_1 omitted) note: _Ieduc_8 omitted because of collinearity note: marrw26 omitted because of collinearity note: bf15 omitted because of collinearity note: radhlw2 omitted because of collinearity Logistic regression Number of obs = 362 LR chi2(45) = 176.34 Prob > chi2 = 0.0000 Log likelihood = -144.48759 Pseudo R2 = 0.3790 ------------------------------------------------------------------------------ HP2hmcare | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0738943 .0179039 4.13 0.000 .0388033 .1089852 _Ieduc_2 | -14.47538 1273.657 -0.01 0.991 -2510.798 2481.847 _Ieduc_3 | -15.05547 1273.657 -0.01 0.991 -2511.378 2481.267 _Ieduc_4 | -13.48341 1273.657 -0.01 0.992 -2509.806 2482.839 _Ieduc_5 | -14.88762 1273.657 -0.01 0.991 -2511.21 2481.435 _Ieduc_6 | -15.58826 1273.657 -0.01 0.990 -2511.911 2480.734 _Ieduc_7 | -13.81171 1273.659 -0.01 0.991 -2510.137 2482.513 _Ieduc_8 | 0 (omitted) occ1w2 | -2.359905 1.509597 -1.56 0.118 -5.318661 .5988504 occ2w2 | -2.373759 1.546944 -1.53 0.125 -5.405713 .6581945 occ3w2 | -1.535666 1.553674 -0.99 0.323 -4.58081 1.509479 occ4w2 | -2.972204 1.655316 -1.80 0.073 -6.216564 .2721556 occ5w2 | -4.352791 1.883178 -2.31 0.021 -8.043752 -.6618289 occ6w2 | -5.059677 2.021732 -2.50 0.012 -9.022199 -1.097155 occ7w2 | -1.364295 1.545156 -0.88 0.377 -4.392746 1.664156 occ8w2 | -.5789576 1.792303 -0.32 0.747 -4.091808 2.933892 marrw21 | -.0690078 1.129464 -0.06 0.951 -2.282717 2.144702 marrw22 | .7043443 1.44356 0.49 0.626 -2.124982 3.533671 marrw23 | 2.097285 .8281102 2.53 0.011 .4742186 3.720351 marrw25 | .9609574 1.20757 0.80 0.426 -1.405836 3.327751 marrw26 | 0 (omitted) inc1w2 | 2.105274 1.594442 1.32 0.187 -1.019775 5.230323 inc2w2 | 3.407471 1.542788 2.21 0.027 .3836621 6.43128 inc3w2 | 2.870172 1.549672 1.85 0.064 -.1671285 5.907473 inc4w2 | 3.606463 1.894634 1.90 0.057 -.1069505 7.319876 radhlw2 | -.0068123 .0061828 -1.10 0.271 -.0189302 .0053057 havmil | .0011484 .0030211 0.38 0.704 -.0047728 .0070696 avgcumdosew2 | -.2667926 .1232968 -2.16 0.030 -.5084499 -.0251353 bf1 | -.0183931 .0079003 -2.33 0.020 -.0338774 -.0029088 bf4 | -.2337773 .0416245 -5.62 0.000 -.3153598 -.1521948 bf6 | .0040038 .0067939 0.59 0.556 -.009312 .0173196 bf7 | -.126659 .0709704 -1.78 0.074 -.2657584 .0124404 bf14 | -.0000228 .0000659 -0.35 0.729 -.0001521 .0001064 bf15 | 0 (omitted) bf40 | .0786288 .0758899 1.04 0.300 -.0701127 .2273704 deaw2 | .6463714 .2506264 2.58 0.010 .1551526 1.13759 dvcew2 | 1.46465 1.066188 1.37 0.170 -.6250398 3.554339 sepaw2 | -1.747364 1.628008 -1.07 0.283 -4.938201 1.443472 accdw2 | -.6760904 .5387942 -1.25 0.210 -1.732108 .3799268 movew2 | -.5261615 .493185 -1.07 0.286 -1.492786 .4404633 radhlw2 | 0 (omitted) illw2 | -.1619986 .1844507 -0.88 0.380 -.5235154 .1995182 shfamw2 | -.0039886 .0060041 -0.66 0.506 -.0157565 .0077793 shhlw2 | -.0091905 .0062486 -1.47 0.141 -.0214375 .0030565 shjobw2 | .0003458 .0057176 0.06 0.952 -.0108605 .011552 shrelaw2 | -.0091776 .006756 -1.36 0.174 -.0224192 .0040639 suprtw2 | -.0077623 .0046946 -1.65 0.098 -.0169635 .0014389 suchrw2 | .0040413 .0050755 0.80 0.426 -.0059065 .013989 havmilsq | -1.23e-06 2.83e-06 -0.44 0.664 -6.79e-06 4.32e-06 _cons | 12.31935 1273.659 0.01 0.992 -2484.005 2508.644 ------------------------------------------------------------------------------ Logistic model for HP2hmcare -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 85 27 | 112 - | 39 211 | 250 -----------+--------------------------+----------- Total | 124 238 | 362 Classified + if predicted Pr(D) >= .5 True D defined as HP2hmcare != 0 -------------------------------------------------- Sensitivity Pr( +| D) 68.55% Specificity Pr( -|~D) 88.66% Positive predictive value Pr( D| +) 75.89% Negative predictive value Pr(~D| -) 84.40% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 11.34% False - rate for true D Pr( -| D) 31.45% False + rate for classified + Pr(~D| +) 24.11% False - rate for classified - Pr( D| -) 15.60% -------------------------------------------------- Correctly classified 81.77% -------------------------------------------------- Logistic model for HP2hmcare, goodness-of-fit test number of observations = 362 number of covariate patterns = 362 Pearson chi2(316) = 339.77 Prob > chi2 = 0.1713 Measures of Fit for logistic of HP2hmcare Log-Lik Intercept Only: -232.660 Log-Lik Full Model: -144.488 D(312): 288.975 LR(45): 176.345 Prob > LR: 0.000 McFadden's R2: 0.379 McFadden's Adj R2: 0.164 Maximum Likelihood R2: 0.386 Cragg & Uhler's R2: 0.533 McKelvey and Zavoina's R2: 0.660 Efron's R2: 0.429 Variance of y*: 9.672 Variance of error: 3.290 Count R2: 0.818 Adj Count R2: 0.468 AIC: 1.075 AIC*n: 388.975 BIC: -1549.218 BIC': 88.779 456 . 457 . title4 "Male Main effects model for dose=> homcare Wave 2" ------------------------------------------------------------------------------- Male Main effects model for dose=> homcare Wave 2 ------------------------------------------------------------------------------- 458 . logit hp2hmcare age radhlw2 avgcumdosew2 bf4 bf40 if gender==1 Iteration 0: log likelihood = -172.87291 Iteration 1: log likelihood = -134.46709 Iteration 2: log likelihood = -131.09369 Iteration 3: log likelihood = -131.04872 Iteration 4: log likelihood = -131.04869 Iteration 5: log likelihood = -131.04869 Logistic regression Number of obs = 340 LR chi2(5) = 83.65 Prob > chi2 = 0.0000 Log likelihood = -131.04869 Pseudo R2 = 0.2419 ------------------------------------------------------------------------------ hp2hmcare | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0217541 .0144303 1.51 0.132 -.0065288 .050037 radhlw2 | .0005523 .0051456 0.11 0.915 -.0095329 .0106375 avgcumdosew2 | -.0011197 .0583762 -0.02 0.985 -.1155351 .1132956 bf4 | -.2083694 .0360875 -5.77 0.000 -.2790996 -.1376393 bf40 | .1322501 .0919626 1.44 0.150 -.0479933 .3124936 _cons | -.5194775 .9808733 -0.53 0.596 -2.441954 1.402999 ------------------------------------------------------------------------------ 459 . 460 . 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 461 . 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 462 . di as input " no male moderate interactions for dose-homecare impact" no male moderate interactions for dose-homecare impact 463 . 464 . scalar SigDoseHmcareMw2 = "no" 465 . scalar MainEffhmcareMw2= "b4" 466 . scalar list MainEffhmcareMw2 = b4 MainEffwkFw2 = age MainEffwkMw2 = workM: age ProbsocMedFw2 = age radhlw2 ProbsocMedMw2 = age ProbsocModFw2 = none MainEffProbSocFw2 = age avgcomdosew2 radhlw2 avgcumodsew2 b4 SigDoseProbsocFw2 = yes ProbSocModMw2 = none SigDoseProbsocMw2 = no PrbsocModMw2 = none MainEffPrbsocMw2 = age radhlw2 shjobw2 SigdoseMw2 = none hmcareMedFw2 = age hmcareMedMw2 = age hmcareModFw2 = none MainEffhmcarew2 = age SigdoseHmcareFw2 = no hmcareModMw2 = none SigDoseHmcareMw2 = no wkMedFw2 = radhlw2 age bf40 bf4m bf1 NameMedMw2 = age ageXillw2 NumModMw2 = none SigDosehmcareMw2 = no SigDoseWKMw2 = no WkMedFw2 = age bf4 WkMedMw2 = age ageXillw2 WkModFw2 = none WKModMw2 = none SigDoseWkMw2 = no SigDoseWkFw2 = no SigDoseFw2 = no wkModFw2 = none wkModMw2 = none 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 467 . 468 . title2 "male main effect plus interaction model" ------------------------------------------------------------------------------- title2: male main effect plus interaction model Date and time: 16 Jun 2012 21:53:59 Working directory: /Users/robertyaffee/ > Documents/data/research/chwk/phase3/Htests/h1tests/h1pt2 Stata data file: chwide16june2012.dta > has 2381 variables and 703 observations male main effect plus interaction model ------------------------------------------------------------------------------- 469 . xi:logit hp2hmcare age bf4 /// > if gender==1 Iteration 0: log likelihood = -172.87291 Iteration 1: log likelihood = -135.14268 Iteration 2: log likelihood = -132.11214 Iteration 3: log likelihood = -132.08145 Iteration 4: log likelihood = -132.08143 Iteration 5: log likelihood = -132.08143 Logistic regression Number of obs = 340 LR chi2(2) = 81.58 Prob > chi2 = 0.0000 Log likelihood = -132.08143 Pseudo R2 = 0.2360 ------------------------------------------------------------------------------ hp2hmcare | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0265235 .0138677 1.91 0.056 -.0006567 .0537037 bf4 | -.2166823 .0319545 -6.78 0.000 -.2793121 -.1540526 _cons | -.3105948 .9017305 -0.34 0.731 -2.077954 1.456764 ------------------------------------------------------------------------------ 470 . 471 . * there are no significant moderators for male dose=hmcare relationship 472 . scalar hmcareModMw2 = "none" 473 . 474 . 475 . title4 "testing female moderators for hp2hmcare in wave 2" ------------------------------------------------------------------------------- testing female moderators for hp2hmcare in wave 2 ------------------------------------------------------------------------------- 476 . local w2bf bf1 bf4 bf6 bf7 bf14 bf15 bf40 477 . * Dose work relationship for females in Wave 2 washes out also 478 . forvalues j = 2/2 { 2. set more off 3. di as input "For females hp2hmcare on wave 1 with dose ns" 4. des age avgcumdosew`j' `w2bf' 5. sw, pr(.1) : logistic hp2hmcare age ageXd2 havmilsq radhlw2 /// > avgcumdosew2 shhlw`j' shjobw`j' shrelaw`j' suprtw`j' if gender==2, coef 6. estat gof 7. estat class 8. fitstat 9. } 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 avgcumdosew2 double %8.0g Average mean dose CS1337 in mGy for wave 2 bf1 float %9.0g bf1 = max(0, kzchorn - 40) bf4 float %9.0g bf4 = max(0, 24 - BSIsoma) bf6 float %9.0g bf6= max(0, radtlw2 - 10) bf7 float %9.0g bf7= max(0, 10 - radtlw2) bf14 float %9.0g bf14= max(0, radw2 - 10) * bf12 bf15 float %9.0g bf15= max(0, 10 - radw2) * bf12 bf40 float %9.0g bf40 = max(0, icdxcnt - 1.01635E-007) begin with full model p = 0.9293 >= 0.1000 removing shhlw2 p = 0.8274 >= 0.1000 removing shjobw2 p = 0.6873 >= 0.1000 removing ageXd2 p = 0.5550 >= 0.1000 removing suprtw2 p = 0.5656 >= 0.1000 removing radhlw2 p = 0.4805 >= 0.1000 removing havmilsq p = 0.1609 >= 0.1000 removing avgcumdosew2 Logistic regression Number of obs = 363 LR chi2(2) = 77.67 Prob > chi2 = 0.0000 Log likelihood = -194.89458 Pseudo R2 = 0.1662 ------------------------------------------------------------------------------ hp2hmcare | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0918011 .0119846 7.66 0.000 .0683117 .1152905 shrelaw2 | -.0069355 .0040475 -1.71 0.087 -.0148684 .0009973 _cons | -5.233407 .6462713 -8.10 0.000 -6.500076 -3.966739 ------------------------------------------------------------------------------ Logistic model for hp2hmcare, goodness-of-fit test number of observations = 363 number of covariate patterns = 199 Pearson chi2(196) = 170.09 Prob > chi2 = 0.9094 Logistic model for hp2hmcare -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 55 30 | 85 - | 70 208 | 278 -----------+--------------------------+----------- Total | 125 238 | 363 Classified + if predicted Pr(D) >= .5 True D defined as hp2hmcare != 0 -------------------------------------------------- Sensitivity Pr( +| D) 44.00% Specificity Pr( -|~D) 87.39% Positive predictive value Pr( D| +) 64.71% Negative predictive value Pr(~D| -) 74.82% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 12.61% False - rate for true D Pr( -| D) 56.00% False + rate for classified + Pr(~D| +) 35.29% False - rate for classified - Pr( D| -) 25.18% -------------------------------------------------- Correctly classified 72.45% -------------------------------------------------- Measures of Fit for logistic of hp2hmcare Log-Lik Intercept Only: -233.729 Log-Lik Full Model: -194.895 D(360): 389.789 LR(2): 77.668 Prob > LR: 0.000 McFadden's R2: 0.166 McFadden's Adj R2: 0.153 Maximum Likelihood R2: 0.193 Cragg & Uhler's R2: 0.266 McKelvey and Zavoina's R2: 0.269 Efron's R2: 0.205 Variance of y*: 4.500 Variance of error: 3.290 Count R2: 0.725 Adj Count R2: 0.200 AIC: 1.090 AIC*n: 395.789 BIC: -1732.196 BIC': -65.879 479 . 480 . scalar SigdoseHmcareFw2="no" 481 . 482 . * capturing significant vars to test as moderators 483 . local cn4: colnames(e(b)) 484 . di "`cn4'" age shrelaw2 _cons 485 . local leng4 = length( "`cn4'") 486 . di `leng4' 18 487 . local leng4b `leng4'-6 488 . di `leng4b' 12 489 . local nuvlist4 = substr("`cn4'",4,`leng4b') 490 . di "`nuvlist4'" shrelaw2 _c 491 . local rhsvars4 = "`nuvlist4'" 492 . local nuvlist4= "`nuvlist4'" 493 . local nuvlist4= substr("`cn4'",1,`leng4b') 494 . di "`nuvlist4'" age shrelaw2 495 . 496 . cap gen shrelaw2Xd2 = shhlw2*avgcumdosew2 497 . 498 . title "No sig female moderators for dose-hmcare impact are found here" ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** No sig female moderators for dose-hmcare impact are found here ***** ***** ***** ***** ***** ***** 16 Jun 2012 21:54:12 ***** ******************************************************************************* ******************************************************************************* 499 . logit hp2hmcare age shrelaw2 avgcumdosew2 if gender==2 Iteration 0: log likelihood = -233.72859 Iteration 1: log likelihood = -194.49312 Iteration 2: log likelihood = -193.80537 Iteration 3: log likelihood = -193.8041 Iteration 4: log likelihood = -193.8041 Logistic regression Number of obs = 363 LR chi2(3) = 79.85 Prob > chi2 = 0.0000 Log likelihood = -193.8041 Pseudo R2 = 0.1708 ------------------------------------------------------------------------------ hp2hmcare | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0945686 .0122059 7.75 0.000 .0706456 .1184916 shrelaw2 | -.0065215 .0040622 -1.61 0.108 -.0144832 .0014402 avgcumdosew2 | -.1304033 .0930091 -1.40 0.161 -.3126979 .0518912 _cons | -5.265709 .6487449 -8.12 0.000 -6.537225 -3.994192 ------------------------------------------------------------------------------ 500 . logit hp2hmcare age shrelaw2 avgcumdosew2 ageXd2 shrelaw2Xd2 Iteration 0: log likelihood = -414.77126 Iteration 1: log likelihood = -367.05934 Iteration 2: log likelihood = -365.62414 Iteration 3: log likelihood = -365.61898 Iteration 4: log likelihood = -365.61898 Logistic regression Number of obs = 702 LR chi2(5) = 98.30 Prob > chi2 = 0.0000 Log likelihood = -365.61898 Pseudo R2 = 0.1185 ------------------------------------------------------------------------------ hp2hmcare | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0710046 .0109202 6.50 0.000 .0496014 .0924077 shrelaw2 | .0003841 .0027815 0.14 0.890 -.0050675 .0058356 avgcumdosew2 | -.3402694 .6925068 -0.49 0.623 -1.697558 1.017019 ageXd2 | .0050687 .011025 0.46 0.646 -.01654 .0266774 shrelaw2Xd2 | -.0002527 .0013833 -0.18 0.855 -.0029639 .0024584 _cons | -4.574253 .6232068 -7.34 0.000 -5.795716 -3.35279 ------------------------------------------------------------------------------ 501 . 502 . 503 . scalar MainEffhmcarew2 = "age" 504 . scalar hmcareModFw2 = "none" 505 . 506 . 507 . title4 "Mediator relationships for home care are tested below" ------------------------------------------------------------------------------- Mediator relationships for home care are tested below ------------------------------------------------------------------------------- 508 . 509 . 510 . 511 . 512 . * age and illw2 are a female mediators of dose - home care impact 513 . 514 . * age is a male and female mediator with impact on home care 515 . glm age avgcumdosew2 if gender==1, fam(gaussian) link(identity) Iteration 0: log likelihood = -1330.6004 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = 147.6853 Deviance = 49917.64009 (1/df) Deviance = 147.6853 Pearson = 49917.64009 (1/df) Pearson = 147.6853 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 7.838826 Log likelihood = -1330.6004 BIC = 47947.46 ------------------------------------------------------------------------------ | OIM age | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew2 | .5832314 .2635871 2.21 0.027 .0666101 1.099853 _cons | 48.62133 .7061562 68.85 0.000 47.23729 50.00537 ------------------------------------------------------------------------------ 516 . 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.) 517 . 518 . glm age avgcumdosew2 if gender==1, fam(gaussian) link(identity) Iteration 0: log likelihood = -1330.6004 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = 147.6853 Deviance = 49917.64009 (1/df) Deviance = 147.6853 Pearson = 49917.64009 (1/df) Pearson = 147.6853 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 7.838826 Log likelihood = -1330.6004 BIC = 47947.46 ------------------------------------------------------------------------------ | OIM age | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew2 | .5832314 .2635871 2.21 0.027 .0666101 1.099853 _cons | 48.62133 .7061562 68.85 0.000 47.23729 50.00537 ------------------------------------------------------------------------------ 519 . glm hp2hmcare age avgcumdosew2 if gender==1 , fam(binomial) irls scale(dev) l > ink(probit) Iteration 1: deviance = 320.7515 Iteration 2: deviance = 319.9643 Iteration 3: deviance = 319.9634 Iteration 4: deviance = 319.9634 Generalized linear models No. of obs = 340 Optimization : MQL Fisher scoring Residual df = 337 (IRLS EIM) Scale parameter = 1 Deviance = 319.9634434 (1/df) Deviance = .9494464 Pearson = 341.5433726 (1/df) Pearson = 1.013482 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1644.391 ------------------------------------------------------------------------------ | EIM hp2hmcare | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0327156 .0064569 5.07 0.000 .0200602 .0453709 avgcumdosew2 | -.0082929 .0299073 -0.28 0.782 -.0669102 .0503243 _cons | -2.484061 .3439022 -7.22 0.000 -3.158097 -1.810025 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 520 . 521 . glm radhlw2 avgcumdosew2 if gender==1, fam(gaussian) link(identity) Iteration 0: log likelihood = -1693.4076 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = 1247.933 Deviance = 421801.4584 (1/df) Deviance = 1247.933 Pearson = 421801.4584 (1/df) Pearson = 1247.933 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 9.972986 Log likelihood = -1693.407647 BIC = 419831.3 ------------------------------------------------------------------------------ | OIM radhlw2 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew2 | 1.220373 .766216 1.59 0.111 -.2813831 2.722128 _cons | 45.63198 2.052711 22.23 0.000 41.60874 49.65522 ------------------------------------------------------------------------------ 522 . glm hp2hmcare radhlw2 if gender==1 , fam(binomial) irls scale(dev) link(probi > t) Iteration 1: deviance = 320.2142 Iteration 2: deviance = 319.4143 Iteration 3: deviance = 319.4134 Iteration 4: deviance = 319.4134 Generalized linear models No. of obs = 340 Optimization : MQL Fisher scoring Residual df = 338 (IRLS EIM) Scale parameter = 1 Deviance = 319.4134212 (1/df) Deviance = .9450101 Pearson = 343.7631942 (1/df) Pearson = 1.017051 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1650.77 ------------------------------------------------------------------------------ | EIM hp2hmcare | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- radhlw2 | .0113273 .0022041 5.14 0.000 .0070074 .0156472 _cons | -1.415444 .1449647 -9.76 0.000 -1.69957 -1.131318 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 523 . 524 . * age is a female mediator wrt dose home care impact 525 . glm age avgcumdosew2 if gender==2, fam(gaussian) link(identity) Iteration 0: log likelihood = -1406.9403 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = 136.9184 Deviance = 49427.52828 (1/df) Deviance = 136.9184 Pearson = 49427.52828 (1/df) Pearson = 136.9184 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 7.762756 Log likelihood = -1406.940271 BIC = 47299.65 ------------------------------------------------------------------------------ | OIM age | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew2 | 1.502324 .4454009 3.37 0.001 .6293547 2.375294 _cons | 48.86944 .7323225 66.73 0.000 47.43412 50.30477 ------------------------------------------------------------------------------ 526 . 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.) 527 . 528 . glm age avgcumdosew2 if gender==2, fam(gaussian) link(identity) Iteration 0: log likelihood = -1406.9403 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = 136.9184 Deviance = 49427.52828 (1/df) Deviance = 136.9184 Pearson = 49427.52828 (1/df) Pearson = 136.9184 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 7.762756 Log likelihood = -1406.940271 BIC = 47299.65 ------------------------------------------------------------------------------ | OIM age | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew2 | 1.502324 .4454009 3.37 0.001 .6293547 2.375294 _cons | 48.86944 .7323225 66.73 0.000 47.43412 50.30477 ------------------------------------------------------------------------------ 529 . glm hp2hmcare age avgcumdosew2 ageXd2 if gender==2, fam(binomial) irls scale( > dev) link(probit) Iteration 1: deviance = 390.9185 Iteration 2: deviance = 390.7726 Iteration 3: deviance = 390.7715 Iteration 4: deviance = 390.7715 Iteration 5: deviance = 390.7715 Generalized linear models No. of obs = 363 Optimization : MQL Fisher scoring Residual df = 359 (IRLS EIM) Scale parameter = 1 Deviance = 390.7715032 (1/df) Deviance = 1.0885 Pearson = 373.6939231 (1/df) Pearson = 1.04093 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1725.319 ------------------------------------------------------------------------------ | EIM hp2hmcare | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0523417 .0088275 5.93 0.000 .0350401 .0696433 avgcumdosew2 | -.3483044 .5012362 -0.69 0.487 -1.330709 .6341005 ageXd2 | .00433 .0082234 0.53 0.599 -.0117875 .0204474 _cons | -2.989983 .4864231 -6.15 0.000 -3.943355 -2.036611 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 530 . 531 . glm radhlw2 avgcumdosew2 if gender==2, fam(gaussian) link(identity) Iteration 0: log likelihood = -1791.2233 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = 1137.567 Deviance = 410661.5604 (1/df) Deviance = 1137.567 Pearson = 410661.5604 (1/df) Pearson = 1137.567 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 9.880018 Log likelihood = -1791.223306 BIC = 408533.7 ------------------------------------------------------------------------------ | OIM radhlw2 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew2 | 3.302288 1.283833 2.57 0.010 .7860214 5.818555 _cons | 56.95167 2.110863 26.98 0.000 52.81445 61.08888 ------------------------------------------------------------------------------ 532 . glm hp2hmcare radhlw2 if gender==2 , fam(binomial) irls scale(dev) link(probi > t) Iteration 1: deviance = 465.9397 Iteration 2: deviance = 465.344 Iteration 3: deviance = 465.3439 Iteration 4: deviance = 465.3439 Generalized linear models No. of obs = 363 Optimization : MQL Fisher scoring Residual df = 361 (IRLS EIM) Scale parameter = 1 Deviance = 465.3438602 (1/df) Deviance = 1.289041 Pearson = 362.9626143 (1/df) Pearson = 1.005437 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1662.536 ------------------------------------------------------------------------------ | EIM hp2hmcare | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- radhlw2 | .0029148 .0022776 1.28 0.201 -.0015493 .0073789 _cons | -.5772317 .1586961 -3.64 0.000 -.8882703 -.266193 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 533 . 534 . scalar hmcareMedMw2 = "age " 535 . scalar hmcareMedFw2 = "age " 536 . set more off 537 . scalar list MainEffhmcareMw2 = b4 MainEffwkFw2 = age MainEffwkMw2 = workM: age ProbsocMedFw2 = age radhlw2 ProbsocMedMw2 = age ProbsocModFw2 = none MainEffProbSocFw2 = age avgcomdosew2 radhlw2 avgcumodsew2 b4 SigDoseProbsocFw2 = yes ProbSocModMw2 = none SigDoseProbsocMw2 = no PrbsocModMw2 = none MainEffPrbsocMw2 = age radhlw2 shjobw2 SigdoseMw2 = none hmcareMedFw2 = age hmcareMedMw2 = age hmcareModFw2 = none MainEffhmcarew2 = age SigdoseHmcareFw2 = no hmcareModMw2 = none SigDoseHmcareMw2 = no wkMedFw2 = radhlw2 age bf40 bf4m bf1 NameMedMw2 = age ageXillw2 NumModMw2 = none SigDosehmcareMw2 = no SigDoseWKMw2 = no WkMedFw2 = age bf4 WkMedMw2 = age ageXillw2 WkModFw2 = none WKModMw2 = none SigDoseWkMw2 = no SigDoseWkFw2 = no SigDoseFw2 = no wkModFw2 = none wkModMw2 = none 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 538 . 539 . * conclusion "age & illw2 are main effects as possible male & female mediator > s" 540 . * conclusion title "their interaction is not a mediator" 541 . 542 . title4 "2. summary matrix construction for H1 pt 2 wave 2 dose=>Home care imp > act" ------------------------------------------------------------------------------- 2. summary matrix construction for H1 pt 2 wave 2 dose=>Home care impact ------------------------------------------------------------------------------- 543 . set more off 544 . matrix define hmcrMw2 = J(1,8, 0) 545 . matrix define hmcrFw2 = J(1,8, 0) 546 . matrix colnames hmcrMw2= hypnum ptnum wave gender medsig numMAsig numModsig > /// > numMed 547 . matrix colnames hmcrFw2= hypnum ptnum wave gender medsig numMAsig numModsig > /// > numMed 548 . matrix rownames hmcrMw2 = hmcareM 549 . matrix rownames hmcrFw2 = hmcareF 550 . matrix define hmcrFw2= (1, 2, 3, 2, 0 ,1, 0 , 1 ) 551 . matrix define hmcrMw2= (1, 2, 3, 1, 0 , 1, 0 , 1 ) 552 . matrix define H1pt2w2 = ( wkMw2 \ wkFw2 \ hmcrMw2 \ hmcrFw2) 553 . matrix colnames H1pt2w2 = hypnum ptnum wave gender medsig numMAsig numMo > dsig numMed 554 . matrix colnames H1pt2w2 = hypnum ptnum wave gender medsig numMAsig numMo > dsig numMed 555 . matrix rownames H1pt2w2 = wkMw2 wkFw2 hmcrMw2 hmcrFw2 556 . matlist H1pt2w2 | hypnum ptnum wave gender medsig numMAsig > numModsig numMed -------------+----------------------------------------------------------------- ----------------------- wkMw2 | 1 2 2 1 0 2 > 0 2 wkFw2 | 1 2 2 2 0 1 > 0 2 hmcrMw2 | 1 2 3 1 0 1 > 0 1 hmcrFw2 | 1 2 3 2 0 1 > 0 1 557 . 558 . * see scalar list for names of variables 559 . scalar list MainEffhmcareMw2 = b4 MainEffwkFw2 = age MainEffwkMw2 = workM: age ProbsocMedFw2 = age radhlw2 ProbsocMedMw2 = age ProbsocModFw2 = none MainEffProbSocFw2 = age avgcomdosew2 radhlw2 avgcumodsew2 b4 SigDoseProbsocFw2 = yes ProbSocModMw2 = none SigDoseProbsocMw2 = no PrbsocModMw2 = none MainEffPrbsocMw2 = age radhlw2 shjobw2 SigdoseMw2 = none hmcareMedFw2 = age hmcareMedMw2 = age hmcareModFw2 = none MainEffhmcarew2 = age SigdoseHmcareFw2 = no hmcareModMw2 = none SigDoseHmcareMw2 = no wkMedFw2 = radhlw2 age bf40 bf4m bf1 NameMedMw2 = age ageXillw2 NumModMw2 = none SigDosehmcareMw2 = no SigDoseWKMw2 = no WkMedFw2 = age bf4 WkMedMw2 = age ageXillw2 WkModFw2 = none WKModMw2 = none SigDoseWkMw2 = no SigDoseWkFw2 = no SigDoseFw2 = no wkModFw2 = none wkModMw2 = none 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 560 . 561 . * X * missing the number of main effects in the trimmed models 562 . 563 . //////////////////////////////////////////////////////////////////////// > *--------- Chunk 4 Dose social problem impact relationship HP2probsoc 564 . *---------------------------------------------------------------------------- > --- 565 . * General model for all part 2 of Nottingham Health Profile 566 . 567 . title "3. H1 part 2 wave 2 Dose - HP2probsoc impact tested" ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** 3. H1 part 2 wave 2 Dose - HP2probsoc impact tested ***** ***** ***** ***** ***** ***** 16 Jun 2012 21:54:31 ***** ******************************************************************************* ******************************************************************************* 568 . 569 . forvalues j = 2/2 { 2. set more off 3. 570 . des age educ1-educ7 marrw`j'1-marrw`j'6 inc1w`j'-inc4w`j' /// > bf1 bf4 bf9 bf11 bf4m bf15m bf30 bf40 4. 571 . 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. 572 . 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 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 marrw21 byte %8.0g marrw2==1. single marrw22 byte %8.0g marrw2==2. cohabitating marrw23 byte %8.0g marrw2==3. married marrw24 byte %8.0g marrw2==4. separated marrw25 byte %8.0g marrw2==5. divorced marrw26 byte %8.0g marrw2==6. widowed inc1w2 double %15.0g LABJ Income is not sufficient for basic neccessities in 1996 inc2w2 double %15.0g LABJ Income is just sufficient for basic neccessities in 1996 inc3w2 double %15.0g LABJ Income is sufficient for basics plus extra purchases/savings in 1996 inc4w2 double %15.0g LABJ Income allows to comfortably afford luxury items in 1996 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= 2 chunk 4 H1 test:Gender= 1 model Wave = 2 for hp2hmcare ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Full Nottingham Part 2 subscale models for male and then females ***** ***** ***** ***** ***** ***** 16 Jun 2012 21:54:31 ***** ******************************************************************************* ******************************************************************************* i.educ _Ieduc_1-8 (naturally coded; _Ieduc_1 omitted) note: _Ieduc_4 != 0 predicts failure perfectly _Ieduc_4 dropped and 12 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: occ6w2 != 0 predicts failure perfectly occ6w2 dropped and 4 obs not used note: occ7w2 != 0 predicts failure perfectly occ7w2 dropped and 14 obs not used note: occ8w2 != 0 predicts failure perfectly occ8w2 dropped and 43 obs not used note: marrw22 != 0 predicts failure perfectly marrw22 dropped and 7 obs not used note: marrw25 != 0 predicts failure perfectly marrw25 dropped and 4 obs not used note: marrw26 != 0 predicts failure perfectly marrw26 dropped and 1 obs not used note: inc4w2 != 0 predicts failure perfectly inc4w2 dropped and 9 obs not used note: dvcew2 != 0 predicts failure perfectly dvcew2 dropped and 3 obs not used note: sepaw2 != 0 predicts failure perfectly sepaw2 dropped and 1 obs not used note: _Ieduc_6 omitted because of collinearity note: bf15 omitted because of collinearity Logistic regression Number of obs = 228 LR chi2(34) = 103.91 Prob > chi2 = 0.0000 Log likelihood = -52.36582 Pseudo R2 = 0.4980 ------------------------------------------------------------------------------ HP2probsoc | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0906854 .0339814 2.67 0.008 .0240831 .1572876 _Ieduc_2 | -.0346926 1.161856 -0.03 0.976 -2.311888 2.242503 _Ieduc_3 | -.6886648 .7207042 -0.96 0.339 -2.101219 .7238895 _Ieduc_4 | 0 (omitted) _Ieduc_5 | .9759744 1.063631 0.92 0.359 -1.108703 3.060652 _Ieduc_6 | 0 (omitted) _Ieduc_7 | 0 (omitted) _Ieduc_8 | 0 (omitted) occ1w2 | -.9172264 10.67202 -0.09 0.932 -21.83401 19.99955 occ2w2 | -.7254984 10.66823 -0.07 0.946 -21.63485 20.18385 occ3w2 | -.6714679 10.68886 -0.06 0.950 -21.62126 20.27832 occ4w2 | -2.239171 10.70842 -0.21 0.834 -23.22728 18.74894 occ5w2 | -.9195542 10.71455 -0.09 0.932 -21.91968 20.08057 occ6w2 | 0 (omitted) occ7w2 | 0 (omitted) occ8w2 | 0 (omitted) marrw21 | 11.0684 1379.375 0.01 0.994 -2692.457 2714.594 marrw22 | 0 (omitted) marrw23 | 8.945925 1379.375 0.01 0.995 -2694.579 2712.471 marrw25 | 0 (omitted) marrw26 | 0 (omitted) inc1w2 | .3641243 10.76623 0.03 0.973 -20.7373 21.46555 inc2w2 | 1.742499 10.67327 0.16 0.870 -19.17672 22.66172 inc3w2 | 3.371881 10.68463 0.32 0.752 -17.56961 24.31337 inc4w2 | 0 (omitted) radhlw2 | .0085407 .0114129 0.75 0.454 -.0138281 .0309095 havmil | -.0006807 .0078287 -0.09 0.931 -.0160246 .0146632 avgcumdosew2 | .099739 .0947343 1.05 0.292 -.0859367 .2854148 bf1 | .0048596 .0179991 0.27 0.787 -.0304181 .0401372 bf4 | -.3368708 .0845017 -3.99 0.000 -.5024911 -.1712504 bf6 | .0294921 .0150976 1.95 0.051 -.0000987 .0590829 bf7 | .2107792 .1280115 1.65 0.100 -.0401186 .4616771 bf14 | -.0000508 .0001111 -0.46 0.648 -.0002685 .0001669 bf15 | 0 (omitted) bf40 | .3587504 .202109 1.78 0.076 -.0373759 .7548768 deaw2 | -.2425986 .5320938 -0.46 0.648 -1.285483 .8002861 dvcew2 | 0 (omitted) sepaw2 | 0 (omitted) accdw2 | -.0583869 .772113 -0.08 0.940 -1.571701 1.454927 movew2 | .534895 .8346364 0.64 0.522 -1.100962 2.170752 illw2 | .3093012 .430894 0.72 0.473 -.5352355 1.153838 shfamw2 | -.0138199 .0107438 -1.29 0.198 -.0348774 .0072375 shhlw2 | -.0108054 .0127581 -0.85 0.397 -.0358108 .0141999 shjobw2 | .024033 .0121387 1.98 0.048 .0002416 .0478244 shrelaw2 | -.0263531 .0111814 -2.36 0.018 -.0482683 -.0044379 suprtw2 | .0130386 .0099595 1.31 0.190 -.0064816 .0325589 suchrw2 | .0121677 .0099924 1.22 0.223 -.007417 .0317524 havmilsq | 4.68e-06 9.92e-06 0.47 0.637 -.0000148 .0000241 _cons | -18.63366 1379.378 -0.01 0.989 -2722.164 2684.897 ------------------------------------------------------------------------------ Logistic model for HP2probsoc -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 27 4 | 31 - | 12 185 | 197 -----------+--------------------------+----------- Total | 39 189 | 228 Classified + if predicted Pr(D) >= .5 True D defined as HP2probsoc != 0 -------------------------------------------------- Sensitivity Pr( +| D) 69.23% Specificity Pr( -|~D) 97.88% Positive predictive value Pr( D| +) 87.10% Negative predictive value Pr(~D| -) 93.91% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 2.12% False - rate for true D Pr( -| D) 30.77% False + rate for classified + Pr(~D| +) 12.90% False - rate for classified - Pr( D| -) 6.09% -------------------------------------------------- Correctly classified 92.98% -------------------------------------------------- Logistic model for HP2probsoc, goodness-of-fit test number of observations = 228 number of covariate patterns = 228 Pearson chi2(193) = 730.19 Prob > chi2 = 0.0000 Measures of Fit for logistic of HP2probsoc Log-Lik Intercept Only: -104.322 Log-Lik Full Model: -52.366 D(179): 104.732 LR(34): 103.912 Prob > LR: 0.000 McFadden's R2: 0.498 McFadden's Adj R2: 0.028 Maximum Likelihood R2: 0.366 Cragg & Uhler's R2: 0.611 McKelvey and Zavoina's R2: 0.779 Efron's R2: 0.554 Variance of y*: 14.912 Variance of error: 3.290 Count R2: 0.930 Adj Count R2: 0.590 AIC: 0.889 AIC*n: 202.732 BIC: -867.121 BIC': 80.686 Full main model for HP2probsoc for wave= 2 chunk 4 H1 test:Gender= 2 model Wave = 2 for HP2probsoc ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Full Nottingham Part 2 subscale models for male and then females ***** ***** ***** ***** ***** ***** 16 Jun 2012 21:54:32 ***** ******************************************************************************* ******************************************************************************* i.educ _Ieduc_1-8 (naturally coded; _Ieduc_1 omitted) note: occ6w2 != 0 predicts failure perfectly occ6w2 dropped and 9 obs not used note: _Ieduc_8 omitted because of collinearity note: marrw26 omitted because of collinearity note: bf15 omitted because of collinearity Logistic regression Number of obs = 353 LR chi2(44) = 173.44 Prob > chi2 = 0.0000 Log likelihood = -93.198778 Pseudo R2 = 0.4820 ------------------------------------------------------------------------------ HP2probsoc | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .1045505 .025349 4.12 0.000 .0548673 .1542337 _Ieduc_2 | -12.29812 1030.765 -0.01 0.990 -2032.56 2007.964 _Ieduc_3 | -12.54704 1030.765 -0.01 0.990 -2032.809 2007.715 _Ieduc_4 | -11.69817 1030.765 -0.01 0.991 -2031.96 2008.564 _Ieduc_5 | -11.74738 1030.765 -0.01 0.991 -2032.009 2008.515 _Ieduc_6 | -12.89754 1030.765 -0.01 0.990 -2033.159 2007.364 _Ieduc_7 | -14.11644 1030.817 -0.01 0.989 -2034.481 2006.248 _Ieduc_8 | 0 (omitted) occ1w2 | -1.104757 3.60974 -0.31 0.760 -8.179718 5.970203 occ2w2 | -1.202019 3.652886 -0.33 0.742 -8.361544 5.957506 occ3w2 | .0703933 3.628444 0.02 0.985 -7.041227 7.182014 occ4w2 | -1.52192 3.712086 -0.41 0.682 -8.797475 5.753635 occ5w2 | -2.24588 3.84541 -0.58 0.559 -9.782745 5.290985 occ6w2 | 0 (omitted) occ7w2 | -.4840598 3.61697 -0.13 0.894 -7.573191 6.605072 occ8w2 | 2.167215 3.89814 0.56 0.578 -5.472999 9.807428 marrw21 | -.4201784 1.629029 -0.26 0.796 -3.613016 2.772659 marrw22 | 1.086175 1.72569 0.63 0.529 -2.296115 4.468466 marrw23 | .7750978 .9250885 0.84 0.402 -1.038042 2.588238 marrw25 | .532399 1.287582 0.41 0.679 -1.991215 3.056013 marrw26 | 0 (omitted) inc1w2 | .0603839 3.624166 0.02 0.987 -7.042851 7.163619 inc2w2 | .8383333 3.595272 0.23 0.816 -6.20827 7.884937 inc3w2 | .536243 3.60018 0.15 0.882 -6.519981 7.592467 inc4w2 | .2312155 3.842475 0.06 0.952 -7.299898 7.762329 radhlw2 | .0147911 .0081819 1.81 0.071 -.0012451 .0308272 havmil | .0022418 .0072934 0.31 0.759 -.0120531 .0165366 avgcumdosew2 | .4925829 .2091227 2.36 0.018 .0827098 .9024559 bf1 | -.0161664 .0113442 -1.43 0.154 -.0384006 .0060677 bf4 | -.2331375 .0505589 -4.61 0.000 -.332231 -.1340439 bf6 | .0021871 .0094776 0.23 0.817 -.0163887 .0207629 bf7 | -.0615381 .1064342 -0.58 0.563 -.2701454 .1470692 bf14 | 8.31e-06 .0000929 0.09 0.929 -.0001737 .0001903 bf15 | 0 (omitted) bf40 | -.005756 .0971846 -0.06 0.953 -.1962344 .1847223 deaw2 | -.0331928 .2378427 -0.14 0.889 -.499356 .4329704 dvcew2 | 1.930249 1.72923 1.12 0.264 -1.45898 5.319477 sepaw2 | -1.211648 2.172861 -0.56 0.577 -5.470378 3.047082 accdw2 | -.6584952 .7729357 -0.85 0.394 -2.173421 .8564309 movew2 | -.3688091 .9599148 -0.38 0.701 -2.250208 1.512589 illw2 | .0217672 .2703514 0.08 0.936 -.5081118 .5516462 shfamw2 | -.0185511 .0084341 -2.20 0.028 -.0350816 -.0020206 shhlw2 | .0005321 .0080879 0.07 0.948 -.0153199 .0163841 shjobw2 | -.0024716 .0076938 -0.32 0.748 -.0175512 .0126079 shrelaw2 | -.0052827 .0086543 -0.61 0.542 -.0222447 .0116794 suprtw2 | .0005602 .0066528 0.08 0.933 -.012479 .0135994 suchrw2 | -.0036935 .00718 -0.51 0.607 -.017766 .0103791 havmilsq | -8.46e-06 .0000154 -0.55 0.582 -.0000386 .0000217 _cons | 6.917383 1030.768 0.01 0.995 -2013.35 2027.185 ------------------------------------------------------------------------------ Note: 3 failures and 0 successes completely determined. Logistic model for HP2probsoc -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 53 11 | 64 - | 20 269 | 289 -----------+--------------------------+----------- Total | 73 280 | 353 Classified + if predicted Pr(D) >= .5 True D defined as HP2probsoc != 0 -------------------------------------------------- Sensitivity Pr( +| D) 72.60% Specificity Pr( -|~D) 96.07% Positive predictive value Pr( D| +) 82.81% Negative predictive value Pr(~D| -) 93.08% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 3.93% False - rate for true D Pr( -| D) 27.40% False + rate for classified + Pr(~D| +) 17.19% False - rate for classified - Pr( D| -) 6.92% -------------------------------------------------- Correctly classified 91.22% -------------------------------------------------- Logistic model for HP2probsoc, goodness-of-fit test number of observations = 353 number of covariate patterns = 353 Pearson chi2(308) = 419.21 Prob > chi2 = 0.0000 Measures of Fit for logistic of HP2probsoc Log-Lik Intercept Only: -179.919 Log-Lik Full Model: -93.199 D(304): 186.398 LR(44): 173.440 Prob > LR: 0.000 McFadden's R2: 0.482 McFadden's Adj R2: 0.210 Maximum Likelihood R2: 0.388 Cragg & Uhler's R2: 0.607 McKelvey and Zavoina's R2: 0.892 Efron's R2: 0.528 Variance of y*: 30.526 Variance of error: 3.290 Count R2: 0.912 Adj Count R2: 0.575 AIC: 0.806 AIC*n: 284.398 BIC: -1597.009 BIC': 84.685 573 . 574 . *-----Chunk 4 dose3 social problem impact--------------no sig dose main effec > t-- 575 . title4 "Male trimmed models of dose and HP2probsoc relationship in Wave 2" ------------------------------------------------------------------------------- Male trimmed models of dose and HP2probsoc relationship in Wave 2 ------------------------------------------------------------------------------- 576 . * male models 577 . forvalues j = 2/2 { 2. set more off 3. local w2bf bf1 bf4 bf6 bf7 bf14 bf15 bf40 4. title4 "trimmed HP2probsoc main effects models Wave 2 for H1 part 2 with d > ose ns" 5. title4 "Wave 2 dose HP2probsoc relationship but avgcumdosew`j': Dose not s > ignif" 6. sw, pr(.1): logit HP2probsoc age radhlw2 accdw`j' `w`j'bf' shjobw`j' illw > `j' havmilsq /// > avgcumdosew`j' shrelaw`j' if gender==1 7. estat class 8. estat gof 9. fitstat 10. } ------------------------------------------------------------------------------- trimmed HP2probsoc main effects models Wave 2 for H1 part 2 with dose ns ------------------------------------------------------------------------------- ------------------------------------------------------------------------------- Wave 2 dose HP2probsoc relationship but avgcumdosew2: Dose not signif ------------------------------------------------------------------------------- note: bf15 dropped because of collinearity begin with full model p = 0.9688 >= 0.1000 removing havmilsq p = 0.8362 >= 0.1000 removing bf40 p = 0.7569 >= 0.1000 removing bf1 p = 0.4563 >= 0.1000 removing bf6 p = 0.6327 >= 0.1000 removing bf7 p = 0.3860 >= 0.1000 removing bf14 p = 0.4368 >= 0.1000 removing illw2 p = 0.3539 >= 0.1000 removing accdw2 p = 0.2376 >= 0.1000 removing radhlw2 p = 0.1378 >= 0.1000 removing avgcumdosew2 Logistic regression Number of obs = 332 LR chi2(4) = 82.60 Prob > chi2 = 0.0000 Log likelihood = -78.833798 Pseudo R2 = 0.3438 ------------------------------------------------------------------------------ HP2probsoc | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0571104 .0201616 2.83 0.005 .0175943 .0966265 bf4 | -.2386201 .0424268 -5.62 0.000 -.321775 -.1554652 shjobw2 | .0183809 .0063016 2.92 0.004 .0060301 .0307318 shrelaw2 | -.0143444 .0067621 -2.12 0.034 -.0275978 -.0010909 _cons | -3.38883 1.393067 -2.43 0.015 -6.11919 -.6584689 ------------------------------------------------------------------------------ Logistic model for HP2probsoc -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 18 6 | 24 - | 21 287 | 308 -----------+--------------------------+----------- Total | 39 293 | 332 Classified + if predicted Pr(D) >= .5 True D defined as HP2probsoc != 0 -------------------------------------------------- Sensitivity Pr( +| D) 46.15% Specificity Pr( -|~D) 97.95% Positive predictive value Pr( D| +) 75.00% Negative predictive value Pr(~D| -) 93.18% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 2.05% False - rate for true D Pr( -| D) 53.85% False + rate for classified + Pr(~D| +) 25.00% False - rate for classified - Pr( D| -) 6.82% -------------------------------------------------- Correctly classified 91.87% -------------------------------------------------- Logistic model for HP2probsoc, goodness-of-fit test number of observations = 332 number of covariate patterns = 315 Pearson chi2(310) = 309.74 Prob > chi2 = 0.4935 Measures of Fit for logit of HP2probsoc Log-Lik Intercept Only: -120.135 Log-Lik Full Model: -78.834 D(327): 157.668 LR(4): 82.603 Prob > LR: 0.000 McFadden's R2: 0.344 McFadden's Adj R2: 0.302 Maximum Likelihood R2: 0.220 Cragg & Uhler's R2: 0.428 McKelvey and Zavoina's R2: 0.483 Efron's R2: 0.343 Variance of y*: 6.358 Variance of error: 3.290 Count R2: 0.919 Adj Count R2: 0.308 AIC: 0.505 AIC*n: 167.668 BIC: -1740.612 BIC': -59.383 578 . 579 . 580 . scalar SigdoseMw2 = "none" 581 . scalar MainEffPrbsocMw2 = "age bf4 shjobw2 shrelaw2" 582 . 583 . foreach var in age bf4 shjobw2 shrelaw2 { 2. cap gen `var'Xd2 = `var'*avgcumdosew2 3. } 584 . 585 . 586 . forvalues j = 2/2 { 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 2 ***** ***** for H1 part 2 with dose ns ***** ***** ***** ***** ***** ***** 16 Jun 2012 21:54:51 ***** ******************************************************************************* ******************************************************************************* ------------------------------------------------------------------------------- title2: Wave `j dose HP2work relationship but avgcumdosew2: Dose not signif Date and time: 16 Jun 2012 21:54:51 Working directory: /Users/robertyaffee/ > Documents/data/research/chwk/phase3/Htests/h1tests/h1pt2 Stata data file: chwide16june2012.dta > has 2383 variables and 703 observations Wave `j dose HP2work relationship but avgcumdosew2: Dose not signif ------------------------------------------------------------------------------- 587 . 588 . scalar MainEffPrbsocMw2 = "age radhlw2 shjobw2" 589 . 590 . foreach var in bf4 age radhlw2 shjobw2 shrelaw2 { 2. cap gen `var'Xd2= `var'*avgcumdosew2 3. } 591 . 592 . forvalues j = 2/2 { 2. title "Main effects Dose ProbSoc model for males" 3. logit HP2probsoc age avgcumdosew2 radhlw2 shjobw`j' /// > ageXd2 radhlw2Xd2 shjobw2Xd2 shrelaw2Xd2 if gender==1 4. estat class 5. estat gof 6. fitstat 7. } ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Main effects Dose ProbSoc model for males ***** ***** ***** ***** ***** ***** 16 Jun 2012 21:54:51 ***** ******************************************************************************* ******************************************************************************* Iteration 0: log likelihood = -125.15243 Iteration 1: log likelihood = -101.41189 Iteration 2: log likelihood = -96.810289 Iteration 3: log likelihood = -95.749548 Iteration 4: log likelihood = -95.67801 Iteration 5: log likelihood = -95.677199 Iteration 6: log likelihood = -95.677198 Logistic regression Number of obs = 340 LR chi2(8) = 58.95 Prob > chi2 = 0.0000 Log likelihood = -95.677198 Pseudo R2 = 0.2355 ------------------------------------------------------------------------------ HP2probsoc | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0782755 .0262825 2.98 0.003 .0267626 .1297883 avgcumdosew2 | .150258 2.58999 0.06 0.954 -4.926029 5.226545 radhlw2 | .0206117 .0087097 2.37 0.018 .003541 .0376824 shjobw2 | .0092276 .0086239 1.07 0.285 -.0076749 .0261301 ageXd2 | -.0191074 .0289443 -0.66 0.509 -.0758372 .0376225 radhlw2Xd2 | .0023073 .0094888 0.24 0.808 -.0162905 .0209051 shjobw2Xd2 | .0103018 .0133884 0.77 0.442 -.0159389 .0365424 shrelaw2Xd2 | -.0019564 .0070152 -0.28 0.780 -.015706 .0117931 _cons | -7.817242 2.087277 -3.75 0.000 -11.90823 -3.726255 ------------------------------------------------------------------------------ Note: 1 failure and 0 successes completely determined. Logistic model for HP2probsoc -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 10 1 | 11 - | 31 298 | 329 -----------+--------------------------+----------- Total | 41 299 | 340 Classified + if predicted Pr(D) >= .5 True D defined as HP2probsoc != 0 -------------------------------------------------- Sensitivity Pr( +| D) 24.39% Specificity Pr( -|~D) 99.67% Positive predictive value Pr( D| +) 90.91% Negative predictive value Pr(~D| -) 90.58% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 0.33% False - rate for true D Pr( -| D) 75.61% False + rate for classified + Pr(~D| +) 9.09% False - rate for classified - Pr( D| -) 9.42% -------------------------------------------------- Correctly classified 90.59% -------------------------------------------------- Logistic model for HP2probsoc, goodness-of-fit test number of observations = 340 number of covariate patterns = 328 Pearson chi2(319) = 362.02 Prob > chi2 = 0.0486 Measures of Fit for logit of HP2probsoc Log-Lik Intercept Only: -125.152 Log-Lik Full Model: -95.677 D(331): 191.354 LR(8): 58.950 Prob > LR: 0.000 McFadden's R2: 0.236 McFadden's Adj R2: 0.164 Maximum Likelihood R2: 0.159 Cragg & Uhler's R2: 0.305 McKelvey and Zavoina's R2: 0.554 Efron's R2: 0.223 Variance of y*: 7.370 Variance of error: 3.290 Count R2: 0.906 Adj Count R2: 0.220 AIC: 0.616 AIC*n: 209.354 BIC: -1738.027 BIC': -12.319 593 . 594 . scalar PrbsocModMw2 = "none" 595 . 596 . forvalues j = 2/2 { 2. logit HP2probsoc age radhlw2 shjobw`j' /// > avgcumdosew`j' /// > shjobw2Xd2 if gender==1 3. estat class 4. estat gof 5. fitstat 6. } Iteration 0: log likelihood = -125.15243 Iteration 1: log likelihood = -102.40367 Iteration 2: log likelihood = -97.802085 Iteration 3: log likelihood = -96.367187 Iteration 4: log likelihood = -96.245667 Iteration 5: log likelihood = -96.239265 Iteration 6: log likelihood = -96.239247 Iteration 7: log likelihood = -96.239247 Logistic regression Number of obs = 340 LR chi2(5) = 57.83 Prob > chi2 = 0.0000 Log likelihood = -96.239247 Pseudo R2 = 0.2310 ------------------------------------------------------------------------------ HP2probsoc | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0645913 .0169521 3.81 0.000 .0313658 .0978168 radhlw2 | .0222475 .0060296 3.69 0.000 .0104297 .0340653 shjobw2 | .0092759 .0068028 1.36 0.173 -.0040574 .0226091 avgcumdosew2 | -.7357041 .6602672 -1.11 0.265 -2.029804 .5583958 shjobw2Xd2 | .0081692 .0068728 1.19 0.235 -.0053013 .0216397 _cons | -7.172995 1.201125 -5.97 0.000 -9.527157 -4.818833 ------------------------------------------------------------------------------ Note: 1 failure and 0 successes completely determined. Logistic model for HP2probsoc -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 10 2 | 12 - | 31 297 | 328 -----------+--------------------------+----------- Total | 41 299 | 340 Classified + if predicted Pr(D) >= .5 True D defined as HP2probsoc != 0 -------------------------------------------------- Sensitivity Pr( +| D) 24.39% Specificity Pr( -|~D) 99.33% Positive predictive value Pr( D| +) 83.33% Negative predictive value Pr(~D| -) 90.55% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 0.67% False - rate for true D Pr( -| D) 75.61% False + rate for classified + Pr(~D| +) 16.67% False - rate for classified - Pr( D| -) 9.45% -------------------------------------------------- Correctly classified 90.29% -------------------------------------------------- Logistic model for HP2probsoc, goodness-of-fit test number of observations = 340 number of covariate patterns = 327 Pearson chi2(321) = 353.15 Prob > chi2 = 0.1047 Measures of Fit for logit of HP2probsoc Log-Lik Intercept Only: -125.152 Log-Lik Full Model: -96.239 D(334): 192.478 LR(5): 57.826 Prob > LR: 0.000 McFadden's R2: 0.231 McFadden's Adj R2: 0.183 Maximum Likelihood R2: 0.156 Cragg & Uhler's R2: 0.300 McKelvey and Zavoina's R2: 0.495 Efron's R2: 0.219 Variance of y*: 6.518 Variance of error: 3.290 Count R2: 0.903 Adj Count R2: 0.195 AIC: 0.601 AIC*n: 204.478 BIC: -1754.389 BIC': -28.682 597 . scalar SigDoseProbsocMw2 = "no" 598 . * xx no signific radhwl3 by dose effect 599 . * xx for males no signif dose social problem effect 600 . * xx for males no significant moderator in dose social problem effect 601 . scalar ProbSocModMw2 = "none" 602 . * female models 603 . 604 . 605 . scalar SigDoseProbsocFw2 = "yes" 606 . scalar MainEffProbSocFw2 = "age avgcomdosew2 radhlw2 avgcumodsew2 b4" 607 . 608 . title4 "H1 pt2 wave 2 trimmed female moderator model with basis functions" ------------------------------------------------------------------------------- H1 pt2 wave 2 trimmed female moderator model with basis functions ------------------------------------------------------------------------------- 609 . forvalues j = 2/2 { 2. local w2bf bf1 bf4 bf6 bf7 bf14 bf15 bf40 3. title "trimmed HP2probsoc main effects models Wave 2 for H1 part 2 " "Dose > is signif Females" 4. title "Wave 2 dose HP2probsoc relationship but avgcumdosew`j': Dose signif > " 5. sw, pr(.1): logit HP2probsoc age radhlw2 illw`j' `w2bf' //// > shrelaw`j' avgcumdosew`j' if gender==2 6. estat class 7. estat gof 8. fitstat 9. } ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** trimmed HP2probsoc main effects models Wave 2 for H1 part 2 ***** ***** Dose is signif Females ***** ***** ***** ***** ***** ***** 16 Jun 2012 21:54:53 ***** ******************************************************************************* ******************************************************************************* ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Wave 2 dose HP2probsoc relationship but avgcumdosew2: Dose signif ***** ***** ***** ***** ***** ***** 16 Jun 2012 21:54:53 ***** ******************************************************************************* ******************************************************************************* note: bf15 dropped because of collinearity begin with full model p = 0.9211 >= 0.1000 removing illw2 p = 0.7587 >= 0.1000 removing bf14 p = 0.5303 >= 0.1000 removing bf40 p = 0.4770 >= 0.1000 removing bf7 p = 0.3763 >= 0.1000 removing bf1 p = 0.2334 >= 0.1000 removing bf6 Logistic regression Number of obs = 363 LR chi2(5) = 148.64 Prob > chi2 = 0.0000 Log likelihood = -109.2514 Pseudo R2 = 0.4049 ------------------------------------------------------------------------------ HP2probsoc | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0970773 .0185105 5.24 0.000 .0607973 .1333572 radhlw2 | .0147041 .0057226 2.57 0.010 .003488 .0259202 avgcumdosew2 | .4069203 .1523059 2.67 0.008 .1084062 .7054343 shrelaw2 | -.0147018 .005883 -2.50 0.012 -.0262323 -.0031712 bf4 | -.1790113 .0368313 -4.86 0.000 -.2511993 -.1068232 _cons | -6.193984 1.259936 -4.92 0.000 -8.663413 -3.724554 ------------------------------------------------------------------------------ Logistic model for HP2probsoc -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 45 10 | 55 - | 29 279 | 308 -----------+--------------------------+----------- Total | 74 289 | 363 Classified + if predicted Pr(D) >= .5 True D defined as HP2probsoc != 0 -------------------------------------------------- Sensitivity Pr( +| D) 60.81% Specificity Pr( -|~D) 96.54% Positive predictive value Pr( D| +) 81.82% Negative predictive value Pr(~D| -) 90.58% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 3.46% False - rate for true D Pr( -| D) 39.19% False + rate for classified + Pr(~D| +) 18.18% False - rate for classified - Pr( D| -) 9.42% -------------------------------------------------- Correctly classified 89.26% -------------------------------------------------- Logistic model for HP2probsoc, goodness-of-fit test number of observations = 363 number of covariate patterns = 362 Pearson chi2(356) = 416.51 Prob > chi2 = 0.0148 Measures of Fit for logit of HP2probsoc Log-Lik Intercept Only: -183.570 Log-Lik Full Model: -109.251 D(357): 218.503 LR(5): 148.637 Prob > LR: 0.000 McFadden's R2: 0.405 McFadden's Adj R2: 0.372 Maximum Likelihood R2: 0.336 Cragg & Uhler's R2: 0.528 McKelvey and Zavoina's R2: 0.585 Efron's R2: 0.450 Variance of y*: 7.926 Variance of error: 3.290 Count R2: 0.893 Adj Count R2: 0.473 AIC: 0.635 AIC*n: 230.503 BIC: -1885.799 BIC': -119.165 610 . 611 . foreach var in b4 shrelaw2 { 2. cap gen `var'Xd2 = `var'*avgcumdosew2 3. } 612 . 613 . * testing the female moderator model with basis functions 614 . forvalues j = 2/2 { 2. local w2bf bf1 bf4 bf6 bf7 bf14 bf15 bf40 3. title "trimmed HP2socprob main effects wv 3 for Hyp1 pt 2" "dose is signi > f for females" 4. title "Wave 2 dose HP2socprob relationship but avgcumdosew`j'" " Dose is s > ignif for females" 5. sw, pr(.1): logit HP2probsoc age radhlw2 illw`j' `w2bf' //// > shrelaw`j' avgcumdosew`j' b4Xd2 shrelaw2Xd2 /// > if gender==2 6. estat class 7. estat gof 8. fitstat 9. } ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** trimmed HP2socprob main effects wv 3 for Hyp1 pt 2 ***** ***** dose is signif for females ***** ***** ***** ***** ***** ***** 16 Jun 2012 21:55:04 ***** ******************************************************************************* ******************************************************************************* ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Wave 2 dose HP2socprob relationship but avgcumdosew2 ***** ***** Dose is signif for females ***** ***** ***** ***** ***** ***** 16 Jun 2012 21:55:04 ***** ******************************************************************************* ******************************************************************************* note: bf15 dropped because of collinearity begin with full model p = 0.8735 >= 0.1000 removing illw2 p = 0.7721 >= 0.1000 removing bf14 p = 0.5776 >= 0.1000 removing bf40 p = 0.5626 >= 0.1000 removing b4Xd2 p = 0.4854 >= 0.1000 removing shrelaw2Xd2 p = 0.4770 >= 0.1000 removing bf7 p = 0.3763 >= 0.1000 removing bf1 p = 0.2334 >= 0.1000 removing bf6 Logistic regression Number of obs = 363 LR chi2(5) = 148.64 Prob > chi2 = 0.0000 Log likelihood = -109.2514 Pseudo R2 = 0.4049 ------------------------------------------------------------------------------ HP2probsoc | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0970773 .0185105 5.24 0.000 .0607973 .1333572 radhlw2 | .0147041 .0057226 2.57 0.010 .003488 .0259202 avgcumdosew2 | .4069203 .1523059 2.67 0.008 .1084062 .7054343 shrelaw2 | -.0147018 .005883 -2.50 0.012 -.0262323 -.0031712 bf4 | -.1790113 .0368313 -4.86 0.000 -.2511993 -.1068232 _cons | -6.193984 1.259936 -4.92 0.000 -8.663413 -3.724554 ------------------------------------------------------------------------------ Logistic model for HP2probsoc -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 45 10 | 55 - | 29 279 | 308 -----------+--------------------------+----------- Total | 74 289 | 363 Classified + if predicted Pr(D) >= .5 True D defined as HP2probsoc != 0 -------------------------------------------------- Sensitivity Pr( +| D) 60.81% Specificity Pr( -|~D) 96.54% Positive predictive value Pr( D| +) 81.82% Negative predictive value Pr(~D| -) 90.58% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 3.46% False - rate for true D Pr( -| D) 39.19% False + rate for classified + Pr(~D| +) 18.18% False - rate for classified - Pr( D| -) 9.42% -------------------------------------------------- Correctly classified 89.26% -------------------------------------------------- Logistic model for HP2probsoc, goodness-of-fit test number of observations = 363 number of covariate patterns = 362 Pearson chi2(356) = 416.51 Prob > chi2 = 0.0148 Measures of Fit for logit of HP2probsoc Log-Lik Intercept Only: -183.570 Log-Lik Full Model: -109.251 D(357): 218.503 LR(5): 148.637 Prob > LR: 0.000 McFadden's R2: 0.405 McFadden's Adj R2: 0.372 Maximum Likelihood R2: 0.336 Cragg & Uhler's R2: 0.528 McKelvey and Zavoina's R2: 0.585 Efron's R2: 0.450 Variance of y*: 7.926 Variance of error: 3.290 Count R2: 0.893 Adj Count R2: 0.473 AIC: 0.635 AIC*n: 230.503 BIC: -1885.799 BIC': -119.165 615 . 616 . scalar ProbsocModFw2 = "none" 617 . 618 . 619 . title4 "H1 pt 2 wave 2 testing for mediators for males" ------------------------------------------------------------------------------- H1 pt 2 wave 2 testing for mediators for males ------------------------------------------------------------------------------- 620 . * Male mediator dose social problem response models 621 . 622 . 623 . 624 . // age is a male mediator 625 . glm age avgcumdosew2 if gender==1, fam(gaus) link(identity) Iteration 0: log likelihood = -1330.6004 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = 147.6853 Deviance = 49917.64009 (1/df) Deviance = 147.6853 Pearson = 49917.64009 (1/df) Pearson = 147.6853 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 7.838826 Log likelihood = -1330.6004 BIC = 47947.46 ------------------------------------------------------------------------------ | OIM age | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew2 | .5832314 .2635871 2.21 0.027 .0666101 1.099853 _cons | 48.62133 .7061562 68.85 0.000 47.23729 50.00537 ------------------------------------------------------------------------------ 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 radhlw2 avgcumdosew2 if gender==1, fam(gaus) link(identity) Iteration 0: log likelihood = -1693.4076 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = 1247.933 Deviance = 421801.4584 (1/df) Deviance = 1247.933 Pearson = 421801.4584 (1/df) Pearson = 1247.933 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 9.972986 Log likelihood = -1693.407647 BIC = 419831.3 ------------------------------------------------------------------------------ | OIM radhlw2 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew2 | 1.220373 .766216 1.59 0.111 -.2813831 2.722128 _cons | 45.63198 2.052711 22.23 0.000 41.60874 49.65522 ------------------------------------------------------------------------------ 629 . glm HP2probsoc radhlw2 if gender==1,fam(bin) irls link(probit) scale(dev) Iteration 1: deviance = 226.5911 Iteration 2: deviance = 218.8478 Iteration 3: deviance = 218.3822 Iteration 4: deviance = 218.3787 Iteration 5: deviance = 218.3787 Generalized linear models No. of obs = 340 Optimization : MQL Fisher scoring Residual df = 338 (IRLS EIM) Scale parameter = 1 Deviance = 218.378733 (1/df) Deviance = .6460909 Pearson = 326.2667817 (1/df) Pearson = .9652863 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1751.805 ------------------------------------------------------------------------------ | EIM HP2probsoc | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- radhlw2 | .0149459 .0022581 6.62 0.000 .0105201 .0193717 _cons | -2.034921 .1640547 -12.40 0.000 -2.356462 -1.71338 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 630 . 631 . glm shjobw2 avgcumdosew2 if gender==1, fam(gaus) link(identity) Iteration 0: log likelihood = -1730.3274 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = 1550.634 Deviance = 524114.2615 (1/df) Deviance = 1550.634 Pearson = 524114.2615 (1/df) Pearson = 1550.634 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 10.19016 Log likelihood = -1730.327396 BIC = 522144.1 ------------------------------------------------------------------------------ | OIM shjobw2 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew2 | .7146559 .8541028 0.84 0.403 -.9593549 2.388667 _cons | 49.09491 2.288162 21.46 0.000 44.61019 53.57962 ------------------------------------------------------------------------------ 632 . glm HP2probsoc shjobw2 if gender==1,fam(bin) irls link(probit) scale(dev) Iteration 1: deviance = 241.5668 Iteration 2: deviance = 238.4954 Iteration 3: deviance = 238.438 Iteration 4: deviance = 238.438 Iteration 5: deviance = 238.438 Generalized linear models No. of obs = 340 Optimization : MQL Fisher scoring Residual df = 338 (IRLS EIM) Scale parameter = 1 Deviance = 238.4379517 (1/df) Deviance = .7054377 Pearson = 344.7520389 (1/df) Pearson = 1.019976 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1731.746 ------------------------------------------------------------------------------ | EIM HP2probsoc | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- shjobw2 | .0079142 .0019981 3.96 0.000 .003998 .0118303 _cons | -1.622345 .1436613 -11.29 0.000 -1.903915 -1.340774 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 633 . 634 . glm shrelaw2 avgcumdosew2 if gender==1, fam(gaus) link(identity) Iteration 0: log likelihood = -1686.1612 Generalized linear models No. of obs = 339 Optimization : ML Residual df = 337 Scale parameter = 1231.384 Deviance = 414976.438 (1/df) Deviance = 1231.384 Pearson = 414976.438 (1/df) Pearson = 1231.384 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 9.959653 Log likelihood = -1686.16125 BIC = 413013.1 ------------------------------------------------------------------------------ | OIM shrelaw2 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew2 | .6230115 .7612097 0.82 0.413 -.868932 2.114955 _cons | 26.21356 2.042278 12.84 0.000 22.21077 30.21635 ------------------------------------------------------------------------------ 635 . glm HP2probsoc shrelaw2 if gender==1,fam(bin) irls link(probit) scale(dev) Iteration 1: deviance = 247.6569 Iteration 2: deviance = 246.6168 Iteration 3: deviance = 246.614 Iteration 4: deviance = 246.614 Generalized linear models No. of obs = 339 Optimization : MQL Fisher scoring Residual df = 337 (IRLS EIM) Scale parameter = 1 Deviance = 246.6140476 (1/df) Deviance = .7317924 Pearson = 341.2333206 (1/df) Pearson = 1.012562 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1716.748 ------------------------------------------------------------------------------ | EIM HP2probsoc | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- shrelaw2 | .0043873 .0020436 2.15 0.032 .0003819 .0083926 _cons | -1.301708 .0997015 -13.06 0.000 -1.497119 -1.106297 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 636 . 637 . glm radhlw2 shjobw2 avgcumdosew2 if gender==1, fam(gaus) link(identity) Iteration 0: log likelihood = -1684.8126 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 337 Scale parameter = 1189.928 Deviance = 401005.7796 (1/df) Deviance = 1189.928 Pearson = 401005.7796 (1/df) Pearson = 1189.928 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 9.92831 Log likelihood = -1684.812637 BIC = 399041.4 ------------------------------------------------------------------------------ | OIM radhlw2 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- shjobw2 | .1991928 .0476483 4.18 0.000 .1058038 .2925817 avgcumdosew2 | 1.078018 .7489714 1.44 0.150 -.3899386 2.545975 _cons | 35.85263 3.080591 11.64 0.000 29.81478 41.89047 ------------------------------------------------------------------------------ 638 . glm HP2probsoc shjobw2 avgcumdosew2 shjobw2Xd2 if gender==1,fam(bin) /// > irls scale(dev) link(probit) Iteration 1: deviance = 238.9844 Iteration 2: deviance = 235.7842 Iteration 3: deviance = 235.5578 Iteration 4: deviance = 235.4233 Iteration 5: deviance = 235.4108 Iteration 6: deviance = 235.4106 Iteration 7: deviance = 235.4106 Iteration 8: deviance = 235.4106 Generalized linear models No. of obs = 340 Optimization : MQL Fisher scoring Residual df = 336 (IRLS EIM) Scale parameter = 1 Deviance = 235.4106098 (1/df) Deviance = .7006268 Pearson = 342.9227819 (1/df) Pearson = 1.020604 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1723.115 ------------------------------------------------------------------------------ | EIM HP2probsoc | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- shjobw2 | .005567 .0027192 2.05 0.041 .0002374 .0108965 avgcumdosew2 | -.2189419 .2705013 -0.81 0.418 -.7491148 .311231 shjobw2Xd2 | .002944 .0028701 1.03 0.305 -.0026813 .0085693 _cons | -1.466051 .2263255 -6.48 0.000 -1.909641 -1.022461 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 639 . 640 . scalar ProbsocMedMw2 = "age" 641 . 642 . title4 "H1 pt2 wave 2 HP2probsoc female mediator tests" ------------------------------------------------------------------------------- H1 pt2 wave 2 HP2probsoc female mediator tests ------------------------------------------------------------------------------- 643 . 644 . // age is a possible female mediator 645 . glm age avgcumdosew2 if gender==2, fam(gaus) link(identity) Iteration 0: log likelihood = -1406.9403 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = 136.9184 Deviance = 49427.52828 (1/df) Deviance = 136.9184 Pearson = 49427.52828 (1/df) Pearson = 136.9184 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 7.762756 Log likelihood = -1406.940271 BIC = 47299.65 ------------------------------------------------------------------------------ | OIM age | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew2 | 1.502324 .4454009 3.37 0.001 .6293547 2.375294 _cons | 48.86944 .7323225 66.73 0.000 47.43412 50.30477 ------------------------------------------------------------------------------ 646 . 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.) 647 . 648 . // radhlw2 is a possible female mediator 649 . glm radhlw2 avgcumdosew2 if gender==2, fam(gaus) link(identity) Iteration 0: log likelihood = -1791.2233 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = 1137.567 Deviance = 410661.5604 (1/df) Deviance = 1137.567 Pearson = 410661.5604 (1/df) Pearson = 1137.567 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 9.880018 Log likelihood = -1791.223306 BIC = 408533.7 ------------------------------------------------------------------------------ | OIM radhlw2 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew2 | 3.302288 1.283833 2.57 0.010 .7860214 5.818555 _cons | 56.95167 2.110863 26.98 0.000 52.81445 61.08888 ------------------------------------------------------------------------------ 650 . glm HP2probsoc radhlw2 if gender==2,fam(bin) irls scale(dev) link(probit) Iteration 1: deviance = 335.706 Iteration 2: deviance = 333.7569 Iteration 3: deviance = 333.7467 Iteration 4: deviance = 333.7467 Iteration 5: deviance = 333.7467 Generalized linear models No. of obs = 363 Optimization : MQL Fisher scoring Residual df = 361 (IRLS EIM) Scale parameter = 1 Deviance = 333.7467432 (1/df) Deviance = .9245062 Pearson = 373.5069806 (1/df) Pearson = 1.034645 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1794.133 ------------------------------------------------------------------------------ | EIM HP2probsoc | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- radhlw2 | .0135849 .002393 5.68 0.000 .0088947 .0182751 _cons | -1.729418 .1840212 -9.40 0.000 -2.090093 -1.368743 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 651 . 652 . // bf4 is a possible female mediator 653 . glm bf4 avgcumdosew2 if gender==2, fam(gaus) link(identity) Iteration 0: log likelihood = -1109.0983 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = 26.53281 Deviance = 9578.344971 (1/df) Deviance = 26.53281 Pearson = 9578.344971 (1/df) Pearson = 26.53281 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 6.121754 Log likelihood = -1109.098281 BIC = 7450.466 ------------------------------------------------------------------------------ | OIM bf4 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew2 | -.595012 .1960703 -3.03 0.002 -.9793027 -.2107212 _cons | 11.02048 .3223763 34.19 0.000 10.38863 11.65232 ------------------------------------------------------------------------------ 654 . 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.) 655 . 656 . glm shrelaw2 avgcumdosew2 if gender==2, fam(gaus) link(identity) Iteration 0: log likelihood = -1767.2727 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = 996.9369 Deviance = 359894.211 (1/df) Deviance = 996.9369 Pearson = 359894.211 (1/df) Pearson = 996.9369 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 9.748059 Log likelihood = -1767.272695 BIC = 357766.3 ------------------------------------------------------------------------------ | OIM shrelaw2 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew2 | 1.945314 1.20186 1.62 0.106 -.4102891 4.300917 _cons | 22.64351 1.976084 11.46 0.000 18.77046 26.51657 ------------------------------------------------------------------------------ 657 . glm HP2probsoc shrelaw2 bf4 if gender==2,fam(bin) irls scale(dev) link(probit > ) Iteration 1: deviance = 289.2064 Iteration 2: deviance = 281.788 Iteration 3: deviance = 281.4059 Iteration 4: deviance = 281.4028 Iteration 5: deviance = 281.4028 Iteration 6: deviance = 281.4028 Generalized linear models No. of obs = 363 Optimization : MQL Fisher scoring Residual df = 360 (IRLS EIM) Scale parameter = 1 Deviance = 281.4028288 (1/df) Deviance = .7816745 Pearson = 310.3983516 (1/df) Pearson = .8622176 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1840.582 ------------------------------------------------------------------------------ | EIM HP2probsoc | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- shrelaw2 | -.0081327 .0026244 -3.10 0.002 -.0132764 -.002989 bf4 | -.1491375 .015739 -9.48 0.000 -.1799854 -.1182895 _cons | .6945159 .1749292 3.97 0.000 .351661 1.037371 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 658 . 659 . 660 . // shjobw2Xd2 is almost significant but not quite 661 . glm radhlw2 shjobw2 avgcumdosew2 if gender==2, fam(gaus) link(identity) Iteration 0: log likelihood = -1791.1332 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 360 Scale parameter = 1140.16 Deviance = 410457.7613 (1/df) Deviance = 1140.16 Pearson = 410457.7613 (1/df) Pearson = 1140.16 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 9.885031 Log likelihood = -1791.133211 BIC = 408335.8 ------------------------------------------------------------------------------ | OIM radhlw2 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- shjobw2 | -.0191223 .0452294 -0.42 0.672 -.1077704 .0695258 avgcumdosew2 | 3.347309 1.2897 2.60 0.009 .819544 5.875074 _cons | 57.93542 3.14326 18.43 0.000 51.77474 64.09609 ------------------------------------------------------------------------------ 662 . glm HP2probsoc shjobw2 avgcumdosew2 shjobw2Xd2 if gender==2,fam(bin) irls sc > ale(dev) link(probit) Iteration 1: deviance = 337.4422 Iteration 2: deviance = 332.2358 Iteration 3: deviance = 329.0807 Iteration 4: deviance = 328.8969 Iteration 5: deviance = 328.895 Iteration 6: deviance = 328.895 Iteration 7: deviance = 328.895 Generalized linear models No. of obs = 363 Optimization : MQL Fisher scoring Residual df = 359 (IRLS EIM) Scale parameter = 1 Deviance = 328.8950257 (1/df) Deviance = .9161421 Pearson = 356.7664651 (1/df) Pearson = .9937785 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1787.196 ------------------------------------------------------------------------------ | EIM HP2probsoc | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- shjobw2 | .0053961 .0034194 1.58 0.115 -.0013058 .0120979 avgcumdosew2 | 1.437383 .3964978 3.63 0.000 .6602614 2.214504 shjobw2Xd2 | -.0121765 .0040881 -2.98 0.003 -.0201891 -.004164 _cons | -1.737153 .2989256 -5.81 0.000 -2.323036 -1.151269 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 663 . 664 . scalar ProbsocMedFw2 = "age radhlw2" 665 . 666 . 667 . * male hp2spM w2 mediators: age 668 . * dose is not significant main effect for males 669 . * female hp2spF w2 mediators: age radhlw2 670 . * dose is not sig main effect for males 671 . 672 . scalar SigDoseProbsocMw2 = "no" 673 . 674 . 675 . 676 . title4 "3. Matrix summary for H1 pt2 wave 2 HP2probsoc Impact" ------------------------------------------------------------------------------- 3. Matrix summary for H1 pt2 wave 2 HP2probsoc Impact ------------------------------------------------------------------------------- 677 . matrix define spMw2 = J(1,8, 0) 678 . matrix define spFw2 = J(1,8, 0) 679 . matrix colnames spMw2= hypnum ptnum wave gender medsig numMAsig numModsig n > umMed 680 . matrix colnames spFw2= hypnum ptnum wave gender medsig numMAsig numModsig n > umMed 681 . 682 . matrix define spMw2= (1, 2, 3, 1, 0, 4, 0, 1 ) 683 . matrix define spFw2= (1, 2, 3, 2, 1, 5, 0, 2 ) 684 . matrix rowname spMw2 = spMw2 685 . matrix rowname spFw2 = spFw2 686 . matlist spMw2 | c1 c2 c3 c4 c5 c6 > c7 c8 -------------+----------------------------------------------------------------- ----------------------- spMw2 | 1 2 3 1 0 4 > 0 1 687 . matlist spFw2 | c1 c2 c3 c4 c5 c6 > c7 c8 -------------+----------------------------------------------------------------- ----------------------- spFw2 | 1 2 3 2 1 5 > 0 2 688 . matrix define H1pt2w2 = ( wkMw2 \ wkFw2 \ hmcrMw2 \ hmcrFw2 \ sp > Mw2 \ spFw2 ) 689 . 690 . matlist H1pt2w2 | c1 c2 c3 c4 c5 c6 > c7 c8 -------------+----------------------------------------------------------------- ----------------------- r1 | 1 2 2 1 0 2 > 0 2 r1 | 1 2 2 2 0 1 > 0 2 r1 | 1 2 3 1 0 1 > 0 1 r1 | 1 2 3 2 0 1 > 0 1 spMw2 | 1 2 3 1 0 4 > 0 1 spFw2 | 1 2 3 2 1 5 > 0 2 691 . matrix colnames H1pt2w2 = hypnum ptnum wave gender medsig numMAsig numMo > dsig numMed 692 . matrix rownames H1pt2w2 = wkMw2 wkFw2 hmcrMw2 hmcrFw2 socprbMw2 socprbF > w2 693 . matlist H1pt2w2 | hypnum ptnum wave gender medsig numMAsig > numModsig numMed -------------+----------------------------------------------------------------- ----------------------- wkMw2 | 1 2 2 1 0 2 > 0 2 wkFw2 | 1 2 2 2 0 1 > 0 2 hmcrMw2 | 1 2 3 1 0 1 > 0 1 hmcrFw2 | 1 2 3 2 0 1 > 0 1 socprbMw2 | 1 2 3 1 0 4 > 0 1 socprbFw2 | 1 2 3 2 1 5 > 0 2 694 . 695 . 696 . *xx significant dose effect for females 697 . scalar ProbsocModFw2 = "none" 698 . *xx no female moderators for Dose Social problem impact relationship 699 . scalar list MainEffPrbsocMw2 = age radhlw2 shjobw2 MainEffhmcareMw2 = b4 MainEffwkFw2 = age MainEffwkMw2 = workM: age ProbsocMedFw2 = age radhlw2 ProbsocMedMw2 = age ProbsocModFw2 = none MainEffProbSocFw2 = age avgcomdosew2 radhlw2 avgcumodsew2 b4 SigDoseProbsocFw2 = yes ProbSocModMw2 = none SigDoseProbsocMw2 = no PrbsocModMw2 = none SigdoseMw2 = none hmcareMedFw2 = age hmcareMedMw2 = age hmcareModFw2 = none MainEffhmcarew2 = age SigdoseHmcareFw2 = no hmcareModMw2 = none SigDoseHmcareMw2 = no wkMedFw2 = radhlw2 age bf40 bf4m bf1 NameMedMw2 = age ageXillw2 NumModMw2 = none SigDosehmcareMw2 = no SigDoseWKMw2 = no WkMedFw2 = age bf4 WkMedMw2 = age ageXillw2 WkModFw2 = none WKModMw2 = none SigDoseWkMw2 = no SigDoseWkFw2 = no SigDoseFw2 = no wkModFw2 = none wkModMw2 = none 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 700 . 701 . 702 . 703 . *----------- Chunk 5 Dose => Problems with the Family at home Impact 704 . title "4. H1 pt 2 wave 2 Dose = Fam Problems at home impact" ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** 4. H1 pt 2 wave 2 Dose = Fam Problems at home impact ***** ***** ***** ***** ***** ***** 16 Jun 2012 21:55:44 ***** ******************************************************************************* ******************************************************************************* 705 . title4 " Wave 2 part2 H1:hypothesis 1 Pt2 Probs with Fam at home" ------------------------------------------------------------------------------- Wave 2 part2 H1:hypothesis 1 Pt2 Probs with Fam at home ------------------------------------------------------------------------------- 706 . title4 " Wave 2 Main effects identification" ------------------------------------------------------------------------------- Wave 2 Main effects identification ------------------------------------------------------------------------------- 707 . forvalues j = 2/2 { 2. set more off 3. 708 . des age educ1-educ7 marrw`j'1-marrw`j'6 inc1w`j'-inc4w`j' /// > bf1 bf4 bf9 bf11 bf4m bf15m bf30 bf40 4. 709 . foreach var in HP2pbfhm { 5. forvalues k=1/2 { 6. local w2bf bf1 bf4 bf6 bf7 bf14 bf15 bf40 7. 710 . 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. 711 . 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 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 marrw21 byte %8.0g marrw2==1. single marrw22 byte %8.0g marrw2==2. cohabitating marrw23 byte %8.0g marrw2==3. married marrw24 byte %8.0g marrw2==4. separated marrw25 byte %8.0g marrw2==5. divorced marrw26 byte %8.0g marrw2==6. widowed inc1w2 double %15.0g LABJ Income is not sufficient for basic neccessities in 1996 inc2w2 double %15.0g LABJ Income is just sufficient for basic neccessities in 1996 inc3w2 double %15.0g LABJ Income is sufficient for basics plus extra purchases/savings in 1996 inc4w2 double %15.0g LABJ Income allows to comfortably afford luxury items in 1996 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= 2 chunk 5 H1 test:Gender= 1 model Wave = 2 for HP2probsoc ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Full Nottingham Part 2 subscale models for male and then females ***** ***** ***** ***** ***** ***** 16 Jun 2012 21:55:44 ***** ******************************************************************************* ******************************************************************************* 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 12 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: occ5w2 != 0 predicts failure perfectly occ5w2 dropped and 17 obs not used note: occ6w2 != 0 predicts failure perfectly occ6w2 dropped and 4 obs not used note: occ8w2 != 0 predicts failure perfectly occ8w2 dropped and 43 obs not used note: marrw22 != 0 predicts failure perfectly marrw22 dropped and 7 obs not used note: marrw25 != 0 predicts failure perfectly marrw25 dropped and 4 obs not used note: marrw26 != 0 predicts failure perfectly marrw26 dropped and 3 obs not used note: inc1w2 != 0 predicts failure perfectly inc1w2 dropped and 13 obs not used note: inc4w2 != 0 predicts failure perfectly inc4w2 dropped and 9 obs not used note: dvcew2 != 0 predicts failure perfectly dvcew2 dropped and 2 obs not used note: sepaw2 != 0 predicts failure perfectly sepaw2 dropped and 1 obs not used note: _Ieduc_6 omitted because of collinearity note: bf15 omitted because of collinearity Logistic regression Number of obs = 201 LR chi2(32) = 57.01 Prob > chi2 = 0.0042 Log likelihood = -38.789787 Pseudo R2 = 0.4236 ------------------------------------------------------------------------------ HP2pbfhm | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0838902 .0451044 1.86 0.063 -.0045127 .1722932 _Ieduc_2 | 0 (omitted) _Ieduc_3 | -1.068513 .9797271 -1.09 0.275 -2.988743 .851717 _Ieduc_4 | 0 (omitted) _Ieduc_5 | -.7464993 1.30613 -0.57 0.568 -3.306468 1.813469 _Ieduc_6 | 0 (omitted) _Ieduc_7 | 0 (omitted) _Ieduc_8 | 0 (omitted) occ1w2 | 1.365472 9.739165 0.14 0.888 -17.72294 20.45389 occ2w2 | .1388058 9.737518 0.01 0.989 -18.94638 19.22399 occ3w2 | 1.99317 9.743118 0.20 0.838 -17.10299 21.08933 occ4w2 | 2.351827 9.813506 0.24 0.811 -16.88229 21.58595 occ5w2 | 0 (omitted) occ6w2 | 0 (omitted) occ7w2 | .8526169 9.853293 0.09 0.931 -18.45948 20.16472 occ8w2 | 0 (omitted) marrw21 | 9.450183 1628.316 0.01 0.995 -3181.99 3200.891 marrw22 | 0 (omitted) marrw23 | 8.041239 1628.316 0.00 0.996 -3183.4 3199.482 marrw25 | 0 (omitted) marrw26 | 0 (omitted) inc1w2 | 0 (omitted) inc2w2 | -.2472615 9.778068 -0.03 0.980 -19.41192 18.9174 inc3w2 | .4803685 9.779356 0.05 0.961 -18.68682 19.64755 inc4w2 | 0 (omitted) radhlw2 | .0219991 .0174949 1.26 0.209 -.0122902 .0562884 havmil | -.0118024 .0110278 -1.07 0.285 -.0334164 .0098117 avgcumdosew2 | -.108206 .7718766 -0.14 0.889 -1.621056 1.404644 bf1 | -.0239769 .0247822 -0.97 0.333 -.0725492 .0245953 bf4 | -.1619124 .088191 -1.84 0.066 -.3347635 .0109388 bf6 | .0726065 .0265235 2.74 0.006 .0206214 .1245916 bf7 | .5947613 .2273662 2.62 0.009 .1491317 1.040391 bf14 | -.0000762 .0001284 -0.59 0.553 -.0003279 .0001756 bf15 | 0 (omitted) bf40 | .1113503 .2734738 0.41 0.684 -.4246485 .6473491 deaw2 | .5485131 .536457 1.02 0.307 -.5029234 1.59995 dvcew2 | 0 (omitted) sepaw2 | 0 (omitted) accdw2 | .185387 1.066161 0.17 0.862 -1.904251 2.275025 movew2 | -.6539417 1.506102 -0.43 0.664 -3.605848 2.297965 illw2 | 1.606215 .6542566 2.46 0.014 .3238954 2.888534 shfamw2 | -.0092438 .0132973 -0.70 0.487 -.0353061 .0168184 shhlw2 | -.031707 .0186076 -1.70 0.088 -.0681771 .0047632 shjobw2 | .0258976 .0158492 1.63 0.102 -.0051662 .0569614 shrelaw2 | -.0153159 .0142321 -1.08 0.282 -.0432103 .0125785 suprtw2 | -.0315277 .0143652 -2.19 0.028 -.059683 -.0033724 suchrw2 | .0165746 .0112144 1.48 0.139 -.0054051 .0385544 havmilsq | .0000128 .0000121 1.06 0.291 -.000011 .0000367 _cons | -18.46331 1628.32 -0.01 0.991 -3209.912 3172.985 ------------------------------------------------------------------------------ Logistic model for HP2pbfhm -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 6 2 | 8 - | 15 178 | 193 -----------+--------------------------+----------- Total | 21 180 | 201 Classified + if predicted Pr(D) >= .5 True D defined as HP2pbfhm != 0 -------------------------------------------------- Sensitivity Pr( +| D) 28.57% Specificity Pr( -|~D) 98.89% Positive predictive value Pr( D| +) 75.00% Negative predictive value Pr(~D| -) 92.23% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 1.11% False - rate for true D Pr( -| D) 71.43% False + rate for classified + Pr(~D| +) 25.00% False - rate for classified - Pr( D| -) 7.77% -------------------------------------------------- Correctly classified 91.54% -------------------------------------------------- Logistic model for HP2pbfhm, goodness-of-fit test number of observations = 201 number of covariate patterns = 201 Pearson chi2(168) = 94.58 Prob > chi2 = 1.0000 Measures of Fit for logistic of HP2pbfhm Log-Lik Intercept Only: -67.297 Log-Lik Full Model: -38.790 D(152): 77.580 LR(32): 57.015 Prob > LR: 0.004 McFadden's R2: 0.424 McFadden's Adj R2: -0.305 Maximum Likelihood R2: 0.247 Cragg & Uhler's R2: 0.506 McKelvey and Zavoina's R2: 0.804 Efron's R2: 0.348 Variance of y*: 16.822 Variance of error: 3.290 Count R2: 0.915 Adj Count R2: 0.190 AIC: 0.874 AIC*n: 175.580 BIC: -728.523 BIC': 112.691 Full main model for HP2pbfhm for wave= 2 chunk 5 H1 test:Gender= 2 model Wave = 2 for HP2pbfhm ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Full Nottingham Part 2 subscale models for male and then females ***** ***** ***** ***** ***** ***** 16 Jun 2012 21:55:46 ***** ******************************************************************************* ******************************************************************************* i.educ _Ieduc_1-8 (naturally coded; _Ieduc_1 omitted) note: occ6w2 != 0 predicts failure perfectly occ6w2 dropped and 9 obs not used note: marrw22 != 0 predicts failure perfectly marrw22 dropped and 8 obs not used note: inc4w2 != 0 predicts failure perfectly inc4w2 dropped and 9 obs not used note: sepaw2 != 0 predicts failure perfectly sepaw2 dropped and 6 obs not used note: movew2 != 0 predicts failure perfectly movew2 dropped and 39 obs not used note: _Ieduc_8 omitted because of collinearity note: marrw26 omitted because of collinearity note: bf15 omitted because of collinearity convergence not achieved Logistic regression Number of obs = 291 LR chi2(39) = 121.44 Prob > chi2 = 0.0000 Log likelihood = -67.950854 Pseudo R2 = 0.4719 ------------------------------------------------------------------------------ HP2pbfhm | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0675647 .0282471 2.39 0.017 .0122015 .1229279 _Ieduc_2 | 22.46198 4.286253 5.24 0.000 14.06108 30.86288 _Ieduc_3 | 22.06025 4.212008 5.24 0.000 13.80487 30.31564 _Ieduc_4 | 22.4092 4.348301 5.15 0.000 13.88669 30.93171 _Ieduc_5 | 22.32965 4.28528 5.21 0.000 13.93065 30.72864 _Ieduc_6 | 22.02862 4.22306 5.22 0.000 13.75158 30.30567 _Ieduc_7 | 21.12883 . . . . . _Ieduc_8 | 0 (omitted) occ1w2 | .9568844 2.829891 0.34 0.735 -4.5896 6.503369 occ2w2 | -2.026671 3.019495 -0.67 0.502 -7.944772 3.891431 occ3w2 | 1.405631 2.856151 0.49 0.623 -4.192322 7.003584 occ4w2 | -1.270684 3.036271 -0.42 0.676 -7.221665 4.680297 occ5w2 | 2.733135 3.099019 0.88 0.378 -3.340831 8.8071 occ6w2 | 0 (omitted) occ7w2 | 2.390639 2.797142 0.85 0.393 -3.091658 7.872935 occ8w2 | 1.799797 3.171082 0.57 0.570 -4.415409 8.015004 marrw21 | 1.863442 1.565893 1.19 0.234 -1.205651 4.932536 marrw22 | 0 (omitted) marrw23 | 1.299753 1.073276 1.21 0.226 -.8038291 3.403334 marrw25 | 1.783742 1.600693 1.11 0.265 -1.353558 4.921042 marrw26 | 0 (omitted) inc1w2 | -1.338762 2.877886 -0.47 0.642 -6.979314 4.301791 inc2w2 | .7251666 2.789285 0.26 0.795 -4.741732 6.192065 inc3w2 | .4037645 2.828422 0.14 0.886 -5.13984 5.947369 inc4w2 | 0 (omitted) radhlw2 | .0119256 .0102886 1.16 0.246 -.0082396 .0320909 havmil | -.0040139 .0172972 -0.23 0.816 -.0379157 .0298879 avgcumdosew2 | .2722171 .2230232 1.22 0.222 -.1649004 .7093346 bf1 | -.0267246 .0134298 -1.99 0.047 -.0530465 -.0004027 bf4 | -.3567161 .0758997 -4.70 0.000 -.5054767 -.2079554 bf6 | .0040524 .0115093 0.35 0.725 -.0185053 .0266102 bf7 | -.087478 .1503624 -0.58 0.561 -.382183 .2072269 bf14 | -.0003779 .0001483 -2.55 0.011 -.0006686 -.0000872 bf15 | 0 (omitted) bf40 | -.3388161 .1424322 -2.38 0.017 -.6179782 -.0596541 deaw2 | -.0547509 .2551957 -0.21 0.830 -.5549253 .4454235 dvcew2 | -1.224029 2.015285 -0.61 0.544 -5.173916 2.725858 sepaw2 | 0 (omitted) accdw2 | -2.829263 1.402671 -2.02 0.044 -5.578447 -.0800779 movew2 | 0 (omitted) illw2 | .0637667 .2827466 0.23 0.822 -.4904064 .6179399 shfamw2 | .0166332 .00908 1.83 0.067 -.0011633 .0344296 shhlw2 | .0127805 .0100076 1.28 0.202 -.006834 .0323949 shjobw2 | -.0073866 .0092188 -0.80 0.423 -.0254551 .0106818 shrelaw2 | -.0222876 .0112977 -1.97 0.049 -.0444307 -.0001445 suprtw2 | -.0213951 .0081927 -2.61 0.009 -.0374524 -.0053378 suchrw2 | -.0010257 .0080813 -0.13 0.899 -.0168647 .0148133 havmilsq | -6.28e-06 .0000546 -0.12 0.908 -.0001132 .0001006 _cons | -23.95744 5.116815 -4.68 0.000 -33.98621 -13.92866 ------------------------------------------------------------------------------ Note: 2 failures and 0 successes completely determined. Warning: convergence not achieved Logistic model for HP2pbfhm -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 27 8 | 35 - | 20 236 | 256 -----------+--------------------------+----------- Total | 47 244 | 291 Classified + if predicted Pr(D) >= .5 True D defined as HP2pbfhm != 0 -------------------------------------------------- Sensitivity Pr( +| D) 57.45% Specificity Pr( -|~D) 96.72% Positive predictive value Pr( D| +) 77.14% Negative predictive value Pr(~D| -) 92.19% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 3.28% False - rate for true D Pr( -| D) 42.55% False + rate for classified + Pr(~D| +) 22.86% False - rate for classified - Pr( D| -) 7.81% -------------------------------------------------- Correctly classified 90.38% -------------------------------------------------- Logistic model for HP2pbfhm, goodness-of-fit test number of observations = 291 number of covariate patterns = 291 Pearson chi2(250) = 231.07 Prob > chi2 = 0.7993 Measures of Fit for logistic of HP2pbfhm Log-Lik Intercept Only: -128.671 Log-Lik Full Model: -67.951 D(242): 135.902 LR(39): 121.440 Prob > LR: 0.000 McFadden's R2: 0.472 McFadden's Adj R2: 0.091 Maximum Likelihood R2: 0.341 Cragg & Uhler's R2: 0.581 McKelvey and Zavoina's R2: 0.819 Efron's R2: 0.487 Variance of y*: 18.199 Variance of error: 3.290 Count R2: 0.904 Adj Count R2: 0.404 AIC: 0.804 AIC*n: 233.902 BIC: -1237.043 BIC': 99.819 712 . 713 . 714 . title4 "Partly Trimmed male Wave 2 Dose => Problems with Family at home mode > ls" ------------------------------------------------------------------------------- Partly Trimmed male Wave 2 Dose => Problems with Family at home models ------------------------------------------------------------------------------- 715 . local w2bf bf1 bf4 bf6 bf7 bf14 bf15 bf40 716 . logit HP2pbfhm age sepaw2 dvcew2 radhlw2 avgcumdosew2 suprtw2 /// > havmilsq illw2 `w2bf' if gender==1, iterate(50) note: sepaw2 != 0 predicts failure perfectly sepaw2 dropped and 6 obs not used note: dvcew2 != 0 predicts failure perfectly dvcew2 dropped and 4 obs not used note: bf15 omitted because of collinearity Iteration 0: log likelihood = -77.69777 Iteration 1: log likelihood = -67.157716 Iteration 2: log likelihood = -58.934212 Iteration 3: log likelihood = -58.608515 Iteration 4: log likelihood = -58.606304 Iteration 5: log likelihood = -58.606303 Logistic regression Number of obs = 323 LR chi2(12) = 38.18 Prob > chi2 = 0.0001 Log likelihood = -58.606303 Pseudo R2 = 0.2457 ------------------------------------------------------------------------------ HP2pbfhm | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0293489 .024747 1.19 0.236 -.0191544 .0778522 sepaw2 | 0 (omitted) dvcew2 | 0 (omitted) radhlw2 | .0117697 .0106734 1.10 0.270 -.0091498 .0326891 avgcumdosew2 | -.1174052 .3535227 -0.33 0.740 -.8102969 .5754865 suprtw2 | -.0080267 .0061596 -1.30 0.193 -.0200994 .0040459 havmilsq | -3.65e-08 5.76e-06 -0.01 0.995 -.0000113 .0000113 illw2 | .9049759 .3924053 2.31 0.021 .1358755 1.674076 bf1 | -.0223279 .0146353 -1.53 0.127 -.0510126 .0063568 bf4 | -.0802471 .0583147 -1.38 0.169 -.1945419 .0340477 bf6 | .0396949 .0144137 2.75 0.006 .0114445 .0679452 bf7 | .2899484 .130624 2.22 0.026 .03393 .5459667 bf14 | -6.92e-06 .0000824 -0.08 0.933 -.0001685 .0001546 bf15 | 0 (omitted) bf40 | -.1058893 .2085913 -0.51 0.612 -.5147207 .3029421 _cons | -5.474896 2.021098 -2.71 0.007 -9.436175 -1.513616 ------------------------------------------------------------------------------ 717 . 718 . estat class Logistic model for HP2pbfhm -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 0 3 | 3 - | 21 299 | 320 -----------+--------------------------+----------- Total | 21 302 | 323 Classified + if predicted Pr(D) >= .5 True D defined as HP2pbfhm != 0 -------------------------------------------------- Sensitivity Pr( +| D) 0.00% Specificity Pr( -|~D) 99.01% Positive predictive value Pr( D| +) 0.00% Negative predictive value Pr(~D| -) 93.44% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 0.99% False - rate for true D Pr( -| D) 100.00% False + rate for classified + Pr(~D| +) 100.00% False - rate for classified - Pr( D| -) 6.56% -------------------------------------------------- Correctly classified 92.57% -------------------------------------------------- 719 . estat gof Logistic model for HP2pbfhm, goodness-of-fit test number of observations = 323 number of covariate patterns = 323 Pearson chi2(310) = 201.67 Prob > chi2 = 1.0000 720 . fitstat Measures of Fit for logit of HP2pbfhm Log-Lik Intercept Only: -77.698 Log-Lik Full Model: -58.606 D(307): 117.213 LR(12): 38.183 Prob > LR: 0.000 McFadden's R2: 0.246 McFadden's Adj R2: 0.040 Maximum Likelihood R2: 0.111 Cragg & Uhler's R2: 0.292 McKelvey and Zavoina's R2: 0.428 Efron's R2: 0.123 Variance of y*: 5.752 Variance of error: 3.290 Count R2: 0.926 Adj Count R2: -0.143 AIC: 0.462 AIC*n: 149.213 BIC: -1656.527 BIC': 31.149 721 . 722 . title4 "trimmed male main effects wv 2" " Dose => Problems with Family at hom > e models" ------------------------------------------------------------------------------- trimmed male main effects wv 2 ------------------------------------------------------------------------------- 723 . local w2bf bf1 bf4 bf6 bf7 bf14 bf15 bf40 724 . sw, pr(.1):logit HP2pbfhm age sepaw2 dvcew2 radhlw2 avgcumdosew2 bf4 bf6 bf7 > suprtw2 /// > havmilsq illw2 if gender==1, iterate(50) note: sepaw2 dropped because of estimability note: dvcew2 dropped because of estimability note: o.sepaw2 dropped because of estimability note: o.dvcew2 dropped because of estimability note: 10 obs. dropped because of estimability begin with full model p = 0.8936 >= 0.1000 removing havmilsq p = 0.7469 >= 0.1000 removing avgcumdosew2 p = 0.6617 >= 0.1000 removing radhlw2 p = 0.3316 >= 0.1000 removing suprtw2 p = 0.2216 >= 0.1000 removing age Logistic regression Number of obs = 330 LR chi2(4) = 30.41 Prob > chi2 = 0.0000 Log likelihood = -65.61942 Pseudo R2 = 0.1881 ------------------------------------------------------------------------------ HP2pbfhm | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- bf6 | .0392413 .01226 3.20 0.001 .0152122 .0632704 bf7 | .2697216 .1148207 2.35 0.019 .0446772 .494766 illw2 | .5624726 .330378 1.70 0.089 -.0850564 1.210002 bf4 | -.1039323 .0416421 -2.50 0.013 -.1855494 -.0223153 _cons | -4.327314 1.14845 -3.77 0.000 -6.578234 -2.076394 ------------------------------------------------------------------------------ 725 . 726 . estat class Logistic model for HP2pbfhm -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 0 0 | 0 - | 22 308 | 330 -----------+--------------------------+----------- Total | 22 308 | 330 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| -) 93.33% -------------------------------------------------- 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| -) 6.67% -------------------------------------------------- Correctly classified 93.33% -------------------------------------------------- 727 . estat gof Logistic model for HP2pbfhm, goodness-of-fit test number of observations = 330 number of covariate patterns = 157 Pearson chi2(152) = 131.86 Prob > chi2 = 0.8794 728 . fitstat Measures of Fit for logit of HP2pbfhm Log-Lik Intercept Only: -80.827 Log-Lik Full Model: -65.619 D(325): 131.239 LR(4): 30.415 Prob > LR: 0.000 McFadden's R2: 0.188 McFadden's Adj R2: 0.126 Maximum Likelihood R2: 0.088 Cragg & Uhler's R2: 0.227 McKelvey and Zavoina's R2: 0.353 Efron's R2: 0.106 Variance of y*: 5.085 Variance of error: 3.290 Count R2: 0.933 Adj Count R2: 0.000 AIC: 0.428 AIC*n: 141.239 BIC: -1753.466 BIC': -7.219 729 . 730 . scalar MainEffPrbfhmMw2 = "bf4 bf6 bf7" 731 . scalar SigDosePrbfhmMw2 = "no" 732 . // construction of moderators for male model 733 . 734 . foreach var in bf4 bf6 bf7 { 2. cap gen `var'Xd2 = `var'*avgcumdosew2 3. } 735 . 736 . 737 . 738 . 739 . ***************************************************************************** > * 740 . *-------chunk 6 continued -testing moderators and none found for males 741 . local w2bf bf1 bf4 bf6 bf7 bf14 bf15 bf40 742 . 743 . 744 . title4 "fully Trimmed male main effects wv 3" /// > "Dose => Problems with Family at home models" ------------------------------------------------------------------------------- fully Trimmed male main effects wv 3 ------------------------------------------------------------------------------- 745 . local w2bf bf1 bf4 bf6 bf7 bf14 bf15 bf40 746 . logit HP2pbfhm age radhlw2 avgcumdosew2 suprtw2 /// > havmilsq illw2 bf4Xd2 bf6Xd2 bf7Xd2 if /// > gender==1, iterate(50) Iteration 0: log likelihood = -81.506236 Iteration 1: log likelihood = -72.800639 Iteration 2: log likelihood = -69.028116 Iteration 3: log likelihood = -67.540232 Iteration 4: log likelihood = -67.005599 Iteration 5: log likelihood = -66.995741 Iteration 6: log likelihood = -66.995738 Logistic regression Number of obs = 340 LR chi2(9) = 29.02 Prob > chi2 = 0.0006 Log likelihood = -66.995738 Pseudo R2 = 0.1780 ------------------------------------------------------------------------------ HP2pbfhm | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0343118 .0208161 1.65 0.099 -.006487 .0751105 radhlw2 | .0106695 .0083229 1.28 0.200 -.0056431 .0269822 avgcumdosew2 | -3.003612 1.869463 -1.61 0.108 -6.667692 .6604683 suprtw2 | -.0054152 .0057198 -0.95 0.344 -.0166259 .0057954 havmilsq | -3.14e-06 7.66e-06 -0.41 0.682 -.0000182 .0000119 illw2 | .4648094 .3233311 1.44 0.151 -.168908 1.098527 bf4Xd2 | -.038029 .0582653 -0.65 0.514 -.1522269 .0761689 bf6Xd2 | .03687 .019993 1.84 0.065 -.0023156 .0760555 bf7Xd2 | .3158796 .1784981 1.77 0.077 -.0339702 .6657294 _cons | -4.382885 1.319377 -3.32 0.001 -6.968817 -1.796954 ------------------------------------------------------------------------------ Note: 3 failures and 0 successes completely determined. 747 . 748 . estat class Logistic model for HP2pbfhm -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 0 0 | 0 - | 22 318 | 340 -----------+--------------------------+----------- Total | 22 318 | 340 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| -) 93.53% -------------------------------------------------- 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| -) 6.47% -------------------------------------------------- Correctly classified 93.53% -------------------------------------------------- 749 . estat gof Logistic model for HP2pbfhm, goodness-of-fit test number of observations = 340 number of covariate patterns = 338 Pearson chi2(328) = 269.41 Prob > chi2 = 0.9921 750 . fitstat Measures of Fit for logit of HP2pbfhm Log-Lik Intercept Only: -81.506 Log-Lik Full Model: -66.996 D(330): 133.991 LR(9): 29.021 Prob > LR: 0.001 McFadden's R2: 0.178 McFadden's Adj R2: 0.055 Maximum Likelihood R2: 0.082 Cragg & Uhler's R2: 0.215 McKelvey and Zavoina's R2: 0.912 Efron's R2: 0.089 Variance of y*: 37.411 Variance of error: 3.290 Count R2: 0.935 Adj Count R2: 0.000 AIC: 0.453 AIC*n: 153.991 BIC: -1789.561 BIC': 23.440 751 . 752 . scalar SigDosePrbfmhmMw2 = "no" 753 . scalar PrbfmhmModw2 = "none" 754 . 755 . * 3 main effects signif no main effect for dose for males 756 . 757 . 758 . *-------Chunk 6 continued -testing meditors for females 759 . title4 "Partly Trimmed female Wave 2" "Dose => Problems with Family at home > models" ------------------------------------------------------------------------------- Partly Trimmed female Wave 2 ------------------------------------------------------------------------------- 760 . local w2bf bf1 bf4 bf6 bf7 bf14 bf15 bf40 761 . logit HP2pbfhm age radhlw2 avgcumdosew2 bf4 if gender==2, iterate(50) Iteration 0: log likelihood = -139.89675 Iteration 1: log likelihood = -113.0036 Iteration 2: log likelihood = -107.10312 Iteration 3: log likelihood = -106.98442 Iteration 4: log likelihood = -106.98403 Iteration 5: log likelihood = -106.98403 Logistic regression Number of obs = 363 LR chi2(4) = 65.83 Prob > chi2 = 0.0000 Log likelihood = -106.98403 Pseudo R2 = 0.2353 ------------------------------------------------------------------------------ HP2pbfhm | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0557545 .0170818 3.26 0.001 .0222747 .0892342 radhlw2 | .0108772 .0060404 1.80 0.072 -.0009617 .0227161 avgcumdosew2 | -.0049664 .0969934 -0.05 0.959 -.19507 .1851373 bf4 | -.1657135 .0368332 -4.50 0.000 -.2379053 -.0935217 _cons | -4.323335 1.125843 -3.84 0.000 -6.529946 -2.116724 ------------------------------------------------------------------------------ 762 . 763 . estat class Logistic model for HP2pbfhm -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 9 6 | 15 - | 38 310 | 348 -----------+--------------------------+----------- Total | 47 316 | 363 Classified + if predicted Pr(D) >= .5 True D defined as HP2pbfhm != 0 -------------------------------------------------- Sensitivity Pr( +| D) 19.15% Specificity Pr( -|~D) 98.10% Positive predictive value Pr( D| +) 60.00% Negative predictive value Pr(~D| -) 89.08% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 1.90% False - rate for true D Pr( -| D) 80.85% False + rate for classified + Pr(~D| +) 40.00% False - rate for classified - Pr( D| -) 10.92% -------------------------------------------------- Correctly classified 87.88% -------------------------------------------------- 764 . estat gof Logistic model for HP2pbfhm, goodness-of-fit test number of observations = 363 number of covariate patterns = 361 Pearson chi2(356) = 363.32 Prob > chi2 = 0.3830 765 . fitstat Measures of Fit for logit of HP2pbfhm Log-Lik Intercept Only: -139.897 Log-Lik Full Model: -106.984 D(358): 213.968 LR(4): 65.825 Prob > LR: 0.000 McFadden's R2: 0.235 McFadden's Adj R2: 0.200 Maximum Likelihood R2: 0.166 Cragg & Uhler's R2: 0.309 McKelvey and Zavoina's R2: 0.390 Efron's R2: 0.216 Variance of y*: 5.395 Variance of error: 3.290 Count R2: 0.879 Adj Count R2: 0.064 AIC: 0.617 AIC*n: 223.968 BIC: -1896.228 BIC': -42.248 766 . 767 . scalar SigDosePrbfmhmFw2="no" 768 . 769 . *-------Chunk 6 continued -testing meditors for females 770 . title4 "More partly female Trimmed Wave 2" "Dose => Problems with Family at > home models" ------------------------------------------------------------------------------- More partly female Trimmed Wave 2 ------------------------------------------------------------------------------- 771 . local w2bf bf1 bf4 bf6 bf7 bf14 bf15 bf40 772 . 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 ------------------------------------------------------------------------------ 773 . 774 . 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% -------------------------------------------------- 775 . 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 776 . 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': -49.868 777 . 778 . 779 . scalar MainEffPrbfmhmFw2 = "age bf4 bf40" 780 . * 3 significant main effects for females 781 . * no significant main effect for dose 782 . 783 . * constructing moderators 784 . 785 . foreach var in bf4 bf40 { 2. cap gen `var'Xd2 = `var'*avgcumdosew2 3. } 786 . 787 . 788 . title4 "testing female moderator effects: no moderator effects for females" ------------------------------------------------------------------------------- testing female moderator effects: no moderator effects for females ------------------------------------------------------------------------------- 789 . 790 . logit HP2pbfhm age bf4 bf40 ageXd2 bf4Xd2 bf40Xd2 if gender==2, iterate(50) Iteration 0: log likelihood = -139.89675 Iteration 1: log likelihood = -111.91159 Iteration 2: log likelihood = -105.8511 Iteration 3: log likelihood = -104.97326 Iteration 4: log likelihood = -104.94985 Iteration 5: log likelihood = -104.9498 Iteration 6: log likelihood = -104.9498 Logistic regression Number of obs = 363 LR chi2(6) = 69.89 Prob > chi2 = 0.0000 Log likelihood = -104.9498 Pseudo R2 = 0.2498 ------------------------------------------------------------------------------ HP2pbfhm | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .057978 .018048 3.21 0.001 .0226046 .0933514 bf4 | -.2081538 .0505288 -4.12 0.000 -.3071884 -.1091193 bf40 | -.0721876 .1339532 -0.54 0.590 -.334731 .1903558 ageXd2 | .006707 .0069963 0.96 0.338 -.0070055 .0204195 bf4Xd2 | .0146354 .0371601 0.39 0.694 -.0581971 .087468 bf40Xd2 | -.1308031 .1156271 -1.13 0.258 -.357428 .0958218 _cons | -3.176982 1.121456 -2.83 0.005 -5.374996 -.9789674 ------------------------------------------------------------------------------ 791 . estat gof Logistic model for HP2pbfhm, goodness-of-fit test number of observations = 363 number of covariate patterns = 359 Pearson chi2(352) = 361.42 Prob > chi2 = 0.3531 792 . estat class Logistic model for HP2pbfhm -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 14 4 | 18 - | 33 312 | 345 -----------+--------------------------+----------- Total | 47 316 | 363 Classified + if predicted Pr(D) >= .5 True D defined as HP2pbfhm != 0 -------------------------------------------------- Sensitivity Pr( +| D) 29.79% Specificity Pr( -|~D) 98.73% Positive predictive value Pr( D| +) 77.78% Negative predictive value Pr(~D| -) 90.43% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 1.27% False - rate for true D Pr( -| D) 70.21% False + rate for classified + Pr(~D| +) 22.22% False - rate for classified - Pr( D| -) 9.57% -------------------------------------------------- Correctly classified 89.81% -------------------------------------------------- 793 . fitstat Measures of Fit for logit of HP2pbfhm Log-Lik Intercept Only: -139.897 Log-Lik Full Model: -104.950 D(356): 209.900 LR(6): 69.894 Prob > LR: 0.000 McFadden's R2: 0.250 McFadden's Adj R2: 0.200 Maximum Likelihood R2: 0.175 Cragg & Uhler's R2: 0.326 McKelvey and Zavoina's R2: 0.411 Efron's R2: 0.233 Variance of y*: 5.585 Variance of error: 3.290 Count R2: 0.898 Adj Count R2: 0.213 AIC: 0.617 AIC*n: 223.900 BIC: -1888.508 BIC': -34.527 794 . 795 . scalar PrbfmhmModFw2="none" 796 . 797 . ***************************************************************************** > *** 798 . *---------Chunk 6 continued testing mediating effects for Problems with famil > y 799 . * at home 800 . 801 . * age is a mediating effect for males for Dose=> problems with family at home 802 . 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) 803 . glm age avgcumdosew2 if gender==1, fam(gaus) link(identity) Iteration 0: log likelihood = -1330.6004 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = 147.6853 Deviance = 49917.64009 (1/df) Deviance = 147.6853 Pearson = 49917.64009 (1/df) Pearson = 147.6853 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 7.838826 Log likelihood = -1330.6004 BIC = 47947.46 ------------------------------------------------------------------------------ | OIM age | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew2 | .5832314 .2635871 2.21 0.027 .0666101 1.099853 _cons | 48.62133 .7061562 68.85 0.000 47.23729 50.00537 ------------------------------------------------------------------------------ 804 . 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.) 805 . 806 . glm bf4 avgcumdosew2 if gender==1, fam(gaus) link(identity) Iteration 0: log likelihood = -1027.1225 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = 24.7771 Deviance = 8374.659221 (1/df) Deviance = 24.7771 Pearson = 8374.659221 (1/df) Pearson = 24.7771 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 6.053662 Log likelihood = -1027.122509 BIC = 6404.476 ------------------------------------------------------------------------------ | OIM bf4 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew2 | -.0331637 .1079644 -0.31 0.759 -.2447701 .1784427 _cons | 12.52896 .2892393 43.32 0.000 11.96206 13.09586 ------------------------------------------------------------------------------ 807 . 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.) 808 . 809 . * age is a mediating effect for females for Dose=> Problems with family at ho > me 810 . glm age avgcumdosew2 if gender==2, fam(gaus) link(identity) Iteration 0: log likelihood = -1406.9403 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = 136.9184 Deviance = 49427.52828 (1/df) Deviance = 136.9184 Pearson = 49427.52828 (1/df) Pearson = 136.9184 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 7.762756 Log likelihood = -1406.940271 BIC = 47299.65 ------------------------------------------------------------------------------ | OIM age | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew2 | 1.502324 .4454009 3.37 0.001 .6293547 2.375294 _cons | 48.86944 .7323225 66.73 0.000 47.43412 50.30477 ------------------------------------------------------------------------------ 811 . 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.) 812 . 813 . * bf4 is a mediting effect for females for Dose=> Problems with family at hom > e 814 . glm bf4 avgcumdosew2 if gender==2, fam(gaus) link(identity) Iteration 0: log likelihood = -1109.0983 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = 26.53281 Deviance = 9578.344971 (1/df) Deviance = 26.53281 Pearson = 9578.344971 (1/df) Pearson = 26.53281 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 6.121754 Log likelihood = -1109.098281 BIC = 7450.466 ------------------------------------------------------------------------------ | OIM bf4 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew2 | -.595012 .1960703 -3.03 0.002 -.9793027 -.2107212 _cons | 11.02048 .3223763 34.19 0.000 10.38863 11.65232 ------------------------------------------------------------------------------ 815 . 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.) 816 . 817 . 818 . glm bf40 avgcumdosew2 if gender==2, fam(gaus) link(identity) Iteration 0: log likelihood = -818.51169 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = 5.351378 Deviance = 1931.847477 (1/df) Deviance = 5.351378 Pearson = 1931.847477 (1/df) Pearson = 5.351378 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 4.520726 Log likelihood = -818.5116931 BIC = -196.0319 ------------------------------------------------------------------------------ | OIM bf40 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew2 | .1794903 .0880548 2.04 0.042 .0069061 .3520745 _cons | 3.004543 .1447786 20.75 0.000 2.720783 3.288304 ------------------------------------------------------------------------------ 819 . 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.) 820 . 821 . scalar PrbfmhmMedMw2 = "age" 822 . scalar PrbfmhmMedFw2 = "age bf4" 823 . * Summary of dose=problems with family at home mediating effects 824 . * males mediators age 1 825 . * females mediators age and BSIsoma rescaled (bf4) 2 826 . 827 . title4 "4. Summary matrix for problems with family at home" ------------------------------------------------------------------------------- 4. Summary matrix for problems with family at home ------------------------------------------------------------------------------- 828 . matrix define prbfamMw2 = J(1,8, 0) 829 . matrix define prbfamFw2 = J(1,8, 0) 830 . matrix colnames prbfamMw2= hypnum ptnum wave gender medsig numMAsig numModsi > g numMed 831 . matrix colnames prbfamFw2= hypnum ptnum wave gender medsig numMAsig > numModsig numMed 832 . matrix define prbfamMw2= (1, 2, 3, 1, 0, 3, 0, 1 ) 833 . matrix define prbfamFw2= (1, 2, 3, 2, 1, 3, 0, 2) 834 . matrix rowname prbfamMw2 = prbfamMw2 835 . matrix rowname prbfamFw2 = prbfamFw2 836 . matlist prbfamMw2 | c1 c2 c3 c4 c5 c6 > c7 c8 -------------+----------------------------------------------------------------- ----------------------- prbfamMw2 | 1 2 3 1 0 3 > 0 1 837 . matlist prbfamFw2 | c1 c2 c3 c4 c5 c6 > c7 c8 -------------+----------------------------------------------------------------- ----------------------- prbfamFw2 | 1 2 3 2 1 3 > 0 2 838 . matrix define H1pt2w2 = ( wkMw2 \ wkFw2 \ hmcrMw2 \ hmcrFw2 \ spMw2 \ > spFw2 \ prbfamMw2 \ prbfamFw2) 839 . 840 . matlist H1pt2w2 | c1 c2 c3 c4 c5 c6 > c7 c8 -------------+----------------------------------------------------------------- ----------------------- r1 | 1 2 2 1 0 2 > 0 2 r1 | 1 2 2 2 0 1 > 0 2 r1 | 1 2 3 1 0 1 > 0 1 r1 | 1 2 3 2 0 1 > 0 1 spMw2 | 1 2 3 1 0 4 > 0 1 spFw2 | 1 2 3 2 1 5 > 0 2 prbfamMw2 | 1 2 3 1 0 3 > 0 1 prbfamFw2 | 1 2 3 2 1 3 > 0 2 841 . matrix colnames H1pt2w2 = hypnum ptnum wave gender medsig numMAsig numMo > dsig numMed 842 . matrix rownames H1pt2w2 = wkMw2 wkFw2 hmcrMw2 hmcrFw2 prbsocMw2 prbsocF > w2 prbfhmMw2 prbfhmFw2 843 . matlist H1pt2w2 | hypnum ptnum wave gender medsig numMAsig > numModsig numMed -------------+----------------------------------------------------------------- ----------------------- wkMw2 | 1 2 2 1 0 2 > 0 2 wkFw2 | 1 2 2 2 0 1 > 0 2 hmcrMw2 | 1 2 3 1 0 1 > 0 1 hmcrFw2 | 1 2 3 2 0 1 > 0 1 prbsocMw2 | 1 2 3 1 0 4 > 0 1 prbsocFw2 | 1 2 3 2 1 5 > 0 2 prbfhmMw2 | 1 2 3 1 0 3 > 0 1 prbfhmFw2 | 1 2 3 2 1 3 > 0 2 844 . 845 . 846 . *---------------------------------------------------------------------------- > --- 847 . ***************************************************************************** > *** 848 . *-------Chunk 7 Dose==> problems with sex life impact 849 . * Chunk 7 General model for all part 2 of Nottingham Health Profile 850 . 851 . title "5. H1 pt 2 Wave 2 part2 H1 dose sex life impact" ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** 5. H1 pt 2 Wave 2 part2 H1 dose sex life impact ***** ***** ***** ***** ***** ***** 16 Jun 2012 21:56:19 ***** ******************************************************************************* ******************************************************************************* 852 . 853 . forvalues j = 2/2 { 2. set more off 3. 854 . des age educ1-educ7 marrw`j'1-marrw`j'6 inc1w`j'-inc4w`j' /// > bf1 bf4 bf9 bf11 bf4m bf15m bf30 bf40 4. 855 . foreach var in HP2sxlife { 5. forvalues k=1/2 { 6. local w2bf bf1 bf4 bf6 bf7 bf14 bf15 bf40 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. 856 . di _skip(4) 10. 857 . 858 . 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 radhlw2 if gender==`k', coef difficult iterate(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 marrw21 byte %8.0g marrw2==1. single marrw22 byte %8.0g marrw2==2. cohabitating marrw23 byte %8.0g marrw2==3. married marrw24 byte %8.0g marrw2==4. separated marrw25 byte %8.0g marrw2==5. divorced marrw26 byte %8.0g marrw2==6. widowed inc1w2 double %15.0g LABJ Income is not sufficient for basic neccessities in 1996 inc2w2 double %15.0g LABJ Income is just sufficient for basic neccessities in 1996 inc3w2 double %15.0g LABJ Income is sufficient for basics plus extra purchases/savings in 1996 inc4w2 double %15.0g LABJ Income allows to comfortably afford luxury items in 1996 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= 2 ***** ***** chunk 7 H1 test:Gender= 1 model Wave = 2 for HP2pbfhm ***** ***** ***** ***** ***** ***** 16 Jun 2012 21:56:19 ***** ******************************************************************************* ******************************************************************************* i.educ _Ieduc_1-8 (naturally coded; _Ieduc_1 omitted) note: _Ieduc_4 != 0 predicts failure perfectly _Ieduc_4 dropped and 12 obs not used note: _Ieduc_7 != 0 predicts failure perfectly _Ieduc_7 dropped and 4 obs not used note: occ8w2 != 0 predicts failure perfectly occ8w2 dropped and 43 obs not used note: marrw22 != 0 predicts failure perfectly marrw22 dropped and 8 obs not used note: marrw25 != 0 predicts failure perfectly marrw25 dropped and 4 obs not used note: inc4w2 != 0 predicts failure perfectly inc4w2 dropped and 9 obs not used note: dvcew2 != 0 predicts failure perfectly dvcew2 dropped and 3 obs not used note: sepaw2 != 0 predicts failure perfectly sepaw2 dropped and 1 obs not used note: _Ieduc_8 omitted because of collinearity note: bf15 omitted because of collinearity note: radhlw2 omitted because of collinearity Logistic regression Number of obs = 248 LR chi2(38) = 124.45 Prob > chi2 = 0.0000 Log likelihood = -81.459667 Pseudo R2 = 0.4331 ------------------------------------------------------------------------------ HP2sxlife | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .045416 .0245513 1.85 0.064 -.0027037 .0935357 _Ieduc_2 | -.0646877 2.529828 -0.03 0.980 -5.02306 4.893684 _Ieduc_3 | -.2043117 2.425172 -0.08 0.933 -4.957562 4.548938 _Ieduc_4 | 0 (omitted) _Ieduc_5 | .5468814 2.47638 0.22 0.825 -4.306734 5.400497 _Ieduc_6 | -.5396204 2.395021 -0.23 0.822 -5.233776 4.154535 _Ieduc_7 | 0 (omitted) _Ieduc_8 | 0 (omitted) occ1w2 | -.914781 4.041769 -0.23 0.821 -8.836503 7.006941 occ2w2 | -1.085289 4.050896 -0.27 0.789 -9.024899 6.854322 occ3w2 | -2.01676 4.099586 -0.49 0.623 -10.0518 6.018282 occ4w2 | -1.281739 4.07837 -0.31 0.753 -9.275197 6.711719 occ5w2 | -2.386463 4.187943 -0.57 0.569 -10.59468 5.821754 occ6w2 | 1.041656 4.356584 0.24 0.811 -7.497091 9.580403 occ7w2 | -.2042994 4.128602 -0.05 0.961 -8.296212 7.887613 occ8w2 | 0 (omitted) marrw21 | 11.19923 1268.681 0.01 0.993 -2475.369 2497.767 marrw22 | 0 (omitted) marrw23 | 11.00787 1268.681 0.01 0.993 -2475.56 2497.576 marrw25 | 0 (omitted) marrw26 | 9.989133 1268.682 0.01 0.994 -2476.582 2496.56 inc1w2 | 2.592204 4.16321 0.62 0.534 -5.567537 10.75195 inc2w2 | 3.029964 4.086266 0.74 0.458 -4.978969 11.0389 inc3w2 | 2.803138 4.089233 0.69 0.493 -5.211611 10.81789 inc4w2 | 0 (omitted) radhlw2 | .0158792 .0090915 1.75 0.081 -.0019397 .0336982 havmil | -.0002765 .0085069 -0.03 0.974 -.0169497 .0163966 avgcumdosew2 | -.0370642 .0826057 -0.45 0.654 -.1989685 .1248401 bf1 | .0019651 .0129727 0.15 0.880 -.0234608 .0273911 bf4 | -.2487796 .05911 -4.21 0.000 -.3646331 -.1329261 bf6 | .0163867 .0108586 1.51 0.131 -.0048957 .0376692 bf7 | .0671464 .105745 0.63 0.525 -.1401099 .2744028 bf14 | -.0000488 .0000798 -0.61 0.541 -.0002053 .0001076 bf15 | 0 (omitted) bf40 | .3417099 .1521463 2.25 0.025 .0435086 .6399112 deaw2 | .0342021 .3561465 0.10 0.923 -.6638321 .7322364 dvcew2 | 0 (omitted) sepaw2 | 0 (omitted) accdw2 | -.0684013 .5282538 -0.13 0.897 -1.10376 .9669571 movew2 | .1688384 .5667796 0.30 0.766 -.9420292 1.279706 illw2 | .2358444 .3235455 0.73 0.466 -.398293 .8699819 shfamw2 | -.0126799 .0083767 -1.51 0.130 -.0290979 .0037381 shhlw2 | -.01343 .0100141 -1.34 0.180 -.0330573 .0061973 shjobw2 | .0172317 .0096379 1.79 0.074 -.0016582 .0361216 shrelaw2 | -.0093206 .0085022 -1.10 0.273 -.0259847 .0073434 suprtw2 | .0077123 .0077451 1.00 0.319 -.0074679 .0228925 suchrw2 | .0029045 .0070402 0.41 0.680 -.0108941 .016703 havmilsq | -1.32e-06 .0000139 -0.10 0.924 -.0000286 .0000259 radhlw2 | 0 (omitted) _cons | -16.32451 1268.684 -0.01 0.990 -2502.9 2470.251 ------------------------------------------------------------------------------ Logistic model for HP2sxlife -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 47 15 | 62 - | 19 167 | 186 -----------+--------------------------+----------- Total | 66 182 | 248 Classified + if predicted Pr(D) >= .5 True D defined as HP2sxlife != 0 -------------------------------------------------- Sensitivity Pr( +| D) 71.21% Specificity Pr( -|~D) 91.76% Positive predictive value Pr( D| +) 75.81% Negative predictive value Pr(~D| -) 89.78% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 8.24% False - rate for true D Pr( -| D) 28.79% False + rate for classified + Pr(~D| +) 24.19% False - rate for classified - Pr( D| -) 10.22% -------------------------------------------------- Correctly classified 86.29% -------------------------------------------------- Logistic model for HP2sxlife, goodness-of-fit test number of observations = 248 number of covariate patterns = 248 Pearson chi2(209) = 320.07 Prob > chi2 = 0.0000 Measures of Fit for logistic of HP2sxlife Log-Lik Intercept Only: -143.684 Log-Lik Full Model: -81.460 D(198): 162.919 LR(38): 124.448 Prob > LR: 0.000 McFadden's R2: 0.433 McFadden's Adj R2: 0.085 Maximum Likelihood R2: 0.395 Cragg & Uhler's R2: 0.575 McKelvey and Zavoina's R2: 0.701 Efron's R2: 0.489 Variance of y*: 11.005 Variance of error: 3.290 Count R2: 0.863 Adj Count R2: 0.485 AIC: 1.060 AIC*n: 262.919 BIC: -928.740 BIC': 85.062 ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Full Nottingham Part 2 subscale models for male & females ***** ***** Full main model for HP2sxlife for wave= 2 ***** ***** chunk 7 H1 test:Gender= 2 model Wave = 2 for HP2sxlife ***** ***** ***** ***** ***** ***** 16 Jun 2012 21:56:20 ***** ******************************************************************************* ******************************************************************************* i.educ _Ieduc_1-8 (naturally coded; _Ieduc_1 omitted) note: _Ieduc_8 omitted because of collinearity note: marrw26 omitted because of collinearity note: bf15 omitted because of collinearity note: radhlw2 omitted because of collinearity Logistic regression Number of obs = 362 LR chi2(45) = 172.53 Prob > chi2 = 0.0000 Log likelihood = -119.99963 Pseudo R2 = 0.4182 ------------------------------------------------------------------------------ HP2sxlife | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0946676 .020348 4.65 0.000 .0547862 .1345489 _Ieduc_2 | -12.06916 856.9725 -0.01 0.989 -1691.704 1667.566 _Ieduc_3 | -10.96566 856.9724 -0.01 0.990 -1690.601 1668.669 _Ieduc_4 | -10.2721 856.9727 -0.01 0.990 -1689.908 1669.364 _Ieduc_5 | -11.78295 856.9726 -0.01 0.989 -1691.418 1667.853 _Ieduc_6 | -10.87488 856.9725 -0.01 0.990 -1690.51 1668.76 _Ieduc_7 | -10.54712 856.9809 -0.01 0.990 -1690.199 1669.105 _Ieduc_8 | 0 (omitted) occ1w2 | -1.924676 1.67129 -1.15 0.249 -5.200344 1.350992 occ2w2 | -1.071334 1.695639 -0.63 0.528 -4.394725 2.252058 occ3w2 | -.4988122 1.696518 -0.29 0.769 -3.823926 2.826301 occ4w2 | -.6837643 1.779367 -0.38 0.701 -4.171259 2.803731 occ5w2 | -.8653809 1.874647 -0.46 0.644 -4.539621 2.80886 occ6w2 | -1.70777 1.969995 -0.87 0.386 -5.568889 2.153348 occ7w2 | -.9209399 1.641247 -0.56 0.575 -4.137725 2.295845 occ8w2 | -.5235734 1.936624 -0.27 0.787 -4.319287 3.272141 marrw21 | -.4474367 1.15873 -0.39 0.699 -2.718505 1.823632 marrw22 | -.2713813 1.430959 -0.19 0.850 -3.07601 2.533247 marrw23 | -.6859987 .8247327 -0.83 0.406 -2.302445 .9304478 marrw25 | -1.534831 1.287976 -1.19 0.233 -4.059218 .9895558 marrw26 | 0 (omitted) inc1w2 | .1793057 1.714781 0.10 0.917 -3.181602 3.540214 inc2w2 | .5322943 1.648367 0.32 0.747 -2.698446 3.763035 inc3w2 | -.4148838 1.696991 -0.24 0.807 -3.740924 2.911157 inc4w2 | -.3610821 2.088477 -0.17 0.863 -4.454421 3.732257 radhlw2 | .0084415 .0066869 1.26 0.207 -.0046645 .0215475 havmil | -.0012719 .0033206 -0.38 0.702 -.0077802 .0052364 avgcumdosew2 | .131101 .1238204 1.06 0.290 -.1115826 .3737846 bf1 | -.0011966 .0090476 -0.13 0.895 -.0189295 .0165364 bf4 | -.1626538 .0410542 -3.96 0.000 -.2431185 -.0821891 bf6 | -.0040259 .0075131 -0.54 0.592 -.0187513 .0106995 bf7 | -.07395 .0811067 -0.91 0.362 -.2329163 .0850162 bf14 | -.000028 .0000759 -0.37 0.712 -.0001769 .0001208 bf15 | 0 (omitted) bf40 | .0142117 .0784184 0.18 0.856 -.1394855 .1679089 deaw2 | .0365782 .2150994 0.17 0.865 -.3850089 .4581654 dvcew2 | -.8025004 1.585115 -0.51 0.613 -3.909268 2.304268 sepaw2 | -.5574826 2.582905 -0.22 0.829 -5.619883 4.504918 accdw2 | -.5477504 .6503834 -0.84 0.400 -1.822478 .7269777 movew2 | .1966685 .5120534 0.38 0.701 -.8069378 1.200275 illw2 | .5493357 .2439985 2.25 0.024 .0711074 1.027564 shfamw2 | .0017721 .0066016 0.27 0.788 -.0111667 .0147109 shhlw2 | .0069859 .006691 1.04 0.296 -.0061281 .0201 shjobw2 | -.0075261 .0063225 -1.19 0.234 -.019918 .0048658 shrelaw2 | -.0137558 .0073868 -1.86 0.063 -.0282337 .000722 suprtw2 | -.0141433 .0055222 -2.56 0.010 -.0249667 -.0033199 suchrw2 | .0162332 .0063006 2.58 0.010 .0038842 .0285821 havmilsq | -1.92e-07 2.92e-06 -0.07 0.948 -5.91e-06 5.53e-06 radhlw2 | 0 (omitted) _cons | 7.796544 856.9744 0.01 0.993 -1671.842 1687.436 ------------------------------------------------------------------------------ Logistic model for HP2sxlife -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 59 19 | 78 - | 34 250 | 284 -----------+--------------------------+----------- Total | 93 269 | 362 Classified + if predicted Pr(D) >= .5 True D defined as HP2sxlife != 0 -------------------------------------------------- Sensitivity Pr( +| D) 63.44% Specificity Pr( -|~D) 92.94% Positive predictive value Pr( D| +) 75.64% Negative predictive value Pr(~D| -) 88.03% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 7.06% False - rate for true D Pr( -| D) 36.56% False + rate for classified + Pr(~D| +) 24.36% False - rate for classified - Pr( D| -) 11.97% -------------------------------------------------- Correctly classified 85.36% -------------------------------------------------- Logistic model for HP2sxlife, goodness-of-fit test number of observations = 362 number of covariate patterns = 362 Pearson chi2(316) = 350.60 Prob > chi2 = 0.0877 Measures of Fit for logistic of HP2sxlife Log-Lik Intercept Only: -206.266 Log-Lik Full Model: -120.000 D(312): 239.999 LR(45): 172.533 Prob > LR: 0.000 McFadden's R2: 0.418 McFadden's Adj R2: 0.176 Maximum Likelihood R2: 0.379 Cragg & Uhler's R2: 0.557 McKelvey and Zavoina's R2: 0.643 Efron's R2: 0.461 Variance of y*: 9.209 Variance of error: 3.290 Count R2: 0.854 Adj Count R2: 0.430 AIC: 0.939 AIC*n: 339.999 BIC: -1598.194 BIC': 92.591 859 . 860 . *-----Chunk 7 dose3 moderator => sex life impact---------------------------- 861 . title4 "Chunk 7 trimmed male model of dose=>HP2sxlife relationship in Wave 2" > ------------------------------------------------------------------------------- Chunk 7 trimmed male model of dose=>HP2sxlife relationship in Wave 2 ------------------------------------------------------------------------------- 862 . 863 . 864 . forvalues j = 2/2 { 2. di as input "trimmed HP2sexlife main effects models wave 1 for H1 part 2 > with dose ns" 3. di as input "Wave 2 male dose avgcumdosew`j' main effect not signif" 4. logit HP2sxlife age bf4 bf40 shjobw`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 2 male dose avgcumdosew2 main effect not signif Iteration 0: log likelihood = -171.28676 Iteration 1: log likelihood = -117.28391 Iteration 2: log likelihood = -108.55607 Iteration 3: log likelihood = -108.27099 Iteration 4: log likelihood = -108.27006 Iteration 5: log likelihood = -108.27006 Logistic regression Number of obs = 339 LR chi2(8) = 126.03 Prob > chi2 = 0.0000 Log likelihood = -108.27006 Pseudo R2 = 0.3679 ------------------------------------------------------------------------------ HP2sxlife | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0687125 .0166236 4.13 0.000 .0361309 .1012942 bf4 | -.1779816 .0384634 -4.63 0.000 -.2533685 -.1025948 bf40 | .2602103 .1044849 2.49 0.013 .0554237 .4649968 shjobw2 | .0126418 .0053828 2.35 0.019 .0020917 .0231919 havmilsq | -2.87e-06 4.95e-06 -0.58 0.562 -.0000126 6.84e-06 shrelaw2 | -.0153172 .0059888 -2.56 0.011 -.027055 -.0035795 avgcumdosew2 | .0633372 .0462428 1.37 0.171 -.0272971 .1539714 radhlw2 | .0102997 .0056666 1.82 0.069 -.0008065 .021406 _cons | -4.654056 1.220985 -3.81 0.000 -7.047141 -2.26097 ------------------------------------------------------------------------------ Logistic model for HP2sxlife -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 35 15 | 50 - | 34 255 | 289 -----------+--------------------------+----------- Total | 69 270 | 339 Classified + if predicted Pr(D) >= .5 True D defined as HP2sxlife != 0 -------------------------------------------------- Sensitivity Pr( +| D) 50.72% Specificity Pr( -|~D) 94.44% Positive predictive value Pr( D| +) 70.00% Negative predictive value Pr(~D| -) 88.24% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 5.56% False - rate for true D Pr( -| D) 49.28% False + rate for classified + Pr(~D| +) 30.00% False - rate for classified - Pr( D| -) 11.76% -------------------------------------------------- Correctly classified 85.55% -------------------------------------------------- Logistic model for HP2sxlife, goodness-of-fit test number of observations = 339 number of covariate patterns = 337 Pearson chi2(328) = 260.62 Prob > chi2 = 0.9975 Measures of Fit for logit of HP2sxlife Log-Lik Intercept Only: -171.287 Log-Lik Full Model: -108.270 D(330): 216.540 LR(8): 126.033 Prob > LR: 0.000 McFadden's R2: 0.368 McFadden's Adj R2: 0.315 Maximum Likelihood R2: 0.310 Cragg & Uhler's R2: 0.488 McKelvey and Zavoina's R2: 0.542 Efron's R2: 0.376 Variance of y*: 7.180 Variance of error: 3.290 Count R2: 0.855 Adj Count R2: 0.290 AIC: 0.692 AIC*n: 234.540 BIC: -1706.040 BIC': -79.425 865 . title "Chunk 7 trimmed male model of dose and HP2sxlife relationship in Wave > 2" ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** *****Chunk 7 trimmed male model of dose and HP2sxlife relationship in Wave 2*** > ** ***** ***** ***** ***** ***** 16 Jun 2012 21:56:23 ***** ******************************************************************************* ******************************************************************************* 866 . title4 "h1 pt 2 wave 2 dose=> sex life impact on males" ------------------------------------------------------------------------------- h1 pt 2 wave 2 dose=> sex life impact on males ------------------------------------------------------------------------------- 867 . forvalues j = 2/2 { 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 2 male dose avgcumdosew`j' main effect not signif" 5. logit HP2sxlife age bf4 shjobw`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 2 male dose avgcumdosew2 main effect not signif Iteration 0: log likelihood = -171.51396 Iteration 1: log likelihood = -121.92704 Iteration 2: log likelihood = -115.34124 Iteration 3: log likelihood = -115.14995 Iteration 4: log likelihood = -115.14978 Iteration 5: log likelihood = -115.14978 Logistic regression Number of obs = 340 LR chi2(4) = 112.73 Prob > chi2 = 0.0000 Log likelihood = -115.14978 Pseudo R2 = 0.3286 ------------------------------------------------------------------------------ HP2sxlife | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0762792 .0158518 4.81 0.000 .0452103 .1073481 bf4 | -.1600963 .0362278 -4.42 0.000 -.2311015 -.089091 shjobw2 | .0087009 .0044966 1.93 0.053 -.0001123 .0175141 radhlw2 | .0099572 .0054074 1.84 0.066 -.0006412 .0205555 _cons | -4.702059 1.167186 -4.03 0.000 -6.989701 -2.414417 ------------------------------------------------------------------------------ Logistic model for HP2sxlife -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 33 13 | 46 - | 36 258 | 294 -----------+--------------------------+----------- Total | 69 271 | 340 Classified + if predicted Pr(D) >= .5 True D defined as HP2sxlife != 0 -------------------------------------------------- Sensitivity Pr( +| D) 47.83% Specificity Pr( -|~D) 95.20% Positive predictive value Pr( D| +) 71.74% Negative predictive value Pr(~D| -) 87.76% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 4.80% False - rate for true D Pr( -| D) 52.17% False + rate for classified + Pr(~D| +) 28.26% False - rate for classified - Pr( D| -) 12.24% -------------------------------------------------- Correctly classified 85.59% -------------------------------------------------- Logistic model for HP2sxlife, goodness-of-fit test number of observations = 340 number of covariate patterns = 330 Pearson chi2(325) = 274.79 Prob > chi2 = 0.9800 Measures of Fit for logit of HP2sxlife Log-Lik Intercept Only: -171.514 Log-Lik Full Model: -115.150 D(335): 230.300 LR(4): 112.728 Prob > LR: 0.000 McFadden's R2: 0.329 McFadden's Adj R2: 0.299 Maximum Likelihood R2: 0.282 Cragg & Uhler's R2: 0.444 McKelvey and Zavoina's R2: 0.483 Efron's R2: 0.343 Variance of y*: 6.366 Variance of error: 3.290 Count R2: 0.856 Adj Count R2: 0.290 AIC: 0.707 AIC*n: 240.300 BIC: -1722.397 BIC': -89.413 868 . 869 . scalar MainEffsxlifeMw2 = "age bf4" 870 . scalar SigDosesxlifeMw2 = "no" 871 . 872 . 873 . forvalues j = 2/2 { 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 2 for H1 part 2 with dose ns*** > ** ***** ***** ***** ***** ***** 16 Jun 2012 21:56:25 ***** ******************************************************************************* ******************************************************************************* ------------------------------------------------------------------------------- title2: Wave `j dose HPsxlife relationship but avgcumdosew2: Dose not signif Date and time: 16 Jun 2012 21:56:25 Working directory: /Users/robertyaffee/ > Documents/data/research/chwk/phase3/Htests/h1tests/h1pt2 Stata data file: chwide16june2012.dta > has 2387 variables and 703 observations Wave `j dose HPsxlife relationship but avgcumdosew2: Dose not signif ------------------------------------------------------------------------------- 874 . 875 . 876 . cap gen radhlw2Xd2 = radhlw2*avgcumdosew2 877 . 878 . set more off 879 . des bf4 storage display value variable name type format label variable label ------------------------------------------------------------------------------- bf4 float %9.0g bf4 = max(0, 24 - BSIsoma) 880 . forvalues j = 2/2 { 2. sw, pr(.1):logistic HP2sxlife age bf4 /// > avgcumdosew`j' ageXd2 b4Xd2 if gender==1, coef 3. estat class 4. estat gof 5. fitstat 6. } begin with full model p = 0.6489 >= 0.1000 removing b4Xd2 p = 0.1447 >= 0.1000 removing avgcumdosew2 p = 0.1083 >= 0.1000 removing ageXd2 Logistic regression Number of obs = 340 LR chi2(2) = 105.30 Prob > chi2 = 0.0000 Log likelihood = -118.86164 Pseudo R2 = 0.3070 ------------------------------------------------------------------------------ HP2sxlife | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0735516 .0151718 4.85 0.000 .0438154 .1032879 bf4 | -.2011944 .0322322 -6.24 0.000 -.2643683 -.1380205 _cons | -3.058766 .9461336 -3.23 0.001 -4.913154 -1.204378 ------------------------------------------------------------------------------ Logistic model for HP2sxlife -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 32 14 | 46 - | 37 257 | 294 -----------+--------------------------+----------- Total | 69 271 | 340 Classified + if predicted Pr(D) >= .5 True D defined as HP2sxlife != 0 -------------------------------------------------- Sensitivity Pr( +| D) 46.38% Specificity Pr( -|~D) 94.83% Positive predictive value Pr( D| +) 69.57% Negative predictive value Pr(~D| -) 87.41% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 5.17% False - rate for true D Pr( -| D) 53.62% False + rate for classified + Pr(~D| +) 30.43% False - rate for classified - Pr( D| -) 12.59% -------------------------------------------------- Correctly classified 85.00% -------------------------------------------------- Logistic model for HP2sxlife, goodness-of-fit test number of observations = 340 number of covariate patterns = 222 Pearson chi2(219) = 215.06 Prob > chi2 = 0.5625 Measures of Fit for logistic of HP2sxlife Log-Lik Intercept Only: -171.514 Log-Lik Full Model: -118.862 D(337): 237.723 LR(2): 105.305 Prob > LR: 0.000 McFadden's R2: 0.307 McFadden's Adj R2: 0.289 Maximum Likelihood R2: 0.266 Cragg & Uhler's R2: 0.419 McKelvey and Zavoina's R2: 0.435 Efron's R2: 0.320 Variance of y*: 5.825 Variance of error: 3.290 Count R2: 0.850 Adj Count R2: 0.261 AIC: 0.717 AIC*n: 243.723 BIC: -1726.631 BIC': -93.647 881 . 882 . scalar sxlifeModMw2 = "none" 883 . *xx male moderators: no main significant dose effect 884 . *xx no male moderators for sexlife impact 885 . 886 . 887 . 888 . title4 "H1 pt2 wave 2 female dose=> sexlife impact models" ------------------------------------------------------------------------------- H1 pt2 wave 2 female dose=> sexlife impact models ------------------------------------------------------------------------------- 889 . 890 . *-----Chunk 7 dose3 moderator => sex life impact---------------------------- 891 . di as input "chunk 7 female wave=3" chunk 7 female wave=3 892 . title "Chunk 7 trimmed female model:" "dose and HP2sxlife relationship in Wav > e 2" ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Chunk 7 trimmed female model: ***** ***** dose and HP2sxlife relationship in Wave 2 ***** ***** ***** ***** ***** ***** 16 Jun 2012 21:56:31 ***** ******************************************************************************* ******************************************************************************* 893 . * female models 894 . forvalues j = 2/2 { 2. 895 . set more off 3. des bf4 bf4m shfamw2 shrelaw2 avgcumdosew2 4. title "trimmed HP2sexlife main effects models" "Wave 2 for H1 part 2 with > dose ns" 5. title "Wave 2 dose HP2sexlife relationship" "avgcumdosew`j' Dose not signi > f" 6. logit HP2sxlife age radhlw`j' bf4 bf4m /// > 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) shfamw2 double %8.0g Percentage of strains and hassles related to family in 1996 shrelaw2 double %8.0g Percentage of strains and hassles related to relationships in 1996 avgcumdosew2 double %8.0g Average mean dose CS1337 in mGy for wave 2 ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** trimmed HP2sexlife main effects models ***** ***** Wave 2 for H1 part 2 with dose ns ***** ***** ***** ***** ***** ***** 16 Jun 2012 21:56:31 ***** ******************************************************************************* ******************************************************************************* ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Wave 2 dose HP2sexlife relationship ***** ***** avgcumdosew2 Dose not signif ***** ***** ***** ***** ***** ***** 16 Jun 2012 21:56:31 ***** ******************************************************************************* ******************************************************************************* Iteration 0: log likelihood = -207.62116 Iteration 1: log likelihood = -146.12472 Iteration 2: log likelihood = -140.853 Iteration 3: log likelihood = -140.77782 Iteration 4: log likelihood = -140.77773 Iteration 5: log likelihood = -140.77773 Logistic regression Number of obs = 363 LR chi2(6) = 133.69 Prob > chi2 = 0.0000 Log likelihood = -140.77773 Pseudo R2 = 0.3219 ------------------------------------------------------------------------------ HP2sxlife | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0769754 .0151437 5.08 0.000 .0472942 .1066565 radhlw2 | .0086172 .004779 1.80 0.071 -.0007494 .0179837 bf4 | -.5726666 .1897808 -3.02 0.003 -.9446301 -.2007032 bf4m | .3839121 .1738091 2.21 0.027 .0432526 .7245716 shrelaw2 | -.0125758 .0051727 -2.43 0.015 -.0227141 -.0024375 avgcumdosew2 | .1836146 .10587 1.73 0.083 -.0238868 .3911161 _cons | -6.850254 1.580753 -4.33 0.000 -9.948473 -3.752035 ------------------------------------------------------------------------------ Logistic model for HP2sxlife -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 52 21 | 73 - | 42 248 | 290 -----------+--------------------------+----------- Total | 94 269 | 363 Classified + if predicted Pr(D) >= .5 True D defined as HP2sxlife != 0 -------------------------------------------------- Sensitivity Pr( +| D) 55.32% Specificity Pr( -|~D) 92.19% Positive predictive value Pr( D| +) 71.23% Negative predictive value Pr(~D| -) 85.52% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 7.81% False - rate for true D Pr( -| D) 44.68% False + rate for classified + Pr(~D| +) 28.77% False - rate for classified - Pr( D| -) 14.48% -------------------------------------------------- Correctly classified 82.64% -------------------------------------------------- Logistic model for HP2sxlife, goodness-of-fit test number of observations = 363 number of covariate patterns = 362 Pearson chi2(355) = 403.58 Prob > chi2 = 0.0383 Measures of Fit for logit of HP2sxlife Log-Lik Intercept Only: -207.621 Log-Lik Full Model: -140.778 D(356): 281.555 LR(6): 133.687 Prob > LR: 0.000 McFadden's R2: 0.322 McFadden's Adj R2: 0.288 Maximum Likelihood R2: 0.308 Cragg & Uhler's R2: 0.452 McKelvey and Zavoina's R2: 0.478 Efron's R2: 0.375 Variance of y*: 6.297 Variance of error: 3.290 Count R2: 0.826 Adj Count R2: 0.330 AIC: 0.814 AIC*n: 295.555 BIC: -1816.852 BIC': -98.320 896 . scalar SigDoseSxlifeFw2 = "no" 897 . scalar MainEffsxlifeFw2 = "age bf4 bf4m shrelaw2" 898 . *----- constructing possible moderators 899 . 900 . foreach var in bf4 bf4m shfamw2 shrelaw2 radhlw2 { 2. cap gen `var'Xd2 = `var'*avgcumdosew2 3. } 901 . 902 . scalar sxlifeModFw2="none" 903 . scalar SigDoseSxlifeFw2 = "none" 904 . 905 . 906 . 907 . *----- testing female moderators 908 . 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***** ***** ***** ***** ***** ***** 16 Jun 2012 21:56:33 ***** ******************************************************************************* ******************************************************************************* 909 . * male models 910 . forvalues j = 2/2 { 2. set more off 3. des bf4 bf4m shfamw2 shrelaw2 avgcumdosew2 4. title3 "trimmed HP2sexlife main effects models wave 1 for H1 part 2 with d > ose ns" 5. title "Wave 2 dose HP2sexlife relationship but avgcumdosew`j': Dose not si > gnif" 6. logit HP2sxlife age radhlw`j' bf4 bf4m /// > shrelaw`j' avgcumdosew`j' radhlw`j'Xd2 /// > bf4Xd2 shrelaw2Xd2 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) shfamw2 double %8.0g Percentage of strains and hassles related to family in 1996 shrelaw2 double %8.0g Percentage of strains and hassles related to relationships in 1996 avgcumdosew2 double %8.0g Average mean dose CS1337 in mGy for wave 2 ------------------------------------------------------------------------------- title3 : trimmed HP2sexlife main effects models wave 1 for H1 part 2 with dose > ns 16 Jun 2012 21:56:33 computer Macintosh (Intel 64-bit) folder /Users/robertyaffee/Documents/data/research/chwk/phase3/Htests/h1tests/ > h1pt2 Data file chwide16june2012.dta currrently has 2389 variables and 703 obse > rvations ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** *****Wave 2 dose HP2sexlife relationship but avgcumdosew2: Dose not signif***** ***** ***** ***** ***** ***** 16 Jun 2012 21:56:33 ***** ******************************************************************************* ******************************************************************************* Iteration 0: log likelihood = -207.62116 Iteration 1: log likelihood = -145.01324 Iteration 2: log likelihood = -139.93843 Iteration 3: log likelihood = -139.87302 Iteration 4: log likelihood = -139.87291 Iteration 5: log likelihood = -139.87291 Logistic regression Number of obs = 363 LR chi2(9) = 135.50 Prob > chi2 = 0.0000 Log likelihood = -139.87291 Pseudo R2 = 0.3263 ------------------------------------------------------------------------------ HP2sxlife | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0779625 .0152939 5.10 0.000 .047987 .107938 radhlw2 | .0071833 .0055921 1.28 0.199 -.0037771 .0181436 bf4 | -.533151 .1964961 -2.71 0.007 -.9182762 -.1480258 bf4m | .392614 .1782988 2.20 0.028 .0431547 .7420733 shrelaw2 | -.0133384 .005395 -2.47 0.013 -.0239123 -.0027645 avgcumdosew2 | .4391845 .5450022 0.81 0.420 -.6290003 1.507369 radhlw2Xd2 | .0013901 .003188 0.44 0.663 -.0048583 .0076386 bf4Xd2 | -.0618629 .0612139 -1.01 0.312 -.1818399 .0581141 shrelaw2Xd2 | .0011583 .0038869 0.30 0.766 -.0064598 .0087764 _cons | -7.199252 1.672261 -4.31 0.000 -10.47682 -3.921681 ------------------------------------------------------------------------------ Logistic model for HP2sxlife -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 53 22 | 75 - | 41 247 | 288 -----------+--------------------------+----------- Total | 94 269 | 363 Classified + if predicted Pr(D) >= .5 True D defined as HP2sxlife != 0 -------------------------------------------------- Sensitivity Pr( +| D) 56.38% Specificity Pr( -|~D) 91.82% Positive predictive value Pr( D| +) 70.67% Negative predictive value Pr(~D| -) 85.76% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 8.18% False - rate for true D Pr( -| D) 43.62% False + rate for classified + Pr(~D| +) 29.33% False - rate for classified - Pr( D| -) 14.24% -------------------------------------------------- Correctly classified 82.64% -------------------------------------------------- Logistic model for HP2sxlife, goodness-of-fit test number of observations = 363 number of covariate patterns = 362 Pearson chi2(352) = 396.94 Prob > chi2 = 0.0493 Measures of Fit for logit of HP2sxlife Log-Lik Intercept Only: -207.621 Log-Lik Full Model: -139.873 D(353): 279.746 LR(9): 135.496 Prob > LR: 0.000 McFadden's R2: 0.326 McFadden's Adj R2: 0.278 Maximum Likelihood R2: 0.312 Cragg & Uhler's R2: 0.457 McKelvey and Zavoina's R2: 0.494 Efron's R2: 0.378 Variance of y*: 6.506 Variance of error: 3.290 Count R2: 0.826 Adj Count R2: 0.330 AIC: 0.826 AIC*n: 299.746 BIC: -1800.978 BIC': -82.447 911 . // trimming further 912 . title "fully female moderator model of dose & HP2sxlife relationship in wv 3" > ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** *****fully female moderator model of dose & HP2sxlife relationship in wv 3***** ***** ***** ***** ***** ***** 16 Jun 2012 21:56:34 ***** ******************************************************************************* ******************************************************************************* 913 . 914 . 915 . * female models 916 . set more off 917 . forvalues j = 2/2 { 2. des bf4 bf4m shfamw2 shrelaw2 avgcumdosew2 3. title3 "trimmed HP2sexlife main effects models wave 1 for H1 part 2 with d > ose ns" 4. title "Wave 2 dose HP2sexlife relationship but avgcumdosew`j': Dose not si > gnif" 5. logit HP2sxlife age radhlw`j' bf4 bf4m /// > shrelaw2 avgcumdosew`j' /// > shrelaw2Xd2 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) shfamw2 double %8.0g Percentage of strains and hassles related to family in 1996 shrelaw2 double %8.0g Percentage of strains and hassles related to relationships in 1996 avgcumdosew2 double %8.0g Average mean dose CS1337 in mGy for wave 2 ------------------------------------------------------------------------------- title3 : trimmed HP2sexlife main effects models wave 1 for H1 part 2 with dose > ns 16 Jun 2012 21:56:34 computer Macintosh (Intel 64-bit) folder /Users/robertyaffee/Documents/data/research/chwk/phase3/Htests/h1tests/ > h1pt2 Data file chwide16june2012.dta currrently has 2389 variables and 703 obse > rvations ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** *****Wave 2 dose HP2sexlife relationship but avgcumdosew2: Dose not signif***** ***** ***** ***** ***** ***** 16 Jun 2012 21:56:34 ***** ******************************************************************************* ******************************************************************************* Iteration 0: log likelihood = -207.62116 Iteration 1: log likelihood = -146.12105 Iteration 2: log likelihood = -140.81793 Iteration 3: log likelihood = -140.73921 Iteration 4: log likelihood = -140.73912 Iteration 5: log likelihood = -140.73912 Logistic regression Number of obs = 363 LR chi2(7) = 133.76 Prob > chi2 = 0.0000 Log likelihood = -140.73912 Pseudo R2 = 0.3221 ------------------------------------------------------------------------------ HP2sxlife | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0775834 .015309 5.07 0.000 .0475783 .1075885 radhlw2 | .0085759 .0047788 1.79 0.073 -.0007904 .0179422 bf4 | -.5709149 .1910856 -2.99 0.003 -.9454358 -.196394 bf4m | .3832611 .1751198 2.19 0.029 .0400325 .7264896 shrelaw2 | -.0128344 .0052527 -2.44 0.015 -.0231295 -.0025393 avgcumdosew2 | .1046963 .2957905 0.35 0.723 -.4750423 .684435 shrelaw2Xd2 | .0009557 .0034004 0.28 0.779 -.0057089 .0076203 _cons | -6.861211 1.589531 -4.32 0.000 -9.976634 -3.745788 ------------------------------------------------------------------------------ Logistic model for HP2sxlife -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 52 22 | 74 - | 42 247 | 289 -----------+--------------------------+----------- Total | 94 269 | 363 Classified + if predicted Pr(D) >= .5 True D defined as HP2sxlife != 0 -------------------------------------------------- Sensitivity Pr( +| D) 55.32% Specificity Pr( -|~D) 91.82% Positive predictive value Pr( D| +) 70.27% Negative predictive value Pr(~D| -) 85.47% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 8.18% False - rate for true D Pr( -| D) 44.68% False + rate for classified + Pr(~D| +) 29.73% False - rate for classified - Pr( D| -) 14.53% -------------------------------------------------- Correctly classified 82.37% -------------------------------------------------- Logistic model for HP2sxlife, goodness-of-fit test number of observations = 363 number of covariate patterns = 362 Pearson chi2(354) = 402.93 Prob > chi2 = 0.0371 Measures of Fit for logit of HP2sxlife Log-Lik Intercept Only: -207.621 Log-Lik Full Model: -140.739 D(355): 281.478 LR(7): 133.764 Prob > LR: 0.000 McFadden's R2: 0.322 McFadden's Adj R2: 0.284 Maximum Likelihood R2: 0.308 Cragg & Uhler's R2: 0.452 McKelvey and Zavoina's R2: 0.477 Efron's R2: 0.375 Variance of y*: 6.292 Variance of error: 3.290 Count R2: 0.824 Adj Count R2: 0.319 AIC: 0.819 AIC*n: 297.478 BIC: -1811.035 BIC': -92.503 918 . * female models 919 . forvalues j = 2/2 { 2. des bf4 bf4m shfamw2 shrelaw2 avgcumdosew2 3. title3 "trimmed HP2sexlife main effects models wave 1 for H1 part 2 with d > ose ns" 4. title "Wave 2 dose HP2sexlife relationship but avgcumdosew`j': Dose not si > gnif" 5. logit HP2sxlife age radhlw`j' bf4 bf4m /// > shrelaw2 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) shfamw2 double %8.0g Percentage of strains and hassles related to family in 1996 shrelaw2 double %8.0g Percentage of strains and hassles related to relationships in 1996 avgcumdosew2 double %8.0g Average mean dose CS1337 in mGy for wave 2 ------------------------------------------------------------------------------- title3 : trimmed HP2sexlife main effects models wave 1 for H1 part 2 with dose > ns 16 Jun 2012 21:56:35 computer Macintosh (Intel 64-bit) folder /Users/robertyaffee/Documents/data/research/chwk/phase3/Htests/h1tests/ > h1pt2 Data file chwide16june2012.dta currrently has 2389 variables and 703 obse > rvations ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** *****Wave 2 dose HP2sexlife relationship but avgcumdosew2: Dose not signif***** ***** ***** ***** ***** ***** 16 Jun 2012 21:56:35 ***** ******************************************************************************* ******************************************************************************* Iteration 0: log likelihood = -206.26609 Iteration 1: log likelihood = -147.80582 Iteration 2: log likelihood = -142.56802 Iteration 3: log likelihood = -142.50325 Iteration 4: log likelihood = -142.50319 Iteration 5: log likelihood = -142.50319 Logistic regression Number of obs = 362 LR chi2(6) = 127.53 Prob > chi2 = 0.0000 Log likelihood = -142.50319 Pseudo R2 = 0.3091 ------------------------------------------------------------------------------ HP2sxlife | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0773867 .0151879 5.10 0.000 .0476189 .1071545 radhlw2 | .0092803 .0047101 1.97 0.049 .0000487 .0185119 bf4 | -.5791652 .1890895 -3.06 0.002 -.9497739 -.2085566 bf4m | .3860275 .1731752 2.23 0.026 .0466104 .7254445 shrelaw2 | -.0111587 .0058224 -1.92 0.055 -.0225703 .000253 shfamw2 | -.0012219 .005072 -0.24 0.810 -.0111628 .008719 _cons | -6.703691 1.604696 -4.18 0.000 -9.848837 -3.558545 ------------------------------------------------------------------------------ Logistic model for HP2sxlife -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 49 23 | 72 - | 44 246 | 290 -----------+--------------------------+----------- Total | 93 269 | 362 Classified + if predicted Pr(D) >= .5 True D defined as HP2sxlife != 0 -------------------------------------------------- Sensitivity Pr( +| D) 52.69% Specificity Pr( -|~D) 91.45% Positive predictive value Pr( D| +) 68.06% Negative predictive value Pr(~D| -) 84.83% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 8.55% False - rate for true D Pr( -| D) 47.31% False + rate for classified + Pr(~D| +) 31.94% False - rate for classified - Pr( D| -) 15.17% -------------------------------------------------- Correctly classified 81.49% -------------------------------------------------- Logistic model for HP2sxlife, goodness-of-fit test number of observations = 362 number of covariate patterns = 357 Pearson chi2(350) = 401.39 Prob > chi2 = 0.0301 Measures of Fit for logit of HP2sxlife Log-Lik Intercept Only: -206.266 Log-Lik Full Model: -142.503 D(355): 285.006 LR(6): 127.526 Prob > LR: 0.000 McFadden's R2: 0.309 McFadden's Adj R2: 0.275 Maximum Likelihood R2: 0.297 Cragg & Uhler's R2: 0.437 McKelvey and Zavoina's R2: 0.465 Efron's R2: 0.360 Variance of y*: 6.146 Variance of error: 3.290 Count R2: 0.815 Adj Count R2: 0.280 AIC: 0.826 AIC*n: 299.006 BIC: -1806.527 BIC': -92.176 920 . 921 . scalar MainEffsxlifeFw2 = "age radhlw2 bf4 bf4m" 922 . scalar SigDoseSxlifeFw2="no" 923 . scalar SxLifeModFw2 = "no" 924 . * xx female main effects model: no sign dose main effect 925 . * xx 6 signif main effects 926 . * xx no moderator effects significant 927 . 928 . title4 "h1 pt 2 wave 2 dose-> sexlife sexlife mediator impact models" ------------------------------------------------------------------------------- h1 pt 2 wave 2 dose-> sexlife sexlife mediator impact models ------------------------------------------------------------------------------- 929 . 930 . di as input "testing possible sex life mediator effects for males" testing possible sex life mediator effects for males 931 . 932 . * age is a mediating effect for males for Dose=> sex life for men 933 . 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) 934 . glm age avgcumdosew2 if gender==1, fam(gaus) link(identity) Iteration 0: log likelihood = -1330.6004 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = 147.6853 Deviance = 49917.64009 (1/df) Deviance = 147.6853 Pearson = 49917.64009 (1/df) Pearson = 147.6853 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 7.838826 Log likelihood = -1330.6004 BIC = 47947.46 ------------------------------------------------------------------------------ | OIM age | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew2 | .5832314 .2635871 2.21 0.027 .0666101 1.099853 _cons | 48.62133 .7061562 68.85 0.000 47.23729 50.00537 ------------------------------------------------------------------------------ 935 . 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.) 936 . 937 . 938 . des illw2 storage display value variable name type format label variable label ------------------------------------------------------------------------------- illw2 double %8.0g Total number of illnesses experienced in time period 1987-1996 939 . glm illw2 avgcumdosew2 if gender==1, fam(gaus) link(identity) Iteration 0: log likelihood = -303.59609 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = .3512988 Deviance = 118.7390083 (1/df) Deviance = .3512988 Pearson = 118.7390083 (1/df) Pearson = .3512988 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 1.797624 Log likelihood = -303.5960853 BIC = -1851.445 ------------------------------------------------------------------------------ | OIM illw2 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew2 | .0085423 .0128556 0.66 0.506 -.0166543 .0337389 _cons | .2741359 .0344406 7.96 0.000 .2066336 .3416382 ------------------------------------------------------------------------------ 940 . glm HP2sxlife illw2 if gender==1, fam(bin) irls scale(dev) link(probit) Iteration 1: deviance = 327.4086 Iteration 2: deviance = 327.3702 Iteration 3: deviance = 327.3699 Iteration 4: deviance = 327.3699 Iteration 5: deviance = 327.3699 Generalized linear models No. of obs = 340 Optimization : MQL Fisher scoring Residual df = 338 (IRLS EIM) Scale parameter = 1 Deviance = 327.36992 (1/df) Deviance = .9685501 Pearson = 335.9738293 (1/df) Pearson = .9940054 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1642.814 ------------------------------------------------------------------------------ | EIM HP2sxlife | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- illw2 | .4754044 .1211711 3.92 0.000 .2379134 .7128953 _cons | -.9963884 .0886054 -11.25 0.000 -1.170052 -.822725 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 941 . 942 . des radhlw2 storage display value variable name type format label variable label ------------------------------------------------------------------------------- radhlw2 double %8.0g how much believed personal health is affected by radiation in 1996 943 . glm radhlw2 avgcumdosew2 if gender==1, fam(gaus) link(identity) Iteration 0: log likelihood = -1693.4076 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = 1247.933 Deviance = 421801.4584 (1/df) Deviance = 1247.933 Pearson = 421801.4584 (1/df) Pearson = 1247.933 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 9.972986 Log likelihood = -1693.407647 BIC = 419831.3 ------------------------------------------------------------------------------ | OIM radhlw2 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew2 | 1.220373 .766216 1.59 0.111 -.2813831 2.722128 _cons | 45.63198 2.052711 22.23 0.000 41.60874 49.65522 ------------------------------------------------------------------------------ 944 . glm HP2sxlife radhlw2 if gender==1, fam(bin) irls scale(dev) link(probit) Iteration 1: deviance = 299.0301 Iteration 2: deviance = 296.5897 Iteration 3: deviance = 296.5625 Iteration 4: deviance = 296.5625 Iteration 5: deviance = 296.5625 Generalized linear models No. of obs = 340 Optimization : MQL Fisher scoring Residual df = 338 (IRLS EIM) Scale parameter = 1 Deviance = 296.5625078 (1/df) Deviance = .8774039 Pearson = 336.752315 (1/df) Pearson = .9963086 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1673.621 ------------------------------------------------------------------------------ | EIM HP2sxlife | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- radhlw2 | .0156386 .0022528 6.94 0.000 .0112232 .020054 _cons | -1.687381 .1543913 -10.93 0.000 -1.989983 -1.38478 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 945 . 946 . 947 . des bf4 storage display value variable name type format label variable label ------------------------------------------------------------------------------- bf4 float %9.0g bf4 = max(0, 24 - BSIsoma) 948 . glm bf4 avgcumdosew2 if gender==1, fam(gaus) link(identity) Iteration 0: log likelihood = -1027.1225 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = 24.7771 Deviance = 8374.659221 (1/df) Deviance = 24.7771 Pearson = 8374.659221 (1/df) Pearson = 24.7771 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 6.053662 Log likelihood = -1027.122509 BIC = 6404.476 ------------------------------------------------------------------------------ | OIM bf4 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew2 | -.0331637 .1079644 -0.31 0.759 -.2447701 .1784427 _cons | 12.52896 .2892393 43.32 0.000 11.96206 13.09586 ------------------------------------------------------------------------------ 949 . 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.) 950 . 951 . des bf4m storage display value variable name type format label variable label ------------------------------------------------------------------------------- bf4m float %9.0g bf4m = max(0, 32 - BSIsoma) 952 . glm bf4m avgcumdosew2 if gender==1, fam(gaus) link(identity) Iteration 0: log likelihood = -1060.7791 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = 30.20174 Deviance = 10208.18969 (1/df) Deviance = 30.20174 Pearson = 10208.18969 (1/df) Pearson = 30.20174 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 6.251642 Log likelihood = -1060.779096 BIC = 8238.006 ------------------------------------------------------------------------------ | OIM bf4m | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew2 | -.0266037 .1191987 -0.22 0.823 -.2602289 .2070215 _cons | 20.34324 .3193362 63.70 0.000 19.71735 20.96913 ------------------------------------------------------------------------------ 953 . 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.) 954 . 955 . des bf4 storage display value variable name type format label variable label ------------------------------------------------------------------------------- bf4 float %9.0g bf4 = max(0, 24 - BSIsoma) 956 . glm shrelaw2 avgcumdosew2 if gender==1, fam(gaus) link(identity) Iteration 0: log likelihood = -1686.1612 Generalized linear models No. of obs = 339 Optimization : ML Residual df = 337 Scale parameter = 1231.384 Deviance = 414976.438 (1/df) Deviance = 1231.384 Pearson = 414976.438 (1/df) Pearson = 1231.384 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 9.959653 Log likelihood = -1686.16125 BIC = 413013.1 ------------------------------------------------------------------------------ | OIM shrelaw2 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew2 | .6230115 .7612097 0.82 0.413 -.868932 2.114955 _cons | 26.21356 2.042278 12.84 0.000 22.21077 30.21635 ------------------------------------------------------------------------------ 957 . glm HP2sxlife shrelaw2 if gender==1, fam(bin) irls scale(dev) link(probit) Iteration 1: deviance = 340.048 Iteration 2: deviance = 339.8281 Iteration 3: deviance = 339.828 Iteration 4: deviance = 339.828 Generalized linear models No. of obs = 339 Optimization : MQL Fisher scoring Residual df = 337 (IRLS EIM) Scale parameter = 1 Deviance = 339.8280445 (1/df) Deviance = 1.008392 Pearson = 339.1270644 (1/df) Pearson = 1.006312 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1623.534 ------------------------------------------------------------------------------ | EIM HP2sxlife | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- shrelaw2 | .0035605 .0021514 1.65 0.098 -.0006562 .0077772 _cons | -.9307902 .1003805 -9.27 0.000 -1.127532 -.734048 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 958 . 959 . glm shfamw2 avgcumdosew2 if gender==1, fam(gaus) link(identity) Iteration 0: log likelihood = -1704.8947 Generalized linear models No. of obs = 339 Optimization : ML Residual df = 337 Scale parameter = 1375.284 Deviance = 463470.769 (1/df) Deviance = 1375.284 Pearson = 463470.769 (1/df) Pearson = 1375.284 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 10.07017 Log likelihood = -1704.894657 BIC = 461507.4 ------------------------------------------------------------------------------ | OIM shfamw2 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew2 | -.7484378 .8043765 -0.93 0.352 -2.324987 .8281112 _cons | 34.76184 2.15791 16.11 0.000 30.53241 38.99127 ------------------------------------------------------------------------------ 960 . glm HP2sxlife shfamw2 if gender==1, fam(bin) irls scale(dev) link(probit) Iteration 1: deviance = 338.2157 Iteration 2: deviance = 338.0066 Iteration 3: deviance = 338.0065 Iteration 4: deviance = 338.0065 Generalized linear models No. of obs = 339 Optimization : MQL Fisher scoring Residual df = 337 (IRLS EIM) Scale parameter = 1 Deviance = 338.0064771 (1/df) Deviance = 1.002987 Pearson = 339.3157137 (1/df) Pearson = 1.006872 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1625.356 ------------------------------------------------------------------------------ | EIM HP2sxlife | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- shfamw2 | .0027669 .0020626 1.34 0.180 -.0012757 .0068096 _cons | -.9380005 .1081399 -8.67 0.000 -1.149951 -.7260503 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 961 . 962 . scalar sxlifeMedMw2 = "age" 963 . 964 . title4 "female impact models mediator search" ------------------------------------------------------------------------------- female impact models mediator search ------------------------------------------------------------------------------- 965 . 966 . * age is a mediating effect for females for Dose=> sex life for women 967 . glm age avgcumdosew2 if gender==2, fam(gaus) link(identity) Iteration 0: log likelihood = -1406.9403 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = 136.9184 Deviance = 49427.52828 (1/df) Deviance = 136.9184 Pearson = 49427.52828 (1/df) Pearson = 136.9184 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 7.762756 Log likelihood = -1406.940271 BIC = 47299.65 ------------------------------------------------------------------------------ | OIM age | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew2 | 1.502324 .4454009 3.37 0.001 .6293547 2.375294 _cons | 48.86944 .7323225 66.73 0.000 47.43412 50.30477 ------------------------------------------------------------------------------ 968 . 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.) 969 . 970 . * illness is a mediating effect for females = > sex life for men 971 . des illw2 storage display value variable name type format label variable label ------------------------------------------------------------------------------- illw2 double %8.0g Total number of illnesses experienced in time period 1987-1996 972 . glm illw2 avgcumdosew2 if gender==2, fam(gaus) link(identity) Iteration 0: log likelihood = -463.51524 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = .756881 Deviance = 273.2340487 (1/df) Deviance = .756881 Pearson = 273.2340487 (1/df) Pearson = .756881 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 2.564822 Log likelihood = -463.5152411 BIC = -1854.645 ------------------------------------------------------------------------------ | OIM illw2 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew2 | .1249912 .0331157 3.77 0.000 .0600856 .1898968 _cons | .301285 .0544484 5.53 0.000 .194568 .4080019 ------------------------------------------------------------------------------ 973 . glm HP2sxlife illw2 if gender==2, fam(bin) irls scale(dev) link(probit) Iteration 1: deviance = 388.6886 Iteration 2: deviance = 388.2329 Iteration 3: deviance = 388.2328 Iteration 4: deviance = 388.2328 Generalized linear models No. of obs = 363 Optimization : MQL Fisher scoring Residual df = 361 (IRLS EIM) Scale parameter = 1 Deviance = 388.2327887 (1/df) Deviance = 1.075437 Pearson = 359.7775997 (1/df) Pearson = .9966138 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1739.647 ------------------------------------------------------------------------------ | EIM HP2sxlife | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- illw2 | .4442672 .0949037 4.68 0.000 .2582594 .630275 _cons | -.8535276 .0872416 -9.78 0.000 -1.024518 -.6825372 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 974 . 975 . *---------- this may be important ------------------------------------------ > - 976 . * radhlw2 can be a mediating factor for females in wave 2 for sxlife 977 . des radhlw2 storage display value variable name type format label variable label ------------------------------------------------------------------------------- radhlw2 double %8.0g how much believed personal health is affected by radiation in 1996 978 . glm radhlw2 avgcumdosew2 if gender==2, fam(gaus) link(identity) Iteration 0: log likelihood = -1791.2233 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = 1137.567 Deviance = 410661.5604 (1/df) Deviance = 1137.567 Pearson = 410661.5604 (1/df) Pearson = 1137.567 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 9.880018 Log likelihood = -1791.223306 BIC = 408533.7 ------------------------------------------------------------------------------ | OIM radhlw2 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew2 | 3.302288 1.283833 2.57 0.010 .7860214 5.818555 _cons | 56.95167 2.110863 26.98 0.000 52.81445 61.08888 ------------------------------------------------------------------------------ 979 . glm HP2sxlife radhlw2 if gender==2, fam(bin) irls scale(dev) link(probit) Iteration 1: deviance = 390.2214 Iteration 2: deviance = 389.9357 Iteration 3: deviance = 389.9356 Iteration 4: deviance = 389.9356 Generalized linear models No. of obs = 363 Optimization : MQL Fisher scoring Residual df = 361 (IRLS EIM) Scale parameter = 1 Deviance = 389.9355535 (1/df) Deviance = 1.080154 Pearson = 370.7850434 (1/df) Pearson = 1.027105 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1737.944 ------------------------------------------------------------------------------ | EIM HP2sxlife | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- radhlw2 | .0108547 .0023275 4.66 0.000 .0062929 .0154166 _cons | -1.340315 .1718732 -7.80 0.000 -1.67718 -1.003449 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 980 . *---------------------------------------------------------------------------- > - 981 . 982 . des bf4 // soma recentered storage display value variable name type format label variable label ------------------------------------------------------------------------------- bf4 float %9.0g bf4 = max(0, 24 - BSIsoma) 983 . * bf4 is a mediting effect for females for Dose=> sex life for women 984 . glm bf4 avgcumdosew2 if gender==2, fam(gaus) link(identity) Iteration 0: log likelihood = -1109.0983 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = 26.53281 Deviance = 9578.344971 (1/df) Deviance = 26.53281 Pearson = 9578.344971 (1/df) Pearson = 26.53281 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 6.121754 Log likelihood = -1109.098281 BIC = 7450.466 ------------------------------------------------------------------------------ | OIM bf4 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew2 | -.595012 .1960703 -3.03 0.002 -.9793027 -.2107212 _cons | 11.02048 .3223763 34.19 0.000 10.38863 11.65232 ------------------------------------------------------------------------------ 985 . 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.) 986 . 987 . des bf4m // soma recentered storage display value variable name type format label variable label ------------------------------------------------------------------------------- bf4m float %9.0g bf4m = max(0, 32 - BSIsoma) 988 . * bf4m is a possible mediating effect for female sex life 989 . glm bf4m avgcumdosew2 if gender==2, fam(gaus) link(identity) Iteration 0: log likelihood = -1140.8259 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = 31.60104 Deviance = 11407.97484 (1/df) Deviance = 31.60104 Pearson = 11407.97484 (1/df) Pearson = 31.60104 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 6.296561 Log likelihood = -1140.825904 BIC = 9280.095 ------------------------------------------------------------------------------ | OIM bf4m | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew2 | -.599311 .2139789 -2.80 0.005 -1.018702 -.1799202 _cons | 18.83424 .3518214 53.53 0.000 18.14469 19.5238 ------------------------------------------------------------------------------ 990 . 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.) 991 . 992 . des shfamw2 storage display value variable name type format label variable label ------------------------------------------------------------------------------- shfamw2 double %8.0g Percentage of strains and hassles related to family in 1996 993 . glm shfamw2 avgcumdosew2 if gender==2, fam(gaus) link(identity) Iteration 0: log likelihood = -1804.1821 Generalized linear models No. of obs = 362 Optimization : ML Residual df = 360 Scale parameter = 1255.79 Deviance = 452084.3956 (1/df) Deviance = 1255.79 Pearson = 452084.3956 (1/df) Pearson = 1255.79 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 9.978907 Log likelihood = -1804.182119 BIC = 449963.4 ------------------------------------------------------------------------------ | OIM shfamw2 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew2 | .6648412 1.349346 0.49 0.622 -1.979828 3.30951 _cons | 33.6876 2.218839 15.18 0.000 29.33876 38.03645 ------------------------------------------------------------------------------ 994 . glm HP2sxlife shfamw2 if gender==2, fam(bin) irls scale(dev) link(probit) Iteration 1: deviance = 411.7925 Iteration 2: deviance = 411.1829 Iteration 3: deviance = 411.1826 Iteration 4: deviance = 411.1826 Generalized linear models No. of obs = 362 Optimization : MQL Fisher scoring Residual df = 360 (IRLS EIM) Scale parameter = 1 Deviance = 411.1826472 (1/df) Deviance = 1.142174 Pearson = 361.8999919 (1/df) Pearson = 1.005278 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1709.809 ------------------------------------------------------------------------------ | EIM HP2sxlife | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- shfamw2 | -.0023803 .0021918 -1.09 0.277 -.0066761 .0019156 _cons | -.5736929 .1047839 -5.48 0.000 -.7790656 -.3683202 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 995 . 996 . des shrelaw2 storage display value variable name type format label variable label ------------------------------------------------------------------------------- shrelaw2 double %8.0g Percentage of strains and hassles related to relationships in 1996 997 . glm shrelaw2 avgcumdosew2 if gender==2, fam(gaus) link(identity) Iteration 0: log likelihood = -1767.2727 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = 996.9369 Deviance = 359894.211 (1/df) Deviance = 996.9369 Pearson = 359894.211 (1/df) Pearson = 996.9369 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 9.748059 Log likelihood = -1767.272695 BIC = 357766.3 ------------------------------------------------------------------------------ | OIM shrelaw2 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew2 | 1.945314 1.20186 1.62 0.106 -.4102891 4.300917 _cons | 22.64351 1.976084 11.46 0.000 18.77046 26.51657 ------------------------------------------------------------------------------ 998 . glm HP2sxlife shrelaw2 if gender==2, fam(bin) irls scale(dev) link(probit) Iteration 1: deviance = 415.0412 Iteration 2: deviance = 414.406 Iteration 3: deviance = 414.4058 Iteration 4: deviance = 414.4058 Generalized linear models No. of obs = 363 Optimization : MQL Fisher scoring Residual df = 361 (IRLS EIM) Scale parameter = 1 Deviance = 414.4057989 (1/df) Deviance = 1.147939 Pearson = 362.9721983 (1/df) Pearson = 1.005463 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1713.474 ------------------------------------------------------------------------------ | EIM HP2sxlife | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- shrelaw2 | -.0020918 .0024591 -0.85 0.395 -.0069114 .0027279 _cons | -.5970179 .0953785 -6.26 0.000 -.7839564 -.4100794 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 999 . 1000 . glm aborw2 avgcumdosew2 if gender==2, fam(pois) link(log) Iteration 0: log likelihood = -293.85682 Iteration 1: log likelihood = -282.01816 Iteration 2: log likelihood = -281.9464 Iteration 3: log likelihood = -281.94638 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = 1 Deviance = 391.5624729 (1/df) Deviance = 1.084661 Pearson = 595.1604651 (1/df) Pearson = 1.648644 Variance function: V(u) = u [Poisson] Link function : g(u) = ln(u) [Log] AIC = 1.564443 Log likelihood = -281.9463797 BIC = -1736.317 ------------------------------------------------------------------------------ | OIM aborw2 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew2 | -.0526825 .0821516 -0.64 0.521 -.2136968 .1083317 _cons | -1.095949 .1143769 -9.58 0.000 -1.320124 -.8717744 ------------------------------------------------------------------------------ 1001 . glm HP2sxlife aborw2 if gender==2, fam(bin) link(probit) irls scale(dev) Iteration 1: deviance = 412.7431 Iteration 2: deviance = 412.0513 Iteration 3: deviance = 412.0507 Iteration 4: deviance = 412.0507 Generalized linear models No. of obs = 363 Optimization : MQL Fisher scoring Residual df = 361 (IRLS EIM) Scale parameter = 1 Deviance = 412.0507362 (1/df) Deviance = 1.141415 Pearson = 361.2552584 (1/df) Pearson = 1.000707 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1715.829 ------------------------------------------------------------------------------ | EIM HP2sxlife | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- aborw2 | -.1967113 .1199217 -1.64 0.101 -.4317535 .0383309 _cons | -.5909716 .0824147 -7.17 0.000 -.7525014 -.4294418 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 1002 . 1003 . title4 "h1 pt2 wave 2 sex life impact summary matrix construction" ------------------------------------------------------------------------------- h1 pt2 wave 2 sex life impact summary matrix construction ------------------------------------------------------------------------------- 1004 . 1005 . *xx summary of mediating effects: age and illness mediate sex life for men 1006 . * age illnesss radhlw2 bf4 bf4m (soma) media > te sex life for women 1007 . 1008 . scalar sxlifeMedMw2 = "age illw2" 1009 . scalar sxlifeMedFw2 = "age illw2 radhlw2 bf4 bf4m" 1010 . *--- summary matrix contstruction 1011 . 1012 . matrix define sxlifeMw2 = J(1,8, 0) 1013 . matrix define sxlifeFw2 = J(1,8, 0) 1014 . matrix colnames sxlifeMw2= hypnum ptnum wave gender medsig numMAsig numMods > ig numMed 1015 . matrix colnames sxlifeFw2= hypnum ptnum wave gender medsig numMAsig > numModsig numMed 1016 . matrix define sxlifeMw2= (1, 2, 3, 1, 0, 2, 0, 2 ) 1017 . matrix define sxlifeFw2= (1, 2, 3, 2, 0, 4, 0, 5) 1018 . matrix rowname sxlifeMw2 = sxlifeMw2 1019 . matrix rowname sxlifeFw2 = sxlifeFw2 1020 . matlist sxlifeMw2 | c1 c2 c3 c4 c5 c6 > c7 c8 -------------+----------------------------------------------------------------- ----------------------- sxlifeMw2 | 1 2 3 1 0 2 > 0 2 1021 . matlist sxlifeFw2 | c1 c2 c3 c4 c5 c6 > c7 c8 -------------+----------------------------------------------------------------- ----------------------- sxlifeFw2 | 1 2 3 2 0 4 > 0 5 1022 . matrix define H1pt2w2 = ( wkMw2 \ wkFw2 \ hmcrMw2 \ hmcrFw2 \ spM > w2 \ spFw2 \ prbfamMw2 \ prbfamFw2 \ sxlifeMw2 \ sxlifeFw2 ) 1023 . 1024 . matlist H1pt2w2 | c1 c2 c3 c4 c5 c6 > c7 c8 -------------+----------------------------------------------------------------- ----------------------- r1 | 1 2 2 1 0 2 > 0 2 r1 | 1 2 2 2 0 1 > 0 2 r1 | 1 2 3 1 0 1 > 0 1 r1 | 1 2 3 2 0 1 > 0 1 spMw2 | 1 2 3 1 0 4 > 0 1 spFw2 | 1 2 3 2 1 5 > 0 2 prbfamMw2 | 1 2 3 1 0 3 > 0 1 prbfamFw2 | 1 2 3 2 1 3 > 0 2 sxlifeMw2 | 1 2 3 1 0 2 > 0 2 sxlifeFw2 | 1 2 3 2 0 4 > 0 5 1025 . matrix colnames H1pt2w2 = hypnum ptnum wave gender medsig numMAsig numMo > dsig numMed 1026 . matrix rownames H1pt2w2 = wkMw2 wkFw2 hmcrMw2 hmcrFw2 spMw2 spFw2 pr > bfhmMw2 prbfhmFw2 1027 . matlist H1pt2w2 | hypnum ptnum wave gender medsig numMAsig > numModsig numMed -------------+----------------------------------------------------------------- ----------------------- wkMw2 | 1 2 2 1 0 2 > 0 2 wkFw2 | 1 2 2 2 0 1 > 0 2 hmcrMw2 | 1 2 3 1 0 1 > 0 1 hmcrFw2 | 1 2 3 2 0 1 > 0 1 spMw2 | 1 2 3 1 0 4 > 0 1 spFw2 | 1 2 3 2 1 5 > 0 2 prbfhmMw2 | 1 2 3 1 0 3 > 0 1 prbfhmFw2 | 1 2 3 2 1 3 > 0 2 prbfhmFw2 | 1 2 3 1 0 2 > 0 2 prbfhmFw2 | 1 2 3 2 0 4 > 0 5 1028 . 1029 . 1030 . 1031 . 1032 . *=================== Chunk 8 Dose => interests and Hobbies relationship 1033 . 1034 . title " 6. H1 Wave 2 part2 Dose-Interest and Hobbies impact" ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** 6. H1 Wave 2 part2 Dose-Interest and Hobbies impact ***** ***** ***** ***** ***** ***** 16 Jun 2012 21:57:19 ***** ******************************************************************************* ******************************************************************************* 1035 . 1036 . 1037 . * Chunk 8 ---male models 1038 . forvalues j = 2/2 { 2. set more off 3. 1039 . des age educ1-educ7 marrw`j'1-marrw`j'6 inc1w`j'-inc4w`j' /// > bf1 bf4 bf9 bf11 bf4m bf15m bf30 bf40 4. 1040 . foreach var in HP2inthob { 5. forvalues k=1/2 { 6. local w2bf bf1 bf4 bf6 bf7 bf14 bf15 bf40 7. 1041 . 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 radhlw2 if gender==`k', coef difficult iterate(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 marrw21 byte %8.0g marrw2==1. single marrw22 byte %8.0g marrw2==2. cohabitating marrw23 byte %8.0g marrw2==3. married marrw24 byte %8.0g marrw2==4. separated marrw25 byte %8.0g marrw2==5. divorced marrw26 byte %8.0g marrw2==6. widowed inc1w2 double %15.0g LABJ Income is not sufficient for basic neccessities in 1996 inc2w2 double %15.0g LABJ Income is just sufficient for basic neccessities in 1996 inc3w2 double %15.0g LABJ Income is sufficient for basics plus extra purchases/savings in 1996 inc4w2 double %15.0g LABJ Income allows to comfortably afford luxury items in 1996 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= 2 chunk 8 H1 test:Gender= 1 model Wave = 2 for HP2sxlife ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Full Nottingham Part 2 subscale models for male and then females ***** ***** ***** ***** ***** ***** 16 Jun 2012 21:57:19 ***** ******************************************************************************* ******************************************************************************* Model for gender==1 and wave == 2 i.educ _Ieduc_1-8 (naturally coded; _Ieduc_1 omitted) note: _Ieduc_4 != 0 predicts failure perfectly _Ieduc_4 dropped and 12 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: occ6w2 != 0 predicts failure perfectly occ6w2 dropped and 4 obs not used note: occ8w2 != 0 predicts failure perfectly occ8w2 dropped and 43 obs not used note: marrw22 != 0 predicts failure perfectly marrw22 dropped and 7 obs not used note: marrw25 != 0 predicts failure perfectly marrw25 dropped and 4 obs not used note: marrw26 != 0 predicts failure perfectly marrw26 dropped and 3 obs not used note: inc4w2 != 0 predicts failure perfectly inc4w2 dropped and 9 obs not used note: dvcew2 != 0 predicts failure perfectly dvcew2 dropped and 3 obs not used note: sepaw2 != 0 predicts failure perfectly sepaw2 dropped and 1 obs not used note: _Ieduc_6 omitted because of collinearity note: bf15 omitted because of collinearity note: radhlw2 omitted because of collinearity Logistic regression Number of obs = 240 LR chi2(35) = 92.50 Prob > chi2 = 0.0000 Log likelihood = -55.199011 Pseudo R2 = 0.4559 ------------------------------------------------------------------------------ HP2inthob | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0625698 .0339541 1.84 0.065 -.0039791 .1291186 _Ieduc_2 | -1.043358 1.579537 -0.66 0.509 -4.139194 2.052478 _Ieduc_3 | -1.383026 .8161024 -1.69 0.090 -2.982558 .216505 _Ieduc_4 | 0 (omitted) _Ieduc_5 | -.3882601 .890757 -0.44 0.663 -2.134112 1.357591 _Ieduc_6 | 0 (omitted) _Ieduc_7 | 0 (omitted) _Ieduc_8 | 0 (omitted) occ1w2 | -1.033982 5.222537 -0.20 0.843 -11.26997 9.202003 occ2w2 | -2.764859 5.282979 -0.52 0.601 -13.11931 7.58959 occ3w2 | -1.159373 5.266774 -0.22 0.826 -11.48206 9.163314 occ4w2 | -1.475817 5.272908 -0.28 0.780 -11.81053 8.858893 occ5w2 | .6777917 5.260041 0.13 0.897 -9.631698 10.98728 occ6w2 | 0 (omitted) occ7w2 | -.3442089 5.327123 -0.06 0.948 -10.78518 10.09676 occ8w2 | 0 (omitted) marrw21 | 13.93224 1621.282 0.01 0.993 -3163.721 3191.586 marrw22 | 0 (omitted) marrw23 | 11.47436 1621.282 0.01 0.994 -3166.179 3189.128 marrw25 | 0 (omitted) marrw26 | 0 (omitted) inc1w2 | -2.09725 5.429773 -0.39 0.699 -12.73941 8.544909 inc2w2 | -.9256519 5.257192 -0.18 0.860 -11.22956 9.378255 inc3w2 | .0745765 5.245026 0.01 0.989 -10.20548 10.35464 inc4w2 | 0 (omitted) radhlw2 | .0364231 .0131057 2.78 0.005 .0107363 .0621099 havmil | .0020332 .0091412 0.22 0.824 -.0158833 .0199497 avgcumdosew2 | -.2023055 .3376483 -0.60 0.549 -.8640841 .4594731 bf1 | .0108557 .0182727 0.59 0.552 -.0249582 .0466696 bf4 | -.290932 .0816796 -3.56 0.000 -.4510211 -.1308428 bf6 | .0111353 .0131635 0.85 0.398 -.0146647 .0369353 bf7 | .0337038 .1171208 0.29 0.774 -.1958487 .2632562 bf14 | -.000219 .0001127 -1.94 0.052 -.0004398 1.92e-06 bf15 | 0 (omitted) bf40 | .490857 .2032201 2.42 0.016 .0925529 .889161 deaw2 | .006222 .5178905 0.01 0.990 -1.008825 1.021269 dvcew2 | 0 (omitted) sepaw2 | 0 (omitted) accdw2 | 1.036869 .5663339 1.83 0.067 -.0731249 2.146863 movew2 | .7948452 .8450104 0.94 0.347 -.8613447 2.451035 illw2 | -.8262786 .5178561 -1.60 0.111 -1.841258 .1887007 shfamw2 | -.003778 .0101348 -0.37 0.709 -.0236419 .0160858 shhlw2 | -.0014472 .0125099 -0.12 0.908 -.0259662 .0230717 shjobw2 | .0044446 .012101 0.37 0.713 -.0192728 .0281621 shrelaw2 | -.0158848 .0098629 -1.61 0.107 -.0352157 .0034461 suprtw2 | -.0048211 .0089741 -0.54 0.591 -.0224099 .0127678 suchrw2 | .016543 .008867 1.87 0.062 -.0008361 .033922 havmilsq | -2.84e-06 .0000159 -0.18 0.858 -.000034 .0000283 radhlw2 | 0 (omitted) _cons | -16.47971 1621.283 -0.01 0.992 -3194.136 3161.177 ------------------------------------------------------------------------------ Note: 1 failure and 0 successes completely determined. Logistic model for HP2inthob -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 20 6 | 26 - | 16 198 | 214 -----------+--------------------------+----------- Total | 36 204 | 240 Classified + if predicted Pr(D) >= .5 True D defined as HP2inthob != 0 -------------------------------------------------- Sensitivity Pr( +| D) 55.56% Specificity Pr( -|~D) 97.06% Positive predictive value Pr( D| +) 76.92% Negative predictive value Pr(~D| -) 92.52% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 2.94% False - rate for true D Pr( -| D) 44.44% False + rate for classified + Pr(~D| +) 23.08% False - rate for classified - Pr( D| -) 7.48% -------------------------------------------------- Correctly classified 90.83% -------------------------------------------------- Logistic model for HP2inthob, goodness-of-fit test number of observations = 240 number of covariate patterns = 240 Pearson chi2(204) = 545.84 Prob > chi2 = 0.0000 Measures of Fit for logistic of HP2inthob Log-Lik Intercept Only: -101.450 Log-Lik Full Model: -55.199 D(190): 110.398 LR(35): 92.502 Prob > LR: 0.000 McFadden's R2: 0.456 McFadden's Adj R2: -0.037 Maximum Likelihood R2: 0.320 Cragg & Uhler's R2: 0.561 McKelvey and Zavoina's R2: 0.776 Efron's R2: 0.482 Variance of y*: 14.694 Variance of error: 3.290 Count R2: 0.908 Adj Count R2: 0.389 AIC: 0.877 AIC*n: 210.398 BIC: -930.923 BIC': 99.320 Full main model for HP2inthob for wave= 2 chunk 8 H1 test:Gender= 2 model Wave = 2 for HP2inthob ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Full Nottingham Part 2 subscale models for male and then females ***** ***** ***** ***** ***** ***** 16 Jun 2012 21:57:21 ***** ******************************************************************************* ******************************************************************************* Model for gender==2 and wave == 2 i.educ _Ieduc_1-8 (naturally coded; _Ieduc_1 omitted) note: sepaw2 != 0 predicts failure perfectly sepaw2 dropped and 8 obs not used note: _Ieduc_8 omitted because of collinearity note: marrw26 omitted because of collinearity note: bf15 omitted because of collinearity note: radhlw2 omitted because of collinearity Logistic regression Number of obs = 354 LR chi2(44) = 115.47 Prob > chi2 = 0.0000 Log likelihood = -111.06431 Pseudo R2 = 0.3420 ------------------------------------------------------------------------------ HP2inthob | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .079863 .021131 3.78 0.000 .0384469 .121279 _Ieduc_2 | -12.93831 1490.754 -0.01 0.993 -2934.762 2908.885 _Ieduc_3 | -12.4076 1490.754 -0.01 0.993 -2934.231 2909.416 _Ieduc_4 | -11.72169 1490.754 -0.01 0.994 -2933.546 2910.102 _Ieduc_5 | -12.09518 1490.754 -0.01 0.994 -2933.919 2909.728 _Ieduc_6 | -12.44516 1490.754 -0.01 0.993 -2934.269 2909.378 _Ieduc_7 | -12.06531 1490.757 -0.01 0.994 -2933.895 2909.764 _Ieduc_8 | 0 (omitted) occ1w2 | -1.681778 1.842381 -0.91 0.361 -5.292779 1.929222 occ2w2 | -2.066763 1.905083 -1.08 0.278 -5.800657 1.66713 occ3w2 | -.925484 1.867622 -0.50 0.620 -4.585956 2.734988 occ4w2 | -1.837685 1.997812 -0.92 0.358 -5.753324 2.077954 occ5w2 | -1.808015 2.160492 -0.84 0.403 -6.042501 2.426471 occ6w2 | -.7980572 2.0458 -0.39 0.696 -4.807751 3.211637 occ7w2 | -.6513668 1.8133 -0.36 0.719 -4.205369 2.902636 occ8w2 | -.7497523 2.02704 -0.37 0.711 -4.722678 3.223174 marrw21 | 1.330155 1.130799 1.18 0.239 -.8861701 3.546479 marrw22 | .1433998 1.421047 0.10 0.920 -2.641801 2.9286 marrw23 | .3124211 .8029396 0.39 0.697 -1.261312 1.886154 marrw25 | .2321157 1.213839 0.19 0.848 -2.146964 2.611196 marrw26 | 0 (omitted) inc1w2 | 1.002608 1.857433 0.54 0.589 -2.637893 4.643109 inc2w2 | 1.21648 1.809887 0.67 0.502 -2.330833 4.763793 inc3w2 | .8716928 1.845137 0.47 0.637 -2.744709 4.488095 inc4w2 | 2.25991 2.119136 1.07 0.286 -1.893519 6.41334 radhlw2 | .0169047 .0075432 2.24 0.025 .0021202 .0316892 havmil | .0026206 .00401 0.65 0.513 -.0052388 .0104801 avgcumdosew2 | .1098391 .1075167 1.02 0.307 -.1008897 .3205679 bf1 | -.0101735 .0098443 -1.03 0.301 -.029468 .0091209 bf4 | -.160166 .0433489 -3.69 0.000 -.2451282 -.0752038 bf6 | -.0029228 .0086097 -0.34 0.734 -.0197974 .0139519 bf7 | -.0201783 .0882604 -0.23 0.819 -.1931656 .152809 bf14 | -.0000789 .0000837 -0.94 0.346 -.000243 .0000853 bf15 | 0 (omitted) bf40 | -.0387073 .0922777 -0.42 0.675 -.2195682 .1421537 deaw2 | .1202612 .2113024 0.57 0.569 -.2938838 .5344063 dvcew2 | .0143372 1.477099 0.01 0.992 -2.880724 2.909399 sepaw2 | 0 (omitted) accdw2 | .4772298 .6036102 0.79 0.429 -.7058243 1.660284 movew2 | -.5141092 .7928535 -0.65 0.517 -2.068073 1.039855 illw2 | .1586699 .2249295 0.71 0.481 -.2821838 .5995235 shfamw2 | -.0005225 .0071722 -0.07 0.942 -.0145799 .0135348 shhlw2 | .0069143 .0072142 0.96 0.338 -.0072252 .0210539 shjobw2 | -.0096031 .0066833 -1.44 0.151 -.0227021 .003496 shrelaw2 | -.011349 .0077316 -1.47 0.142 -.0265027 .0038047 suprtw2 | -.01257 .0057932 -2.17 0.030 -.0239246 -.0012155 suchrw2 | .000171 .0063873 0.03 0.979 -.0123478 .0126898 havmilsq | -2.75e-06 5.84e-06 -0.47 0.638 -.0000142 8.69e-06 radhlw2 | 0 (omitted) _cons | 8.21905 1490.755 0.01 0.996 -2913.607 2930.045 ------------------------------------------------------------------------------ Note: 1 failure and 0 successes completely determined. Logistic model for HP2inthob -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 35 12 | 47 - | 30 277 | 307 -----------+--------------------------+----------- Total | 65 289 | 354 Classified + if predicted Pr(D) >= .5 True D defined as HP2inthob != 0 -------------------------------------------------- Sensitivity Pr( +| D) 53.85% Specificity Pr( -|~D) 95.85% Positive predictive value Pr( D| +) 74.47% Negative predictive value Pr(~D| -) 90.23% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 4.15% False - rate for true D Pr( -| D) 46.15% False + rate for classified + Pr(~D| +) 25.53% False - rate for classified - Pr( D| -) 9.77% -------------------------------------------------- Correctly classified 88.14% -------------------------------------------------- Logistic model for HP2inthob, goodness-of-fit test number of observations = 354 number of covariate patterns = 354 Pearson chi2(309) = 384.69 Prob > chi2 = 0.0022 Measures of Fit for logistic of HP2inthob Log-Lik Intercept Only: -168.799 Log-Lik Full Model: -111.064 D(304): 222.129 LR(44): 115.469 Prob > LR: 0.000 McFadden's R2: 0.342 McFadden's Adj R2: 0.046 Maximum Likelihood R2: 0.278 Cragg & Uhler's R2: 0.453 McKelvey and Zavoina's R2: 0.619 Efron's R2: 0.372 Variance of y*: 8.629 Variance of error: 3.290 Count R2: 0.881 Adj Count R2: 0.354 AIC: 0.910 AIC*n: 322.129 BIC: -1562.138 BIC': 142.780 1042 . 1043 . label var radhlw2 "Self-perceived Chornobyl health threat in Wave 2" 1044 . 1045 . title4 "7. Testing H1 Wv2 Moderators of male Dose => Interests and Hobbies Im > pact" ------------------------------------------------------------------------------- 7. Testing H1 Wv2 Moderators of male Dose => Interests and Hobbies Impact ------------------------------------------------------------------------------- 1046 . 1047 . 1048 . forvalues j = 2/2 { 2. set more off 3. 1049 . des age educ1-educ7 marrw`j'1-marrw`j'6 inc1w`j'-inc4w`j' /// > bf1 bf4 bf9 bf11 bf4m bf15m bf30 bf40 4. 1050 . foreach var in HP2inthob { 5. local w2bf bf1 bf4 bf6 bf7 bf14 bf15 bf40 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 shfamw2 radhlw2 bf4m 13. xi: logistic `var' radhlw2 bf4 bf40 /// > if gender==1, coef 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 marrw21 byte %8.0g marrw2==1. single marrw22 byte %8.0g marrw2==2. cohabitating marrw23 byte %8.0g marrw2==3. married marrw24 byte %8.0g marrw2==4. separated marrw25 byte %8.0g marrw2==5. divorced marrw26 byte %8.0g marrw2==6. widowed inc1w2 double %15.0g LABJ Income is not sufficient for basic neccessities in 1996 inc2w2 double %15.0g LABJ Income is just sufficient for basic neccessities in 1996 inc3w2 double %15.0g LABJ Income is sufficient for basics plus extra purchases/savings in 1996 inc4w2 double %15.0g LABJ Income allows to comfortably afford luxury items in 1996 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= 2 chunk 8 H1 test:Gender= male model Wave = 2 for HP2inthob ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Full Nottingham Part 2 subscale models ***** ***** males on wave=2 ***** ***** ***** ***** ***** ***** 16 Jun 2012 21:57:22 ***** ******************************************************************************* ******************************************************************************* storage display value variable name type format label variable label ------------------------------------------------------------------------------- bf5m float %9.0g bf5m = max(0, ecprw3 - 75) * bf4m shfamw2 double %8.0g Percentage of strains and hassles related to family in 1996 radhlw2 double %8.0g Self-perceived Chornobyl health threat in Wave 2 bf4m float %9.0g bf4m = max(0, 32 - BSIsoma) Logistic regression Number of obs = 340 LR chi2(3) = 62.07 Prob > chi2 = 0.0000 Log likelihood = -88.03087 Pseudo R2 = 0.2606 ------------------------------------------------------------------------------ HP2inthob | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- radhlw2 | .0239738 .0073138 3.28 0.001 .0096391 .0383086 bf4 | -.1279475 .0383841 -3.33 0.001 -.2031789 -.0527161 bf40 | .233975 .112384 2.08 0.037 .0137064 .4542437 _cons | -2.905755 .8678535 -3.35 0.001 -4.606717 -1.204793 ------------------------------------------------------------------------------ Logistic model for HP2inthob -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 9 6 | 15 - | 29 296 | 325 -----------+--------------------------+----------- Total | 38 302 | 340 Classified + if predicted Pr(D) >= .5 True D defined as HP2inthob != 0 -------------------------------------------------- Sensitivity Pr( +| D) 23.68% Specificity Pr( -|~D) 98.01% Positive predictive value Pr( D| +) 60.00% Negative predictive value Pr(~D| -) 91.08% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 1.99% False - rate for true D Pr( -| D) 76.32% False + rate for classified + Pr(~D| +) 40.00% False - rate for classified - Pr( D| -) 8.92% -------------------------------------------------- Correctly classified 89.71% -------------------------------------------------- Logistic model for HP2inthob, goodness-of-fit test number of observations = 340 number of covariate patterns = 227 Pearson chi2(223) = 237.91 Prob > chi2 = 0.2351 Measures of Fit for logistic of HP2inthob Log-Lik Intercept Only: -119.064 Log-Lik Full Model: -88.031 D(336): 176.062 LR(3): 62.067 Prob > LR: 0.000 McFadden's R2: 0.261 McFadden's Adj R2: 0.227 Maximum Likelihood R2: 0.167 Cragg & Uhler's R2: 0.331 McKelvey and Zavoina's R2: 0.404 Efron's R2: 0.218 Variance of y*: 5.521 Variance of error: 3.290 Count R2: 0.897 Adj Count R2: 0.079 AIC: 0.541 AIC*n: 184.062 BIC: -1782.464 BIC': -44.580 Note: bf4m is necssary for bf5 but if bf4m is in model bf5 is not signif. Therefore, bf5 is not deemed significant. 1051 . 1052 . cap gen bf4Xd2 = bf4*avgcumdosew2 1053 . cap gen bf40Xd2 = bf40*agecumdosew2 1054 . 1055 . scalar SigdoseMEinthob = "no" 1056 . scalar MainEffMw2 = "radhlw2 bf4 bf40" 1057 . 1058 . title3 "Wave 2 Main effects Dose=> Interests and Hobbies impact identificatio > n" ------------------------------------------------------------------------------- title3 : Wave 2 Main effects Dose=> Interests and Hobbies impact identification 16 Jun 2012 21:57:24 computer Macintosh (Intel 64-bit) folder /Users/robertyaffee/Documents/data/research/chwk/phase3/Htests/h1tests/ > h1pt2 Data file chwide16june2012.dta currrently has 2382 variables and 703 obse > rvations 1059 . forvalues j = 2/2 { 2. set more off 3. 1060 . des age educ1-educ7 marrw`j'1-marrw`j'6 inc1w`j'-inc4w`j' /// > bf1 bf4 bf9 bf11 bf4m bf15m bf30 bf40 4. 1061 . foreach var in HP2inthob { 5. local w2bf bf1 bf4 bf6 bf7 bf14 bf15 bf40 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. 1062 . xi: logistic `var' age /// > radhlw`j' avgcumdosew`j' /// > shfamw`j' bf4 /// > bf40 bf4Xd2 bf40Xd2 if gender==1, coef 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 marrw21 byte %8.0g marrw2==1. single marrw22 byte %8.0g marrw2==2. cohabitating marrw23 byte %8.0g marrw2==3. married marrw24 byte %8.0g marrw2==4. separated marrw25 byte %8.0g marrw2==5. divorced marrw26 byte %8.0g marrw2==6. widowed inc1w2 double %15.0g LABJ Income is not sufficient for basic neccessities in 1996 inc2w2 double %15.0g LABJ Income is just sufficient for basic neccessities in 1996 inc3w2 double %15.0g LABJ Income is sufficient for basics plus extra purchases/savings in 1996 inc4w2 double %15.0g LABJ Income allows to comfortably afford luxury items in 1996 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= 2 chunk 8 H1 test:Gender= male model Wave = 2 for HP2inthob ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Full Nottingham Part 2 subscale models for males in wave=2 ***** ***** ***** ***** ***** ***** 16 Jun 2012 21:57:24 ***** ******************************************************************************* ******************************************************************************* Logistic regression Number of obs = 339 LR chi2(8) = 68.60 Prob > chi2 = 0.0000 Log likelihood = -84.646353 Pseudo R2 = 0.2884 ------------------------------------------------------------------------------ HP2inthob | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .019434 .0190292 1.02 0.307 -.0178625 .0567305 radhlw2 | .0239518 .0073094 3.28 0.001 .0096255 .038278 avgcumdosew2 | 2.556026 1.455092 1.76 0.079 -.2959014 5.407954 shfamw2 | -.0013078 .0052959 -0.25 0.805 -.0116875 .0090719 bf4 | .0106918 .0838793 0.13 0.899 -.1537086 .1750922 bf40 | .4187179 .1715551 2.44 0.015 .082476 .7549597 bf4Xd2 | -.1876111 .108152 -1.73 0.083 -.3995851 .0243629 bf40Xd2 | -.2942793 .1683543 -1.75 0.080 -.6242477 .035689 _cons | -5.700963 1.702573 -3.35 0.001 -9.037944 -2.363982 ------------------------------------------------------------------------------ Note: 1 failure and 0 successes completely determined. Logistic model for HP2inthob -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 14 7 | 21 - | 24 294 | 318 -----------+--------------------------+----------- Total | 38 301 | 339 Classified + if predicted Pr(D) >= .5 True D defined as HP2inthob != 0 -------------------------------------------------- Sensitivity Pr( +| D) 36.84% Specificity Pr( -|~D) 97.67% Positive predictive value Pr( D| +) 66.67% Negative predictive value Pr(~D| -) 92.45% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 2.33% False - rate for true D Pr( -| D) 63.16% False + rate for classified + Pr(~D| +) 33.33% False - rate for classified - Pr( D| -) 7.55% -------------------------------------------------- Correctly classified 90.86% -------------------------------------------------- Logistic model for HP2inthob, goodness-of-fit test number of observations = 339 number of covariate patterns = 334 Pearson chi2(325) = 281.60 Prob > chi2 = 0.9606 Measures of Fit for logistic of HP2inthob Log-Lik Intercept Only: -118.946 Log-Lik Full Model: -84.646 D(330): 169.293 LR(8): 68.598 Prob > LR: 0.000 McFadden's R2: 0.288 McFadden's Adj R2: 0.213 Maximum Likelihood R2: 0.183 Cragg & Uhler's R2: 0.363 McKelvey and Zavoina's R2: 0.691 Efron's R2: 0.260 Variance of y*: 10.643 Variance of error: 3.290 Count R2: 0.909 Adj Count R2: 0.184 AIC: 0.552 AIC*n: 187.293 BIC: -1753.287 BIC': -21.990 1063 . scalar SigDoseInthbMw2 = "no" 1064 . scalar MainEffInthbMw2 = "age radhlw2 shfamw2" 1065 . scalar InthbModMw2 = "none" 1066 . 1067 . *------chunk 8 female moderator models 1068 . title4 "trimmed Moderators of female Dose => Interests and Hobbies Impact" ------------------------------------------------------------------------------- trimmed Moderators of female Dose => Interests and Hobbies Impact ------------------------------------------------------------------------------- 1069 . 1070 . 1071 . forvalues j = 2/2 { 2. set more off 3. 1072 . des age educ1-educ7 marrw`j'1-marrw`j'6 inc1w`j'-inc4w`j' /// > bf1 bf4 bf9 bf11 bf4m bf15m bf30 bf40 4. 1073 . foreach var in HP2inthob { 5. local w2bf bf1 bf4 bf6 bf7 bf14 bf15 bf40 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. 1074 . xi: logistic `var' age /// > radhlw`j' avgcumdosew`j' /// > bf4 /// > if gender==2, coef 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 marrw21 byte %8.0g marrw2==1. single marrw22 byte %8.0g marrw2==2. cohabitating marrw23 byte %8.0g marrw2==3. married marrw24 byte %8.0g marrw2==4. separated marrw25 byte %8.0g marrw2==5. divorced marrw26 byte %8.0g marrw2==6. widowed inc1w2 double %15.0g LABJ Income is not sufficient for basic neccessities in 1996 inc2w2 double %15.0g LABJ Income is just sufficient for basic neccessities in 1996 inc3w2 double %15.0g LABJ Income is sufficient for basics plus extra purchases/savings in 1996 inc4w2 double %15.0g LABJ Income allows to comfortably afford luxury items in 1996 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= 2 chunk 8 H1 test:Gender= male model Wave = 2 for HP2inthob ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Full Nottingham Part 2 subscale models for females ***** ***** ***** ***** ***** ***** 16 Jun 2012 21:57:25 ***** ******************************************************************************* ******************************************************************************* Logistic regression Number of obs = 363 LR chi2(4) = 85.23 Prob > chi2 = 0.0000 Log likelihood = -129.49784 Pseudo R2 = 0.2476 ------------------------------------------------------------------------------ HP2inthob | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0747628 .0160244 4.67 0.000 .0433556 .10617 radhlw2 | .0174604 .0053569 3.26 0.001 .0069611 .0279597 avgcumdosew2 | .0556287 .0871446 0.64 0.523 -.1151717 .226429 bf4 | -.0957645 .0312145 -3.07 0.002 -.1569439 -.0345852 _cons | -5.962105 1.09169 -5.46 0.000 -8.101778 -3.822431 ------------------------------------------------------------------------------ Logistic model for HP2inthob -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 27 8 | 35 - | 39 289 | 328 -----------+--------------------------+----------- Total | 66 297 | 363 Classified + if predicted Pr(D) >= .5 True D defined as HP2inthob != 0 -------------------------------------------------- Sensitivity Pr( +| D) 40.91% Specificity Pr( -|~D) 97.31% Positive predictive value Pr( D| +) 77.14% Negative predictive value Pr(~D| -) 88.11% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 2.69% False - rate for true D Pr( -| D) 59.09% False + rate for classified + Pr(~D| +) 22.86% False - rate for classified - Pr( D| -) 11.89% -------------------------------------------------- Correctly classified 87.05% -------------------------------------------------- Logistic model for HP2inthob, goodness-of-fit test number of observations = 363 number of covariate patterns = 361 Pearson chi2(356) = 453.01 Prob > chi2 = 0.0004 Measures of Fit for logistic of HP2inthob Log-Lik Intercept Only: -172.113 Log-Lik Full Model: -129.498 D(358): 258.996 LR(4): 85.229 Prob > LR: 0.000 McFadden's R2: 0.248 McFadden's Adj R2: 0.219 Maximum Likelihood R2: 0.209 Cragg & Uhler's R2: 0.342 McKelvey and Zavoina's R2: 0.407 Efron's R2: 0.292 Variance of y*: 5.547 Variance of error: 3.290 Count R2: 0.871 Adj Count R2: 0.288 AIC: 0.741 AIC*n: 268.996 BIC: -1851.201 BIC': -61.652 1075 . scalar SigdoseInthbFw2 = "no" 1076 . scalar MainEffInthbFw2 = "age radhlw2 bf4" 1077 . 1078 . *------chunk 8 testing female moderators 1079 . title " trimmed Moderators of female Dose => Interests and Hobbies Impact" ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** trimmed Moderators of female Dose => Interests and Hobbies Impact ***** ***** ***** ***** ***** ***** 16 Jun 2012 21:57:26 ***** ******************************************************************************* ******************************************************************************* 1080 . 1081 . 1082 . forvalues j = 2/2 { 2. set more off 3. 1083 . des age educ1-educ7 marrw`j'1-marrw`j'6 inc1w`j'-inc4w`j' /// > bf1 bf4 bf9 bf11 bf4m bf15m bf30 bf40 4. 1084 . foreach var in HP2inthob { 5. local w2bf bf1 bf4 bf6 bf7 bf14 bf15 bf40 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. 1085 . xi: logistic `var' age /// > radhlw`j' avgcumdosew`j' /// > bf4 bf4Xd2 ageXd2 radhlw2Xd2 /// > if gender==2, coef 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 marrw21 byte %8.0g marrw2==1. single marrw22 byte %8.0g marrw2==2. cohabitating marrw23 byte %8.0g marrw2==3. married marrw24 byte %8.0g marrw2==4. separated marrw25 byte %8.0g marrw2==5. divorced marrw26 byte %8.0g marrw2==6. widowed inc1w2 double %15.0g LABJ Income is not sufficient for basic neccessities in 1996 inc2w2 double %15.0g LABJ Income is just sufficient for basic neccessities in 1996 inc3w2 double %15.0g LABJ Income is sufficient for basics plus extra purchases/savings in 1996 inc4w2 double %15.0g LABJ Income allows to comfortably afford luxury items in 1996 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= 2 chunk 8 H1 test:Gender= male model Wave = 2 for HP2inthob ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Full Nottingham Part 2 subscale models for females in wave=2 ***** ***** ***** ***** ***** ***** 16 Jun 2012 21:57:26 ***** ******************************************************************************* ******************************************************************************* Logistic regression Number of obs = 363 LR chi2(7) = 87.82 Prob > chi2 = 0.0000 Log likelihood = -128.20013 Pseudo R2 = 0.2551 ------------------------------------------------------------------------------ HP2inthob | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .069622 .0190503 3.65 0.000 .0322841 .1069599 radhlw2 | .0222021 .0063839 3.48 0.001 .00969 .0347143 avgcumdosew2 | .0545345 .7778922 0.07 0.944 -1.470106 1.579175 bf4 | -.096555 .0395926 -2.44 0.015 -.1741551 -.0189549 bf4Xd2 | -.0006382 .0261986 -0.02 0.981 -.0519866 .0507102 ageXd2 | .0057178 .0123652 0.46 0.644 -.0185176 .0299531 radhlw2Xd2 | -.0041808 .003242 -1.29 0.197 -.0105349 .0021734 _cons | -6.018454 1.285872 -4.68 0.000 -8.538717 -3.498191 ------------------------------------------------------------------------------ Logistic model for HP2inthob -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 28 9 | 37 - | 38 288 | 326 -----------+--------------------------+----------- Total | 66 297 | 363 Classified + if predicted Pr(D) >= .5 True D defined as HP2inthob != 0 -------------------------------------------------- Sensitivity Pr( +| D) 42.42% Specificity Pr( -|~D) 96.97% Positive predictive value Pr( D| +) 75.68% Negative predictive value Pr(~D| -) 88.34% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 3.03% False - rate for true D Pr( -| D) 57.58% False + rate for classified + Pr(~D| +) 24.32% False - rate for classified - Pr( D| -) 11.66% -------------------------------------------------- Correctly classified 87.05% -------------------------------------------------- Logistic model for HP2inthob, goodness-of-fit test number of observations = 363 number of covariate patterns = 361 Pearson chi2(353) = 461.27 Prob > chi2 = 0.0001 Measures of Fit for logistic of HP2inthob Log-Lik Intercept Only: -172.113 Log-Lik Full Model: -128.200 D(355): 256.400 LR(7): 87.825 Prob > LR: 0.000 McFadden's R2: 0.255 McFadden's Adj R2: 0.209 Maximum Likelihood R2: 0.215 Cragg & Uhler's R2: 0.351 McKelvey and Zavoina's R2: 0.419 Efron's R2: 0.304 Variance of y*: 5.660 Variance of error: 3.290 Count R2: 0.871 Adj Count R2: 0.288 AIC: 0.750 AIC*n: 272.400 BIC: -1836.113 BIC': -46.564 1086 . scalar InthbModFw2 = "none" 1087 . 1088 . title4 " dose- interests and hobbies mediator effect models" ------------------------------------------------------------------------------- dose- interests and hobbies mediator effect models ------------------------------------------------------------------------------- 1089 . 1090 . * age is a mediating effect for males for Dose=> sex life for men 1091 . 1092 . glm age avgcumdosew2 if gender==1, fam(gaus) link(identity) Iteration 0: log likelihood = -1330.6004 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = 147.6853 Deviance = 49917.64009 (1/df) Deviance = 147.6853 Pearson = 49917.64009 (1/df) Pearson = 147.6853 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 7.838826 Log likelihood = -1330.6004 BIC = 47947.46 ------------------------------------------------------------------------------ | OIM age | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew2 | .5832314 .2635871 2.21 0.027 .0666101 1.099853 _cons | 48.62133 .7061562 68.85 0.000 47.23729 50.00537 ------------------------------------------------------------------------------ 1093 . 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.) 1094 . 1095 . * illness is a mediating effect for males = > sex life for men 1096 . des illw2 storage display value variable name type format label variable label ------------------------------------------------------------------------------- illw2 double %8.0g Total number of illnesses experienced in time period 1987-1996 1097 . glm illw2 avgcumdosew2 if gender==1, fam(gaus) link(identity) Iteration 0: log likelihood = -303.59609 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = .3512988 Deviance = 118.7390083 (1/df) Deviance = .3512988 Pearson = 118.7390083 (1/df) Pearson = .3512988 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 1.797624 Log likelihood = -303.5960853 BIC = -1851.445 ------------------------------------------------------------------------------ | OIM illw2 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew2 | .0085423 .0128556 0.66 0.506 -.0166543 .0337389 _cons | .2741359 .0344406 7.96 0.000 .2066336 .3416382 ------------------------------------------------------------------------------ 1098 . glm HP2inthob illw2 if gender==1, fam(bin) irls scale(dev) link(probit) Iteration 1: deviance = 237.2651 Iteration 2: deviance = 236.0196 Iteration 3: deviance = 236.0142 Iteration 4: deviance = 236.0142 Iteration 5: deviance = 236.0142 Generalized linear models No. of obs = 340 Optimization : MQL Fisher scoring Residual df = 338 (IRLS EIM) Scale parameter = 1 Deviance = 236.0141663 (1/df) Deviance = .6982668 Pearson = 338.89241 (1/df) Pearson = 1.00264 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1734.169 ------------------------------------------------------------------------------ | EIM HP2inthob | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- illw2 | .2044103 .113873 1.80 0.073 -.0187766 .4275973 _cons | -1.284117 .0852302 -15.07 0.000 -1.451165 -1.117069 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 1099 . 1100 . des radhlw2 storage display value variable name type format label variable label ------------------------------------------------------------------------------- radhlw2 double %8.0g Self-perceived Chornobyl health threat in Wave 2 1101 . glm radhlw2 avgcumdosew2 if gender==1, fam(gaus) link(identity) Iteration 0: log likelihood = -1693.4076 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = 1247.933 Deviance = 421801.4584 (1/df) Deviance = 1247.933 Pearson = 421801.4584 (1/df) Pearson = 1247.933 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 9.972986 Log likelihood = -1693.407647 BIC = 419831.3 ------------------------------------------------------------------------------ | OIM radhlw2 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew2 | 1.220373 .766216 1.59 0.111 -.2813831 2.722128 _cons | 45.63198 2.052711 22.23 0.000 41.60874 49.65522 ------------------------------------------------------------------------------ 1102 . glm HP2inthob radhlw2 if gender==1, fam(bin) irls scale(dev) link(probit) Iteration 1: deviance = 207.4869 Iteration 2: deviance = 195.0786 Iteration 3: deviance = 193.7239 Iteration 4: deviance = 193.6942 Iteration 5: deviance = 193.6942 Iteration 6: deviance = 193.6942 Generalized linear models No. of obs = 340 Optimization : MQL Fisher scoring Residual df = 338 (IRLS EIM) Scale parameter = 1 Deviance = 193.694234 (1/df) Deviance = .5730599 Pearson = 330.3909814 (1/df) Pearson = .9774881 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1776.489 ------------------------------------------------------------------------------ | EIM HP2inthob | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- radhlw2 | .0187765 .0024049 7.81 0.000 .014063 .02349 _cons | -2.360804 .1846104 -12.79 0.000 -2.722634 -1.998974 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 1103 . 1104 . 1105 . des shfamw2 storage display value variable name type format label variable label ------------------------------------------------------------------------------- shfamw2 double %8.0g Percentage of strains and hassles related to family in 1996 1106 . glm shfamw2 avgcumdosew2 if gender==1, fam(gaus) link(identity) Iteration 0: log likelihood = -1704.8947 Generalized linear models No. of obs = 339 Optimization : ML Residual df = 337 Scale parameter = 1375.284 Deviance = 463470.769 (1/df) Deviance = 1375.284 Pearson = 463470.769 (1/df) Pearson = 1375.284 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 10.07017 Log likelihood = -1704.894657 BIC = 461507.4 ------------------------------------------------------------------------------ | OIM shfamw2 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew2 | -.7484378 .8043765 -0.93 0.352 -2.324987 .8281112 _cons | 34.76184 2.15791 16.11 0.000 30.53241 38.99127 ------------------------------------------------------------------------------ 1107 . glm HP2inthob shfamw2 if gender==1, fam(bin) irls scale(dev) link(probit) Iteration 1: deviance = 236.0134 Iteration 2: deviance = 234.459 Iteration 3: deviance = 234.4495 Iteration 4: deviance = 234.4495 Generalized linear models No. of obs = 339 Optimization : MQL Fisher scoring Residual df = 337 (IRLS EIM) Scale parameter = 1 Deviance = 234.4495475 (1/df) Deviance = .695696 Pearson = 340.0883436 (1/df) Pearson = 1.009164 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1728.912 ------------------------------------------------------------------------------ | EIM HP2inthob | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- shfamw2 | .0043459 .0019602 2.22 0.027 .0005039 .0081879 _cons | -1.379269 .1084635 -12.72 0.000 -1.591853 -1.166684 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 1108 . 1109 . des bf5m storage display value variable name type format label variable label ------------------------------------------------------------------------------- bf5m float %9.0g bf5m = max(0, ecprw3 - 75) * bf4m 1110 . glm bf5m avgcumdosew2 if gender==1, fam(gaus) link(identity) Iteration 0: log likelihood = -2273.2523 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = 37801.15 Deviance = 12776789.76 (1/df) Deviance = 37801.15 Pearson = 12776789.76 (1/df) Pearson = 37801.15 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 13.38384 Log likelihood = -2273.252279 BIC = 1.28e+07 ------------------------------------------------------------------------------ | OIM bf5m | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew2 | 9.243905 4.217043 2.19 0.028 .9786526 17.50916 _cons | 104.6228 11.29756 9.26 0.000 82.47996 126.7656 ------------------------------------------------------------------------------ 1111 . 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.) 1112 . 1113 . glm bf4 avgcumdosew2 if gender==1, fam(gaus) link(identity) Iteration 0: log likelihood = -1027.1225 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = 24.7771 Deviance = 8374.659221 (1/df) Deviance = 24.7771 Pearson = 8374.659221 (1/df) Pearson = 24.7771 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 6.053662 Log likelihood = -1027.122509 BIC = 6404.476 ------------------------------------------------------------------------------ | OIM bf4 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew2 | -.0331637 .1079644 -0.31 0.759 -.2447701 .1784427 _cons | 12.52896 .2892393 43.32 0.000 11.96206 13.09586 ------------------------------------------------------------------------------ 1114 . 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.) 1115 . 1116 . 1117 . scalar inthobMw2 = "age illw2" 1118 . 1119 . * age is a mediating effect for females for Dose=> sex life for women 1120 . glm age avgcumdosew2 if gender==2, fam(gaus) link(identity) Iteration 0: log likelihood = -1406.9403 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = 136.9184 Deviance = 49427.52828 (1/df) Deviance = 136.9184 Pearson = 49427.52828 (1/df) Pearson = 136.9184 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 7.762756 Log likelihood = -1406.940271 BIC = 47299.65 ------------------------------------------------------------------------------ | OIM age | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew2 | 1.502324 .4454009 3.37 0.001 .6293547 2.375294 _cons | 48.86944 .7323225 66.73 0.000 47.43412 50.30477 ------------------------------------------------------------------------------ 1121 . 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.) 1122 . 1123 . * illw2 is a mediating effect for females for Dose=> sex life for women 1124 . glm illw2 avgcumdosew2 if gender==2, fam(gaus) link(identity) Iteration 0: log likelihood = -463.51524 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = .756881 Deviance = 273.2340487 (1/df) Deviance = .756881 Pearson = 273.2340487 (1/df) Pearson = .756881 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 2.564822 Log likelihood = -463.5152411 BIC = -1854.645 ------------------------------------------------------------------------------ | OIM illw2 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew2 | .1249912 .0331157 3.77 0.000 .0600856 .1898968 _cons | .301285 .0544484 5.53 0.000 .194568 .4080019 ------------------------------------------------------------------------------ 1125 . glm HP2inthob illw2 if gender==2, fam(bin) irls scale(dev) link(probit) Iteration 1: deviance = 337.9924 Iteration 2: deviance = 337.8991 Iteration 3: deviance = 337.8989 Iteration 4: deviance = 337.8989 Generalized linear models No. of obs = 363 Optimization : MQL Fisher scoring Residual df = 361 (IRLS EIM) Scale parameter = 1 Deviance = 337.8988998 (1/df) Deviance = .936008 Pearson = 362.1873188 (1/df) Pearson = 1.003289 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1789.981 ------------------------------------------------------------------------------ | EIM HP2inthob | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- illw2 | .204938 .0789434 2.60 0.009 .0502118 .3596641 _cons | -1.005064 .0841351 -11.95 0.000 -1.169965 -.8401618 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 1126 . 1127 . des bf4 // soma recentered storage display value variable name type format label variable label ------------------------------------------------------------------------------- bf4 float %9.0g bf4 = max(0, 24 - BSIsoma) 1128 . * bf4 is a mediting effect for females for Dose=> sex life for women 1129 . glm bf4 avgcumdosew2 if gender==2, fam(gaus) link(identity) Iteration 0: log likelihood = -1109.0983 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = 26.53281 Deviance = 9578.344971 (1/df) Deviance = 26.53281 Pearson = 9578.344971 (1/df) Pearson = 26.53281 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 6.121754 Log likelihood = -1109.098281 BIC = 7450.466 ------------------------------------------------------------------------------ | OIM bf4 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew2 | -.595012 .1960703 -3.03 0.002 -.9793027 -.2107212 _cons | 11.02048 .3223763 34.19 0.000 10.38863 11.65232 ------------------------------------------------------------------------------ 1130 . 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.) 1131 . 1132 . des bf4m // soma recentered storage display value variable name type format label variable label ------------------------------------------------------------------------------- bf4m float %9.0g bf4m = max(0, 32 - BSIsoma) 1133 . * bf4m is a possible mediating effect for female sex life 1134 . glm bf4m avgcumdosew2 if gender==2, fam(gaus) link(identity) Iteration 0: log likelihood = -1140.8259 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = 31.60104 Deviance = 11407.97484 (1/df) Deviance = 31.60104 Pearson = 11407.97484 (1/df) Pearson = 31.60104 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 6.296561 Log likelihood = -1140.825904 BIC = 9280.095 ------------------------------------------------------------------------------ | OIM bf4m | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew2 | -.599311 .2139789 -2.80 0.005 -1.018702 -.1799202 _cons | 18.83424 .3518214 53.53 0.000 18.14469 19.5238 ------------------------------------------------------------------------------ 1135 . 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.) 1136 . 1137 . des shfamw2 storage display value variable name type format label variable label ------------------------------------------------------------------------------- shfamw2 double %8.0g Percentage of strains and hassles related to family in 1996 1138 . glm shfamw2 avgcumdosew2 if gender==1, fam(gaus) link(identity) Iteration 0: log likelihood = -1704.8947 Generalized linear models No. of obs = 339 Optimization : ML Residual df = 337 Scale parameter = 1375.284 Deviance = 463470.769 (1/df) Deviance = 1375.284 Pearson = 463470.769 (1/df) Pearson = 1375.284 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 10.07017 Log likelihood = -1704.894657 BIC = 461507.4 ------------------------------------------------------------------------------ | OIM shfamw2 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew2 | -.7484378 .8043765 -0.93 0.352 -2.324987 .8281112 _cons | 34.76184 2.15791 16.11 0.000 30.53241 38.99127 ------------------------------------------------------------------------------ 1139 . glm HP2sxlife shfamw2 if gender==1, fam(bin) irls scale(dev) link(probit) Iteration 1: deviance = 338.2157 Iteration 2: deviance = 338.0066 Iteration 3: deviance = 338.0065 Iteration 4: deviance = 338.0065 Generalized linear models No. of obs = 339 Optimization : MQL Fisher scoring Residual df = 337 (IRLS EIM) Scale parameter = 1 Deviance = 338.0064771 (1/df) Deviance = 1.002987 Pearson = 339.3157137 (1/df) Pearson = 1.006872 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1625.356 ------------------------------------------------------------------------------ | EIM HP2sxlife | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- shfamw2 | .0027669 .0020626 1.34 0.180 -.0012757 .0068096 _cons | -.9380005 .1081399 -8.67 0.000 -1.149951 -.7260503 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 1140 . 1141 . des shrelaw2 storage display value variable name type format label variable label ------------------------------------------------------------------------------- shrelaw2 double %8.0g Percentage of strains and hassles related to relationships in 1996 1142 . glm shrelaw2 avgcumdosew2 if gender==1, fam(gaus) link(identity) Iteration 0: log likelihood = -1686.1612 Generalized linear models No. of obs = 339 Optimization : ML Residual df = 337 Scale parameter = 1231.384 Deviance = 414976.438 (1/df) Deviance = 1231.384 Pearson = 414976.438 (1/df) Pearson = 1231.384 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 9.959653 Log likelihood = -1686.16125 BIC = 413013.1 ------------------------------------------------------------------------------ | OIM shrelaw2 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew2 | .6230115 .7612097 0.82 0.413 -.868932 2.114955 _cons | 26.21356 2.042278 12.84 0.000 22.21077 30.21635 ------------------------------------------------------------------------------ 1143 . glm HP2inthob shrelaw2 if gender==1, fam(bin) irls scale(dev) link(probit) Iteration 1: deviance = 236.715 Iteration 2: deviance = 235.3689 Iteration 3: deviance = 235.3625 Iteration 4: deviance = 235.3625 Generalized linear models No. of obs = 339 Optimization : MQL Fisher scoring Residual df = 337 (IRLS EIM) Scale parameter = 1 Deviance = 235.3625161 (1/df) Deviance = .6984051 Pearson = 339.597009 (1/df) Pearson = 1.007706 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1728 ------------------------------------------------------------------------------ | EIM HP2inthob | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- shrelaw2 | .0038952 .0020421 1.91 0.056 -.0001073 .0078976 _cons | -1.331337 .0990092 -13.45 0.000 -1.525391 -1.137282 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 1144 . 1145 . title4 "6. Summary matrix for dose - interests and hobbies impact" ------------------------------------------------------------------------------- 6. Summary matrix for dose - interests and hobbies impact ------------------------------------------------------------------------------- 1146 . *xx summary of mediating effects: males only age and illw2 2 1147 . *xx females: age 1148 . 1149 . 1150 . 1151 . * summary of inthob moderator effects none 1152 . scalar inthobMedMw2 = "age illw2" 1153 . scalar inthobMedFw2 = "age bf4 illw2 bf4m" 1154 . 1155 . * no sign main dose effect for males 1156 . * no male moderators 1157 . * 3 signif main effects in male main effect model 1158 . 1159 . 1160 . * no signif dose main effect for females 1161 . * 3 main female effects 1162 . * no significant female moderators 1163 . di _skip(4) 1164 . matrix define inthbMw2 = J(1,8, 0) 1165 . matrix define inthbFw2 = J(1,8, 0) 1166 . matrix colnames inthbMw2= hypnum ptnum wave gender medsig numMAsig numModsi > g numMed 1167 . matrix colnames inthbFw2= hypnum ptnum wave gender medsig numMAsig numModsi > g numMed 1168 . matrix define inthbMw2= (1, 2, 3, 1, 0, 3, 0, 2 ) 1169 . matrix define inthbFw2= (1, 2, 3, 2, 0, 3, 0, 4 ) 1170 . matrix rowname inthbMw2 = inthbM 1171 . matrix rowname inthbFw2 = inthobF 1172 . matlist inthbMw2 | c1 c2 c3 c4 c5 c6 > c7 c8 -------------+----------------------------------------------------------------- ----------------------- inthbM | 1 2 3 1 0 3 > 0 2 1173 . matlist inthbFw2 | c1 c2 c3 c4 c5 c6 > c7 c8 -------------+----------------------------------------------------------------- ----------------------- inthobF | 1 2 3 2 0 3 > 0 4 1174 . matrix define H1pt2w2 = ( wkMw2 \ wkFw2 \ hmcrMw2 \ hmcrFw2 \ sp > Mw2 /// > \ spFw2 \ prbfamMw2 \ prbfamFw2 \ sxlifeMw2 \ sxlifeFw2 \ inthb > Mw2 \ inthbFw2) 1175 . 1176 . matlist H1pt2w2 | c1 c2 c3 c4 c5 c6 > c7 c8 -------------+----------------------------------------------------------------- ----------------------- r1 | 1 2 2 1 0 2 > 0 2 r1 | 1 2 2 2 0 1 > 0 2 r1 | 1 2 3 1 0 1 > 0 1 r1 | 1 2 3 2 0 1 > 0 1 spMw2 | 1 2 3 1 0 4 > 0 1 spFw2 | 1 2 3 2 1 5 > 0 2 prbfamMw2 | 1 2 3 1 0 3 > 0 1 prbfamFw2 | 1 2 3 2 1 3 > 0 2 sxlifeMw2 | 1 2 3 1 0 2 > 0 2 sxlifeFw2 | 1 2 3 2 0 4 > 0 5 inthbM | 1 2 3 1 0 3 > 0 2 inthobF | 1 2 3 2 0 3 > 0 4 1177 . matrix colnames H1pt2w2 = hypnum ptnum wave gender medsig numMAsig numMo > dsig numMed 1178 . matrix rownames H1pt2w2 = wkMw2 wkFw2 hmcrMw2 hmcrFw2 socprbMw2 s > ocprbFw2 prbfamMw2 prbFamFw2 inthbMw2 inthbFw2 1179 . matlist H1pt2w2 | hypnum ptnum wave gender medsig numMAsig > numModsig numMed -------------+----------------------------------------------------------------- ----------------------- wkMw2 | 1 2 2 1 0 2 > 0 2 wkFw2 | 1 2 2 2 0 1 > 0 2 hmcrMw2 | 1 2 3 1 0 1 > 0 1 hmcrFw2 | 1 2 3 2 0 1 > 0 1 socprbMw2 | 1 2 3 1 0 4 > 0 1 socprbFw2 | 1 2 3 2 1 5 > 0 2 prbfamMw2 | 1 2 3 1 0 3 > 0 1 prbFamFw2 | 1 2 3 2 1 3 > 0 2 inthbMw2 | 1 2 3 1 0 2 > 0 2 inthbFw2 | 1 2 3 2 0 4 > 0 5 inthbFw2 | 1 2 3 1 0 3 > 0 2 inthbFw2 | 1 2 3 2 0 3 > 0 4 1180 . 1181 . title "7. h1 pt2 wave 2 Dose=> vacation plans impact analysis "xxxxxxxxxxxx > xxxxxxx ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** 7. h1 pt2 wave 2 Dose=> vacation plans impact analysis ***** ***** xxxxxxxxxxxxxxxxxxx ***** ***** ***** ***** ***** ***** 16 Jun 2012 21:58:01 ***** ******************************************************************************* ******************************************************************************* 1182 . 1183 . 1184 . 1185 . cap gen hp2vacatn = HP2vacatn 1186 . 1187 . forvalues j = 2/2 { 2. title " H1 pt 2 Wave 2 Dose = > hp2vacatn main effects models" 3. set more off 4. local w1bf bf1 bf4 bf9 bf10 bf11 bf4m bf15m bf20 bf22 bf30 bf40 5. local w2bf bf1 bf4 bf6 bf7 bf14 bf15 bf40 6. local w2bf bf1 bf4 bf6 bf7 bf14 bf15 bf40 7. di _skip(3) 8. 1188 . di as input "Male model Wave 2 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 11. di _skip(4) 12. title3 "trimmed hp2hmcare main effects models for H1 no direct dose effec > t for male" 13. pwcorr hp2hmcare age deaw2 shjobw2 bf7m shjobw2 havmilsq /// > radhlw2 avgcumdosew1 if gender==1, sig obs sidak star(.05) listwise 14. di _skip(1) 15. di as input "For males hp2hmcare on wave3 and d2 is not signif " 16. di _skip(1) 17. logistic hp2hmcare age deaw2 shjobw2 bf7m havmilsq /// > radhlw2 avgcumdosew1 if /// > gender==1, coef 18. } ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** H1 pt 2 Wave 2 Dose = > hp2vacatn main effects models ***** ***** ***** ***** ***** ***** 16 Jun 2012 21:58:01 ***** ******************************************************************************* ******************************************************************************* Male model Wave 2 dose-hp2vactn moderator model i.educ _Ieduc_1-8 (naturally coded; _Ieduc_1 omitted) note: _Ieduc_4 != 0 predicts failure perfectly _Ieduc_4 dropped and 12 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: occ6w2 != 0 predicts failure perfectly occ6w2 dropped and 4 obs not used note: occ8w2 != 0 predicts failure perfectly occ8w2 dropped and 43 obs not used note: marrw22 != 0 predicts failure perfectly marrw22 dropped and 7 obs not used note: marrw26 != 0 predicts failure perfectly marrw26 dropped and 3 obs not used note: inc1w2 != 0 predicts failure perfectly inc1w2 dropped and 15 obs not used note: inc4w2 != 0 predicts failure perfectly inc4w2 dropped and 10 obs not used note: sepaw2 != 0 predicts failure perfectly sepaw2 dropped and 3 obs not used note: marrw25 != 0 predicts success perfectly marrw25 dropped and 1 obs not used note: dvcew2 != 0 predicts failure perfectly dvcew2 dropped and 2 obs not used note: _Ieduc_6 omitted because of collinearity note: bf15 omitted because of collinearity note: radhlw2 omitted because of collinearity note: avgcumdosew2 omitted because of collinearity Logistic regression Number of obs = 226 LR chi2(34) = 89.37 Prob > chi2 = 0.0000 Log likelihood = -56.061123 Pseudo R2 = 0.4435 ------------------------------------------------------------------------------ hp2vacatn | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0518481 .0320007 1.62 0.105 -.0108721 .1145682 _Ieduc_2 | -.8995561 1.385138 -0.65 0.516 -3.614377 1.815265 _Ieduc_3 | -.9705268 .7645926 -1.27 0.204 -2.469101 .5280471 _Ieduc_4 | 0 (omitted) _Ieduc_5 | .2832276 .9129115 0.31 0.756 -1.506046 2.072501 _Ieduc_6 | 0 (omitted) _Ieduc_7 | 0 (omitted) _Ieduc_8 | 0 (omitted) occ1w2 | .8106927 4.39778 0.18 0.854 -7.808798 9.430184 occ2w2 | .6920438 4.410202 0.16 0.875 -7.951794 9.335881 occ3w2 | .1305127 4.486304 0.03 0.977 -8.662482 8.923507 occ4w2 | .89698 4.456507 0.20 0.840 -7.837613 9.631573 occ5w2 | 2.521801 4.487812 0.56 0.574 -6.274149 11.31775 occ6w2 | 0 (omitted) occ7w2 | -.3588464 4.557173 -0.08 0.937 -9.290741 8.573048 occ8w2 | 0 (omitted) marrw21 | -2.421712 1.8269 -1.33 0.185 -6.002369 1.158946 marrw22 | 0 (omitted) marrw23 | -3.630848 1.854766 -1.96 0.050 -7.266123 .0044279 marrw25 | 0 (omitted) marrw26 | 0 (omitted) inc1w2 | 0 (omitted) inc2w2 | 1.85842 4.404089 0.42 0.673 -6.773436 10.49027 inc3w2 | 2.742231 4.406664 0.62 0.534 -5.894672 11.37913 inc4w2 | 0 (omitted) radhlw2 | .0040453 .0113057 0.36 0.720 -.0181135 .0262041 havmil | .0057124 .0149305 0.38 0.702 -.0235508 .0349756 avgcumdosew2 | -.2290056 .2971244 -0.77 0.441 -.8113587 .3533474 bf1 | -.0014462 .0165487 -0.09 0.930 -.0338809 .0309886 bf4 | -.3542988 .0849763 -4.17 0.000 -.5208492 -.1877483 bf6 | .0330318 .0142347 2.32 0.020 .0051324 .0609312 bf7 | .138525 .1284222 1.08 0.281 -.1131778 .3902278 bf14 | -.0001823 .0001057 -1.72 0.085 -.0003895 .0000249 bf15 | 0 (omitted) bf40 | .7151656 .2261712 3.16 0.002 .2718781 1.158453 deaw2 | -.1293481 .4547459 -0.28 0.776 -1.020634 .7619374 dvcew2 | 0 (omitted) sepaw2 | 0 (omitted) accdw2 | .6561002 .566831 1.16 0.247 -.4548681 1.767069 movew2 | .8988969 .8083424 1.11 0.266 -.6854251 2.483219 illw2 | -.1907347 .4011558 -0.48 0.634 -.9769857 .5955162 shfamw2 | .0075499 .0104385 0.72 0.470 -.0129092 .0280089 shhlw2 | -.0086364 .01369 -0.63 0.528 -.0354682 .0181955 shjobw2 | -.0142832 .0135576 -1.05 0.292 -.0408556 .0122892 shrelaw2 | -.0233172 .0117345 -1.99 0.047 -.0463164 -.000318 suprtw2 | .0076256 .010193 0.75 0.454 -.0123524 .0276036 suchrw2 | -.0031525 .0091098 -0.35 0.729 -.0210073 .0147023 havmilsq | -.00002 .0000344 -0.58 0.560 -.0000874 .0000473 radhlw2 | 0 (omitted) avgcumdosew2 | 0 (omitted) _cons | -2.643954 3.239572 -0.82 0.414 -8.993397 3.70549 ------------------------------------------------------------------------------ Note: 1 failure and 0 successes completely determined. ------------------------------------------------------------------------------- title3 : trimmed hp2hmcare main effects models for H1 no direct dose effect for > male 16 Jun 2012 21:58:02 computer Macintosh (Intel 64-bit) folder /Users/robertyaffee/Documents/data/research/chwk/phase3/Htests/h1tests/ > h1pt2 Data file chwide16june2012.dta currrently has 2389 variables and 703 obse > rvations | hp2hmc~e age deaw2 shjobw2 bf7m shjobw2 havmilsq -------------+--------------------------------------------------------------- hp2hmcare | 1.0000 | | 340 | age | 0.2761* 1.0000 | 0.0000 | 340 340 | deaw2 | 0.0240 0.2906* 1.0000 | 1.0000 0.0000 | 340 340 340 | shjobw2 | 0.0806 0.0604 -0.0188 1.0000 | 0.9953 1.0000 1.0000 | 340 340 340 340 | bf7m | -0.1339 -0.0182 0.1279 0.0160 1.0000 | 0.3860 1.0000 0.4863 1.0000 | 340 340 340 340 340 | shjobw2 | 0.0806 0.0604 -0.0188 1.0000* 0.0160 1.0000 | 0.9953 1.0000 1.0000 0.0000 1.0000 | 340 340 340 340 340 340 | havmilsq | -0.0347 0.0207 -0.0098 -0.0082 -0.0420 -0.0082 1.0000 | 1.0000 1.0000 1.0000 1.0000 1.0000 1.0000 | 340 340 340 340 340 340 340 | radhlw2 | 0.2793* 0.3358* -0.0218 0.2249* 0.1098 0.2249* -0.0846 | 0.0000 0.0000 1.0000 0.0010 0.7946 0.0010 0.9898 | 340 340 340 340 340 340 340 | avgcumdosew1 | 0.0010 0.0918 0.0232 0.0706 0.0206 0.0706 -0.0345 | 1.0000 0.9680 1.0000 0.9996 1.0000 0.9996 1.0000 | 340 340 340 340 340 340 340 | | radhlw2 avgcum~1 -------------+------------------ radhlw2 | 1.0000 | | 340 | avgcumdosew1 | 0.0826 1.0000 | 0.9929 | 340 340 | For males hp2hmcare on wave3 and d2 is not signif Logistic regression Number of obs = 340 LR chi2(7) = 48.88 Prob > chi2 = 0.0000 Log likelihood = -148.43473 Pseudo R2 = 0.1414 ------------------------------------------------------------------------------ hp2hmcare | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0450179 .0133302 3.38 0.001 .0188913 .0711446 deaw2 | .0173604 .2473738 0.07 0.944 -.4674833 .502204 shjobw2 | .0027843 .0037898 0.73 0.463 -.0046436 .0102121 bf7m | -.0005385 .0002016 -2.67 0.008 -.0009337 -.0001433 havmilsq | -1.19e-06 2.74e-06 -0.44 0.663 -6.56e-06 4.17e-06 radhlw2 | .0157842 .0044199 3.57 0.000 .0071214 .024447 avgcumdosew1 | -.0485455 .0977732 -0.50 0.620 -.2401774 .1430864 _cons | -4.109458 .7445561 -5.52 0.000 -5.568762 -2.650155 ------------------------------------------------------------------------------ 1189 . 1190 . scalar SigDoseVactnMw2 = "no" 1191 . scalar MainEffVactnMw2 = "age bf7m radhlw2 " 1192 . 1193 . local cn7:colnames(e(b)) 1194 . di "`cn7'" age deaw2 shjobw2 bf7m havmilsq radhlw2 avgcumdosew1 _cons 1195 . local len7 = length("`cn7'") 1196 . di `len7' 58 1197 . local len7b = `len7' - 6 1198 . di `len7b' 52 1199 . local myvarlist = substr("`cn7'",1,`len7b') 1200 . di "`myvarlist'" age deaw2 shjobw2 bf7m havmilsq radhlw2 avgcumdosew1 1201 . 1202 . foreach var in `myvarlist' { 2. cap gen `var'Xd2 = `var'*avgcumdosew2 3. } 1203 . 1204 . title " Trimmed male main effects dose=> vacation plans model" ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Trimmed male main effects dose=> vacation plans model ***** ***** ***** ***** ***** ***** 16 Jun 2012 21:58:04 ***** ******************************************************************************* ******************************************************************************* 1205 . di as input "No sig main male dose main effects model" No sig main male dose main effects model 1206 . sw, pr(.1): logit hp2vacatn `myvarlist' if gender==1 begin with full model p = 0.7050 >= 0.1000 removing deaw2 p = 0.6331 >= 0.1000 removing avgcumdosew1 p = 0.4916 >= 0.1000 removing shjobw2 p = 0.4627 >= 0.1000 removing havmilsq p = 0.1243 >= 0.1000 removing bf7m Logistic regression Number of obs = 340 LR chi2(2) = 36.09 Prob > chi2 = 0.0000 Log likelihood = -107.10862 Pseudo R2 = 0.1442 ------------------------------------------------------------------------------ hp2vacatn | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0587352 .0156958 3.74 0.000 .027972 .0894984 radhlw2 | .0163217 .005398 3.02 0.002 .0057417 .0269016 _cons | -6.0454 .8953448 -6.75 0.000 -7.800244 -4.290557 ------------------------------------------------------------------------------ 1207 . 1208 . 1209 . local cn8:colnames(e(b)) 1210 . di "`cn8'" age radhlw2 _cons 1211 . local len8 = length("`cn8'") 1212 . di `len7' 58 1213 . local len8b = `len8' - 6 1214 . di `len8b' 11 1215 . local myvarlist = substr("`cn8'",1,`len8b') 1216 . di "`myvarlist'" age radhlw2 1217 . 1218 . logit hp2vacatn age radhlw2 avgcumdosew2 ageXd2 radhlw2Xd2 if gender==1 Iteration 0: log likelihood = -125.15243 Iteration 1: log likelihood = -109.21801 Iteration 2: log likelihood = -106.67525 Iteration 3: log likelihood = -106.57547 Iteration 4: log likelihood = -106.5735 Iteration 5: log likelihood = -106.5735 Logistic regression Number of obs = 340 LR chi2(5) = 37.16 Prob > chi2 = 0.0000 Log likelihood = -106.5735 Pseudo R2 = 0.1485 ------------------------------------------------------------------------------ hp2vacatn | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0665329 .0222738 2.99 0.003 .022877 .1101887 radhlw2 | .0125498 .0074393 1.69 0.092 -.0020309 .0271304 avgcumdosew2 | .1747054 1.332435 0.13 0.896 -2.436818 2.786229 ageXd2 | -.0112359 .0243435 -0.46 0.644 -.0589483 .0364764 radhlw2Xd2 | .005418 .0075235 0.72 0.471 -.0093278 .0201638 _cons | -6.162813 1.25139 -4.92 0.000 -8.615492 -3.710135 ------------------------------------------------------------------------------ 1219 . 1220 . title "Trimmed male interaction dose=> vacation plans model" ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** Trimmed male interaction dose=> vacation plans model ***** ***** ***** ***** ***** ***** 16 Jun 2012 21:58:14 ***** ******************************************************************************* ******************************************************************************* 1221 . logit hp2vacatn age radhlw2 ageXd2 bf7m avgcumdosew2 bf4m bf4mXd2 bf7mXd2 if > gender==1 Iteration 0: log likelihood = -125.15243 Iteration 1: log likelihood = -103.6908 Iteration 2: log likelihood = -95.548287 Iteration 3: log likelihood = -94.791601 Iteration 4: log likelihood = -94.72809 Iteration 5: log likelihood = -94.72726 Iteration 6: log likelihood = -94.727259 Logistic regression Number of obs = 340 LR chi2(8) = 60.85 Prob > chi2 = 0.0000 Log likelihood = -94.727259 Pseudo R2 = 0.2431 ------------------------------------------------------------------------------ hp2vacatn | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0748804 .0361789 2.07 0.038 .003971 .1457898 radhlw2 | .000021 .0067408 0.00 0.998 -.0131908 .0132328 ageXd2 | -.0497686 .0503553 -0.99 0.323 -.1484632 .0489259 bf7m | .0001854 .0004234 0.44 0.661 -.0006444 .0010153 avgcumdosew2 | 4.201192 4.071901 1.03 0.302 -3.779588 12.18197 bf4m | -.1121478 .0674199 -1.66 0.096 -.2442883 .0199927 bf4mXd2 | -.0946542 .0750285 -1.26 0.207 -.2417073 .0523988 bf7mXd2 | .0002633 .0003512 0.75 0.453 -.0004251 .0009517 _cons | -4.20268 2.927797 -1.44 0.151 -9.941058 1.535697 ------------------------------------------------------------------------------ Note: 1 failure and 0 successes completely determined. 1222 . 1223 . scalar vactnModMw2 ="none" 1224 . 1225 . di as input "Trimmed Female model Wave 2j = 2/2j = 2/2 main effects dose-hp2 > vacatn model " Trimmed Female model Wave 2j = 2/2j = 2/2 main effects dose-hp2vacatn model 1226 . forvalues j = 2/2 { 2. local w2bf bf1 bf4 bf6 bf7 bf14 bf15 bf40 3. 1227 . xi: logistic hp2vacatn age radhlw`j' avgcumdosew`j' /// > deaw`j' suchrw`j' /// > if gender==2, coef difficult iterate(50) 4. 1228 . } Logistic regression Number of obs = 363 LR chi2(5) = 70.03 Prob > chi2 = 0.0000 Log likelihood = -132.50308 Pseudo R2 = 0.2090 ------------------------------------------------------------------------------ hp2vacatn | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0851818 .0154813 5.50 0.000 .054839 .1155246 radhlw2 | .0170145 .0053804 3.16 0.002 .0064692 .0275599 avgcumdosew2 | .0786711 .0879844 0.89 0.371 -.0937752 .2511173 deaw2 | .201149 .1681372 1.20 0.232 -.1283938 .5306918 suchrw2 | -.0020193 .0038609 -0.52 0.601 -.0095866 .005548 _cons | -7.431055 .9998597 -7.43 0.000 -9.390744 -5.471366 ------------------------------------------------------------------------------ 1229 . 1230 . scalar SigDoseVactnMw2 = "no" 1231 . scalar VactnModMw2 = "none" 1232 . 1233 . * summary of male moderating effects: no sign main dose effect in main effec > ts model 1234 . * no signif male moderators 1235 . * 3 significant main effects in main effects model 1236 . 1237 . * summary of female moderation main effects: no signif main dose effect 1238 . 1239 . 1240 . 1241 . * general female dose vacatn w2 models 1242 . 1243 . forvalues j = 2/2 { 2. title " H1 pt 2 Wave 2 Dose = > hp2vacatn main effects models" 3. set more off 4. local w1bf bf1 bf4 bf9 bf10 bf11 bf4m bf15m bf20 bf22 bf30 bf40 5. local w2bf bf1 bf4 bf6 bf7 bf14 bf15 bf40 6. local w2bf bf1 bf4 bf6 bf7 bf14 bf15 bf40 7. di _skip(3) 8. 1244 . di as input "Male model Wave 2 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 11. di _skip(4) 12. title3 "trimmed hp2hmcare main effects models for H1 no direct dose effec > t for male" 13. pwcorr hp2hmcare age deaw2 shjobw2 bf7m shjobw2 havmilsq /// > radhlw2 avgcumdosew1 if gender==1, sig obs sidak star(.05) listwise 14. di _skip(1) 15. di as input "For males hp2hmcare on wave3 and d2 is not signif " 16. di _skip(1) 17. logistic hp2hmcare age deaw2 shjobw2 bf7m havmilsq /// > radhlw2 avgcumdosew1 if /// > gender==2, coef 18. } ******************************************************************************* ******************************************************************************* ***** ***** ***** ***** ***** H1 pt 2 Wave 2 Dose = > hp2vacatn main effects models ***** ***** ***** ***** ***** ***** 16 Jun 2012 21:58:17 ***** ******************************************************************************* ******************************************************************************* Male model Wave 2 dose-hp2vactn moderator model i.educ _Ieduc_1-8 (naturally coded; _Ieduc_1 omitted) note: _Ieduc_4 != 0 predicts failure perfectly _Ieduc_4 dropped and 12 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: occ6w2 != 0 predicts failure perfectly occ6w2 dropped and 4 obs not used note: occ8w2 != 0 predicts failure perfectly occ8w2 dropped and 43 obs not used note: marrw22 != 0 predicts failure perfectly marrw22 dropped and 7 obs not used note: marrw26 != 0 predicts failure perfectly marrw26 dropped and 3 obs not used note: inc1w2 != 0 predicts failure perfectly inc1w2 dropped and 15 obs not used note: inc4w2 != 0 predicts failure perfectly inc4w2 dropped and 10 obs not used note: sepaw2 != 0 predicts failure perfectly sepaw2 dropped and 3 obs not used note: marrw25 != 0 predicts success perfectly marrw25 dropped and 1 obs not used note: dvcew2 != 0 predicts failure perfectly dvcew2 dropped and 2 obs not used note: _Ieduc_6 omitted because of collinearity note: bf15 omitted because of collinearity note: radhlw2 omitted because of collinearity note: avgcumdosew2 omitted because of collinearity Logistic regression Number of obs = 226 LR chi2(34) = 89.37 Prob > chi2 = 0.0000 Log likelihood = -56.061123 Pseudo R2 = 0.4435 ------------------------------------------------------------------------------ hp2vacatn | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0518481 .0320007 1.62 0.105 -.0108721 .1145682 _Ieduc_2 | -.8995561 1.385138 -0.65 0.516 -3.614377 1.815265 _Ieduc_3 | -.9705268 .7645926 -1.27 0.204 -2.469101 .5280471 _Ieduc_4 | 0 (omitted) _Ieduc_5 | .2832276 .9129115 0.31 0.756 -1.506046 2.072501 _Ieduc_6 | 0 (omitted) _Ieduc_7 | 0 (omitted) _Ieduc_8 | 0 (omitted) occ1w2 | .8106927 4.39778 0.18 0.854 -7.808798 9.430184 occ2w2 | .6920438 4.410202 0.16 0.875 -7.951794 9.335881 occ3w2 | .1305127 4.486304 0.03 0.977 -8.662482 8.923507 occ4w2 | .89698 4.456507 0.20 0.840 -7.837613 9.631573 occ5w2 | 2.521801 4.487812 0.56 0.574 -6.274149 11.31775 occ6w2 | 0 (omitted) occ7w2 | -.3588464 4.557173 -0.08 0.937 -9.290741 8.573048 occ8w2 | 0 (omitted) marrw21 | -2.421712 1.8269 -1.33 0.185 -6.002369 1.158946 marrw22 | 0 (omitted) marrw23 | -3.630848 1.854766 -1.96 0.050 -7.266123 .0044279 marrw25 | 0 (omitted) marrw26 | 0 (omitted) inc1w2 | 0 (omitted) inc2w2 | 1.85842 4.404089 0.42 0.673 -6.773436 10.49027 inc3w2 | 2.742231 4.406664 0.62 0.534 -5.894672 11.37913 inc4w2 | 0 (omitted) radhlw2 | .0040453 .0113057 0.36 0.720 -.0181135 .0262041 havmil | .0057124 .0149305 0.38 0.702 -.0235508 .0349756 avgcumdosew2 | -.2290056 .2971244 -0.77 0.441 -.8113587 .3533474 bf1 | -.0014462 .0165487 -0.09 0.930 -.0338809 .0309886 bf4 | -.3542988 .0849763 -4.17 0.000 -.5208492 -.1877483 bf6 | .0330318 .0142347 2.32 0.020 .0051324 .0609312 bf7 | .138525 .1284222 1.08 0.281 -.1131778 .3902278 bf14 | -.0001823 .0001057 -1.72 0.085 -.0003895 .0000249 bf15 | 0 (omitted) bf40 | .7151656 .2261712 3.16 0.002 .2718781 1.158453 deaw2 | -.1293481 .4547459 -0.28 0.776 -1.020634 .7619374 dvcew2 | 0 (omitted) sepaw2 | 0 (omitted) accdw2 | .6561002 .566831 1.16 0.247 -.4548681 1.767069 movew2 | .8988969 .8083424 1.11 0.266 -.6854251 2.483219 illw2 | -.1907347 .4011558 -0.48 0.634 -.9769857 .5955162 shfamw2 | .0075499 .0104385 0.72 0.470 -.0129092 .0280089 shhlw2 | -.0086364 .01369 -0.63 0.528 -.0354682 .0181955 shjobw2 | -.0142832 .0135576 -1.05 0.292 -.0408556 .0122892 shrelaw2 | -.0233172 .0117345 -1.99 0.047 -.0463164 -.000318 suprtw2 | .0076256 .010193 0.75 0.454 -.0123524 .0276036 suchrw2 | -.0031525 .0091098 -0.35 0.729 -.0210073 .0147023 havmilsq | -.00002 .0000344 -0.58 0.560 -.0000874 .0000473 radhlw2 | 0 (omitted) avgcumdosew2 | 0 (omitted) _cons | -2.643954 3.239572 -0.82 0.414 -8.993397 3.70549 ------------------------------------------------------------------------------ Note: 1 failure and 0 successes completely determined. ------------------------------------------------------------------------------- title3 : trimmed hp2hmcare main effects models for H1 no direct dose effect for > male 16 Jun 2012 21:58:18 computer Macintosh (Intel 64-bit) folder /Users/robertyaffee/Documents/data/research/chwk/phase3/Htests/h1tests/ > h1pt2 Data file chwide16june2012.dta currrently has 2393 variables and 703 obse > rvations | hp2hmc~e age deaw2 shjobw2 bf7m shjobw2 havmilsq -------------+--------------------------------------------------------------- hp2hmcare | 1.0000 | | 340 | age | 0.2761* 1.0000 | 0.0000 | 340 340 | deaw2 | 0.0240 0.2906* 1.0000 | 1.0000 0.0000 | 340 340 340 | shjobw2 | 0.0806 0.0604 -0.0188 1.0000 | 0.9953 1.0000 1.0000 | 340 340 340 340 | bf7m | -0.1339 -0.0182 0.1279 0.0160 1.0000 | 0.3860 1.0000 0.4863 1.0000 | 340 340 340 340 340 | shjobw2 | 0.0806 0.0604 -0.0188 1.0000* 0.0160 1.0000 | 0.9953 1.0000 1.0000 0.0000 1.0000 | 340 340 340 340 340 340 | havmilsq | -0.0347 0.0207 -0.0098 -0.0082 -0.0420 -0.0082 1.0000 | 1.0000 1.0000 1.0000 1.0000 1.0000 1.0000 | 340 340 340 340 340 340 340 | radhlw2 | 0.2793* 0.3358* -0.0218 0.2249* 0.1098 0.2249* -0.0846 | 0.0000 0.0000 1.0000 0.0010 0.7946 0.0010 0.9898 | 340 340 340 340 340 340 340 | avgcumdosew1 | 0.0010 0.0918 0.0232 0.0706 0.0206 0.0706 -0.0345 | 1.0000 0.9680 1.0000 0.9996 1.0000 0.9996 1.0000 | 340 340 340 340 340 340 340 | | radhlw2 avgcum~1 -------------+------------------ radhlw2 | 1.0000 | | 340 | avgcumdosew1 | 0.0826 1.0000 | 0.9929 | 340 340 | For males hp2hmcare on wave3 and d2 is not signif Logistic regression Number of obs = 363 LR chi2(7) = 89.48 Prob > chi2 = 0.0000 Log likelihood = -188.98829 Pseudo R2 = 0.1914 ------------------------------------------------------------------------------ hp2hmcare | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0914245 .0127348 7.18 0.000 .0664649 .1163842 deaw2 | .2566908 .1640083 1.57 0.118 -.0647596 .5781412 shjobw2 | -.0020132 .0032819 -0.61 0.540 -.0084456 .0044193 bf7m | -.0004447 .0001853 -2.40 0.016 -.0008079 -.0000816 havmilsq | -1.23e-06 1.60e-06 -0.77 0.443 -4.37e-06 1.91e-06 radhlw2 | .0003168 .0041439 0.08 0.939 -.0078051 .0084387 avgcumdosew1 | -.4512825 .274905 -1.64 0.101 -.9900864 .0875213 _cons | -4.714677 .702826 -6.71 0.000 -6.092191 -3.337164 ------------------------------------------------------------------------------ 1245 . 1246 . * 3 signif main effects 1247 . 1248 . local cn9:colnames(e(b)) 1249 . di "`cn9'" age deaw2 shjobw2 bf7m havmilsq radhlw2 avgcumdosew1 _cons 1250 . local len9 = length("`cn9'") 1251 . di `len9' 58 1252 . local len9b = `len9' - 6 1253 . di `len9b' 52 1254 . local myvarlist = substr("`cn9'",1,`len9b') 1255 . di "`myvarlist'" age deaw2 shjobw2 bf7m havmilsq radhlw2 avgcumdosew1 1256 . 1257 . 1258 . foreach var in `myvarlist' { 2. cap gen `var'Xd2 = `var'*avgcumdosew2 3. } 1259 . 1260 . 1261 . 1262 . title4 "trimmed hp2vacatn wave3 main effects models for H1" ------------------------------------------------------------------------------- trimmed hp2vacatn wave3 main effects models for H1 ------------------------------------------------------------------------------- 1263 . di as input "For females hp2vacatn on wave3" For females hp2vacatn on wave3 1264 . sw, pr(.1):logit hp2vacatn age deaw2 shjobw2 bf7m havmilsq radhlw2 avgcumdose > w2 /// > if gender==2 begin with full model p = 0.7397 >= 0.1000 removing havmilsq p = 0.4709 >= 0.1000 removing avgcumdosew2 p = 0.3504 >= 0.1000 removing deaw2 p = 0.1430 >= 0.1000 removing shjobw2 Logistic regression Number of obs = 363 LR chi2(3) = 73.11 Prob > chi2 = 0.0000 Log likelihood = -130.96199 Pseudo R2 = 0.2182 ------------------------------------------------------------------------------ hp2vacatn | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .0833325 .0154265 5.40 0.000 .0530972 .1135679 radhlw2 | .0230045 .005688 4.04 0.000 .0118562 .0341529 bf7m | -.0005443 .0002398 -2.27 0.023 -.0010144 -.0000743 _cons | -7.040937 .9639411 -7.30 0.000 -8.930227 -5.151647 ------------------------------------------------------------------------------ 1265 . estat class Logistic model for hp2vacatn -------- True -------- Classified | D ~D | Total -----------+--------------------------+----------- + | 21 6 | 27 - | 42 294 | 336 -----------+--------------------------+----------- Total | 63 300 | 363 Classified + if predicted Pr(D) >= .5 True D defined as hp2vacatn != 0 -------------------------------------------------- Sensitivity Pr( +| D) 33.33% Specificity Pr( -|~D) 98.00% Positive predictive value Pr( D| +) 77.78% Negative predictive value Pr(~D| -) 87.50% -------------------------------------------------- False + rate for true ~D Pr( +|~D) 2.00% False - rate for true D Pr( -| D) 66.67% False + rate for classified + Pr(~D| +) 22.22% False - rate for classified - Pr( D| -) 12.50% -------------------------------------------------- Correctly classified 86.78% -------------------------------------------------- 1266 . estat gof Logistic model for hp2vacatn, goodness-of-fit test number of observations = 363 number of covariate patterns = 352 Pearson chi2(348) = 428.22 Prob > chi2 = 0.0021 1267 . fitstat Measures of Fit for logit of hp2vacatn Log-Lik Intercept Only: -167.516 Log-Lik Full Model: -130.962 D(359): 261.924 LR(3): 73.108 Prob > LR: 0.000 McFadden's R2: 0.218 McFadden's Adj R2: 0.194 Maximum Likelihood R2: 0.182 Cragg & Uhler's R2: 0.303 McKelvey and Zavoina's R2: 0.382 Efron's R2: 0.250 Variance of y*: 5.323 Variance of error: 3.290 Count R2: 0.868 Adj Count R2: 0.238 AIC: 0.744 AIC*n: 269.924 BIC: -1854.167 BIC': -55.425 1268 . 1269 . scalar SigDoseVactnFw2 = "no" 1270 . scalar MainEffVactnFw2 = "age radhlw2 bf7m" 1271 . 1272 . cap gen suchrw2Xd2 = suchrw2*avgcumdosew2 1273 . 1274 . di as result " Full moderator model for females for dose=> Vacation plans" Full moderator model for females for dose=> Vacation plans 1275 . logit hp2vacatn age radhlw2 deaw2 suchrw2 avgcumdosew2 ageXd2 radhlw2Xd2 deaw > 2Xd2 /// > bf7m bf7mXd2 havmilsq if gender==2 Iteration 0: log likelihood = -167.516 Iteration 1: log likelihood = -132.6956 Iteration 2: log likelihood = -126.97504 Iteration 3: log likelihood = -126.75963 Iteration 4: log likelihood = -126.75692 Iteration 5: log likelihood = -126.7569 Iteration 6: log likelihood = -126.7569 Logistic regression Number of obs = 363 LR chi2(11) = 81.52 Prob > chi2 = 0.0000 Log likelihood = -126.7569 Pseudo R2 = 0.2433 ------------------------------------------------------------------------------ hp2vacatn | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .1016803 .0203343 5.00 0.000 .0618258 .1415349 radhlw2 | .0224803 .006712 3.35 0.001 .0093251 .0356355 deaw2 | .5684263 .2676717 2.12 0.034 .0437993 1.093053 suchrw2 | -.0044436 .0040662 -1.09 0.274 -.0124132 .003526 avgcumdosew2 | 1.454694 .8439843 1.72 0.085 -.1994849 3.108873 ageXd2 | -.0274517 .0150227 -1.83 0.068 -.0568956 .0019923 radhlw2Xd2 | -.000022 .002904 -0.01 0.994 -.0057137 .0056697 deaw2Xd2 | -.506854 .2727385 -1.86 0.063 -1.041412 .0277036 bf7m | -.0009742 .0003383 -2.88 0.004 -.0016373 -.0003111 bf7mXd2 | .0003801 .0002161 1.76 0.079 -.0000435 .0008037 havmilsq | -3.39e-07 1.17e-06 -0.29 0.772 -2.64e-06 1.96e-06 _cons | -7.723588 1.265256 -6.10 0.000 -10.20345 -5.243731 ------------------------------------------------------------------------------ 1276 . 1277 . title4 "trimmed female moderator model for dose=> vacation plans" ------------------------------------------------------------------------------- trimmed female moderator model for dose=> vacation plans ------------------------------------------------------------------------------- 1278 . logit hp2vacatn age avgcumdosew2 ageXd2 if gender==2 Iteration 0: log likelihood = -167.516 Iteration 1: log likelihood = -142.56205 Iteration 2: log likelihood = -139.72946 Iteration 3: log likelihood = -139.69256 Iteration 4: log likelihood = -139.69255 Logistic regression Number of obs = 363 LR chi2(3) = 55.65 Prob > chi2 = 0.0000 Log likelihood = -139.69255 Pseudo R2 = 0.1661 ------------------------------------------------------------------------------ hp2vacatn | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | .1004779 .0176044 5.71 0.000 .0659739 .1349819 avgcumdosew2 | .5493265 .6015158 0.91 0.361 -.6296229 1.728276 ageXd2 | -.0076822 .0101879 -0.75 0.451 -.0276501 .0122856 _cons | -7.129878 1.024876 -6.96 0.000 -9.138598 -5.121157 ------------------------------------------------------------------------------ 1279 . 1280 . scalar VacatnModFw2 = "none" 1281 . *xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx > xxx 1282 . cap gen hp2vactn = HP2vacatn 1283 . title4 "Male mediator tests for vacation plans impact of dose" ------------------------------------------------------------------------------- Male mediator tests for vacation plans impact of dose ------------------------------------------------------------------------------- 1284 . * for males 1285 . 1286 . * age is a mediator for males 1287 . glm age avgcumdosew2 if gender==1, fam(gaus) link(identity) Iteration 0: log likelihood = -1330.6004 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = 147.6853 Deviance = 49917.64009 (1/df) Deviance = 147.6853 Pearson = 49917.64009 (1/df) Pearson = 147.6853 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 7.838826 Log likelihood = -1330.6004 BIC = 47947.46 ------------------------------------------------------------------------------ | OIM age | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew2 | .5832314 .2635871 2.21 0.027 .0666101 1.099853 _cons | 48.62133 .7061562 68.85 0.000 47.23729 50.00537 ------------------------------------------------------------------------------ 1288 . 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.) 1289 . 1290 . 1291 . des illw2 storage display value variable name type format label variable label ------------------------------------------------------------------------------- illw2 double %8.0g Total number of illnesses experienced in time period 1987-1996 1292 . glm illw2 avgcumdosew2 if gender==1, fam(gaus) link(identity) Iteration 0: log likelihood = -303.59609 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = .3512988 Deviance = 118.7390083 (1/df) Deviance = .3512988 Pearson = 118.7390083 (1/df) Pearson = .3512988 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 1.797624 Log likelihood = -303.5960853 BIC = -1851.445 ------------------------------------------------------------------------------ | OIM illw2 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew2 | .0085423 .0128556 0.66 0.506 -.0166543 .0337389 _cons | .2741359 .0344406 7.96 0.000 .2066336 .3416382 ------------------------------------------------------------------------------ 1293 . glm hp2vactn illw2 if gender==1, fam(bin) irls scale(dev) link(probit) Iteration 1: deviance = 246.5506 Iteration 2: deviance = 245.3093 Iteration 3: deviance = 245.3029 Iteration 4: deviance = 245.3029 Iteration 5: deviance = 245.3029 Generalized linear models No. of obs = 340 Optimization : MQL Fisher scoring Residual df = 338 (IRLS EIM) Scale parameter = 1 Deviance = 245.3029322 (1/df) Deviance = .7257483 Pearson = 335.4909761 (1/df) Pearson = .9925769 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1724.881 ------------------------------------------------------------------------------ | EIM hp2vactn | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- illw2 | .3031606 .1114242 2.72 0.007 .0847731 .5215481 _cons | -1.277579 .0863769 -14.79 0.000 -1.446875 -1.108284 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 1294 . 1295 . des radhlw2 storage display value variable name type format label variable label ------------------------------------------------------------------------------- radhlw2 double %8.0g Self-perceived Chornobyl health threat in Wave 2 1296 . glm radhlw2 avgcumdosew2 if gender==1, fam(gaus) link(identity) Iteration 0: log likelihood = -1693.4076 Generalized linear models No. of obs = 340 Optimization : ML Residual df = 338 Scale parameter = 1247.933 Deviance = 421801.4584 (1/df) Deviance = 1247.933 Pearson = 421801.4584 (1/df) Pearson = 1247.933 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 9.972986 Log likelihood = -1693.407647 BIC = 419831.3 ------------------------------------------------------------------------------ | OIM radhlw2 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew2 | 1.220373 .766216 1.59 0.111 -.2813831 2.722128 _cons | 45.63198 2.052711 22.23 0.000 41.60874 49.65522 ------------------------------------------------------------------------------ 1297 . glm hp2vactn radhlw2 if gender==1, fam(bin) irls scale(dev) link(probit) Iteration 1: deviance = 234.5448 Iteration 2: deviance = 229.6041 Iteration 3: deviance = 229.4465 Iteration 4: deviance = 229.4462 Iteration 5: deviance = 229.4462 Generalized linear models No. of obs = 340 Optimization : MQL Fisher scoring Residual df = 338 (IRLS EIM) Scale parameter = 1 Deviance = 229.4462113 (1/df) Deviance = .6788349 Pearson = 340.4683102 (1/df) Pearson = 1.007303 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1740.737 ------------------------------------------------------------------------------ | EIM hp2vactn | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- radhlw2 | .0116586 .0021811 5.35 0.000 .0073837 .0159334 _cons | -1.817407 .1519393 -11.96 0.000 -2.115203 -1.519612 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 1298 . 1299 . * for females 1300 . 1301 . * age is a mediator for females 1302 . glm age avgcumdosew2 if gender==2, fam(gaus) link(identity) Iteration 0: log likelihood = -1406.9403 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = 136.9184 Deviance = 49427.52828 (1/df) Deviance = 136.9184 Pearson = 49427.52828 (1/df) Pearson = 136.9184 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 7.762756 Log likelihood = -1406.940271 BIC = 47299.65 ------------------------------------------------------------------------------ | OIM age | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew2 | 1.502324 .4454009 3.37 0.001 .6293547 2.375294 _cons | 48.86944 .7323225 66.73 0.000 47.43412 50.30477 ------------------------------------------------------------------------------ 1303 . 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.) 1304 . 1305 . * illness is a mediating effect for females = > vacatn 1306 . des illw2 storage display value variable name type format label variable label ------------------------------------------------------------------------------- illw2 double %8.0g Total number of illnesses experienced in time period 1987-1996 1307 . glm illw2 avgcumdosew2 if gender==2, fam(gaus) link(identity) Iteration 0: log likelihood = -463.51524 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = .756881 Deviance = 273.2340487 (1/df) Deviance = .756881 Pearson = 273.2340487 (1/df) Pearson = .756881 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 2.564822 Log likelihood = -463.5152411 BIC = -1854.645 ------------------------------------------------------------------------------ | OIM illw2 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew2 | .1249912 .0331157 3.77 0.000 .0600856 .1898968 _cons | .301285 .0544484 5.53 0.000 .194568 .4080019 ------------------------------------------------------------------------------ 1308 . glm hp2vactn illw2 if gender==2, fam(bin) irls scale(dev) link(probit) Iteration 1: deviance = 329.874 Iteration 2: deviance = 329.8007 Iteration 3: deviance = 329.8005 Iteration 4: deviance = 329.8005 Generalized linear models No. of obs = 363 Optimization : MQL Fisher scoring Residual df = 361 (IRLS EIM) Scale parameter = 1 Deviance = 329.8005369 (1/df) Deviance = .9135749 Pearson = 363.0908863 (1/df) Pearson = 1.005792 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1798.079 ------------------------------------------------------------------------------ | EIM hp2vactn | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- illw2 | .1861547 .0776301 2.40 0.016 .0340026 .3383068 _cons | -1.027515 .0837109 -12.27 0.000 -1.191586 -.8634451 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 1309 . 1310 . * radhlw2 is a mediating effect for females => vactn 1311 . des radhlw2 storage display value variable name type format label variable label ------------------------------------------------------------------------------- radhlw2 double %8.0g Self-perceived Chornobyl health threat in Wave 2 1312 . glm radhlw2 avgcumdosew2 if gender==2, fam(gaus) link(identity) Iteration 0: log likelihood = -1791.2233 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 361 Scale parameter = 1137.567 Deviance = 410661.5604 (1/df) Deviance = 1137.567 Pearson = 410661.5604 (1/df) Pearson = 1137.567 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 9.880018 Log likelihood = -1791.223306 BIC = 408533.7 ------------------------------------------------------------------------------ | OIM radhlw2 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew2 | 3.302288 1.283833 2.57 0.010 .7860214 5.818555 _cons | 56.95167 2.110863 26.98 0.000 52.81445 61.08888 ------------------------------------------------------------------------------ 1313 . glm hp2vactn radhlw2 if gender==2, fam(bin) irls scale(dev) link(probit) Iteration 1: deviance = 310.7426 Iteration 2: deviance = 307.9144 Iteration 3: deviance = 307.878 Iteration 4: deviance = 307.878 Iteration 5: deviance = 307.878 Generalized linear models No. of obs = 363 Optimization : MQL Fisher scoring Residual df = 361 (IRLS EIM) Scale parameter = 1 Deviance = 307.8780006 (1/df) Deviance = .8528476 Pearson = 369.926962 (1/df) Pearson = 1.024728 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1820.001 ------------------------------------------------------------------------------ | EIM hp2vactn | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- radhlw2 | .0127779 .0023866 5.35 0.000 .0081002 .0174555 _cons | -1.793767 .1848064 -9.71 0.000 -2.15598 -1.431553 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 1314 . 1315 . * summary of male moderating effects: no sign main dose effect in main effec > ts model 1316 . * no signif male moderators 1317 . * 3 significant main effects in main effects model 1318 . * summary omnibus model 1319 . des radhlw2 storage display value variable name type format label variable label ------------------------------------------------------------------------------- radhlw2 double %8.0g Self-perceived Chornobyl health threat in Wave 2 1320 . glm radhlw2 avgcumdosew2 illw2 if gender==2, fam(gaus) link(identity) Iteration 0: log likelihood = -1788.7036 Generalized linear models No. of obs = 363 Optimization : ML Residual df = 360 Scale parameter = 1125 Deviance = 404999.9575 (1/df) Deviance = 1125 Pearson = 404999.9575 (1/df) Pearson = 1125 Variance function: V(u) = 1 [Gaussian] Link function : g(u) = u [Identity] AIC = 9.871645 Log likelihood = -1788.70364 BIC = 402878 ------------------------------------------------------------------------------ | OIM radhlw2 | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- avgcumdosew2 | 2.733328 1.30167 2.10 0.036 .1821022 5.284554 illw2 | 4.552 2.029125 2.24 0.025 .5749882 8.529013 _cons | 55.58022 2.186381 25.42 0.000 51.29499 59.86544 ------------------------------------------------------------------------------ 1321 . glm hp2vactn radhlw2 illw2 avgcumdosew2 if gender==2, fam(bin) irls scale(dev > ) link(probit) Iteration 1: deviance = 306.8282 Iteration 2: deviance = 303.8899 Iteration 3: deviance = 303.8448 Iteration 4: deviance = 303.8448 Iteration 5: deviance = 303.8448 Generalized linear models No. of obs = 363 Optimization : MQL Fisher scoring Residual df = 359 (IRLS EIM) Scale parameter = 1 Deviance = 303.8447923 (1/df) Deviance = .8463643 Pearson = 365.1970108 (1/df) Pearson = 1.017262 Variance function: V(u) = u*(1-u) [Bernoulli] Link function : g(u) = invnorm(u) [Probit] BIC = -1812.246 ------------------------------------------------------------------------------ | EIM hp2vactn | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- radhlw2 | .0120672 .0024098 5.01 0.000 .007344 .0167903 illw2 | .1173614 .0786613 1.49 0.136 -.036812 .2715347 avgcumdosew2 | .0586976 .047942 1.22 0.221 -.035267 .1526623 _cons | -1.859623 .1874026 -9.92 0.000 -2.226926 -1.492321 ------------------------------------------------------------------------------ (Standard errors scaled using square root of deviance-based dispersion.) 1322 . 1323 . 1324 . scalar VactnMedMw2 = "age illw2" 1325 . scalar VactnMedFw2 = "age illw2 radhlw2" 1326 . 1327 . *xx summary of moderator effects for females: 1328 . * no signif main dose effect 1329 . * 3 signif main effects in main effect model 1330 . * 1 moderator: deaw2Xd2 1331 . title4 "7. Summary Matrix construction of dose - vacatn plans impact" ------------------------------------------------------------------------------- 7. Summary Matrix construction of dose - vacatn plans impact ------------------------------------------------------------------------------- 1332 . 1333 . matrix define vactnMw2 = J(1,8, 0) 1334 . matrix define vactnFw2 = J(1,8, 0) 1335 . matrix colnames vactnMw2= hypnum ptnum wave gender medsig numMAsig numModsi > g numMed 1336 . matrix colnames vactnFw2= hypnum ptnum wave gender medsig numMAsig numModsi > g numMed 1337 . matrix define vactnMw2= (1, 2, 3, 1, 0, 3, 0, 2 ) 1338 . matrix define vactnFw2= (1, 2, 3, 2, 0, 3, 0, 3 ) 1339 . matrix rowname vactnMw2 = vactnM 1340 . matrix rowname vactnFw2 = vactnF 1341 . matlist vactnMw2 | c1 c2 c3 c4 c5 c6 > c7 c8 -------------+----------------------------------------------------------------- ----------------------- vactnM | 1 2 3 1 0 3 > 0 2 1342 . matlist vactnFw2 | c1 c2 c3 c4 c5 c6 > c7 c8 -------------+----------------------------------------------------------------- ----------------------- vactnF | 1 2 3 2 0 3 > 0 3 1343 . matrix define H1pt2w2 = ( wkMw2 \ wkFw2 \ hmcrMw2 \ hmcrFw2 \ sp > Mw2 /// > \ spFw2 \ sxlifeMw2 \ sxlifeFw2 \ inthbMw2 \ inthbFw2 \ vactnM > w2 \ vactnFw2 ) 1344 . 1345 . matlist H1pt2w2 | c1 c2 c3 c4 c5 c6 > c7 c8 -------------+----------------------------------------------------------------- ----------------------- r1 | 1 2 2 1 0 2 > 0 2 r1 | 1 2 2 2 0 1 > 0 2 r1 | 1 2 3 1 0 1 > 0 1 r1 | 1 2 3 2 0 1 > 0 1 spMw2 | 1 2 3 1 0 4 > 0 1 spFw2 | 1 2 3 2 1 5 > 0 2 sxlifeMw2 | 1 2 3 1 0 2 > 0 2 sxlifeFw2 | 1 2 3 2 0 4 > 0 5 inthbM | 1 2 3 1 0 3 > 0 2 inthobF | 1 2 3 2 0 3 > 0 4 vactnM | 1 2 3 1 0 3 > 0 2 vactnF | 1 2 3 2 0 3 > 0 3 1346 . matrix colnames H1pt2w2 = hypnum ptnum wave gender medsig numMAsig numMo > dsig numMed 1347 . matrix rownames H1pt2w2 = wkMw2 wkFw2 hmcrMw2 hmcrFw2 socprbMw2 s > ocprbFw2 inthbMw2 inthbFw2 vactnMw2 vacatnFw2 1348 . matlist H1pt2w2 | hypnum ptnum wave gender medsig numMAsig > numModsig numMed -------------+----------------------------------------------------------------- ----------------------- wkMw2 | 1 2 2 1 0 2 > 0 2 wkFw2 | 1 2 2 2 0 1 > 0 2 hmcrMw2 | 1 2 3 1 0 1 > 0 1 hmcrFw2 | 1 2 3 2 0 1 > 0 1 socprbMw2 | 1 2 3 1 0 4 > 0 1 socprbFw2 | 1 2 3 2 1 5 > 0 2 inthbMw2 | 1 2 3 1 0 2 > 0 2 inthbFw2 | 1 2 3 2 0 4 > 0 5 vactnMw2 | 1 2 3 1 0 3 > 0 2 vacatnFw2 | 1 2 3 2 0 3 > 0 4 vacatnFw2 | 1 2 3 1 0 3 > 0 2 vacatnFw2 | 1 2 3 2 0 3 > 0 3 1349 . scalar list VactnMedFw2 = age illw2 radhlw2 VactnMedMw2 = age illw2 VacatnModFw2 = none MainEffVactnFw2 = age radhlw2 bf7m SigDoseVactnFw2 = no VactnModMw2 = none vactnModMw2 = none MainEffVactnMw2 = age bf7m radhlw2 SigDoseVactnMw2 = no inthobMedFw2 = age bf4 illw2 bf4m inthobMedMw2 = age illw2 inthobMw2 = age illw2 InthbModFw2 = none MainEffInthbFw2 = age radhlw2 bf4 SigdoseInthbFw2 = no InthbModMw2 = none MainEffInthbMw2 = age radhlw2 shfamw2 SigDoseInthbMw2 = no MainEffMw2 = radhlw2 bf4 bf40 SigdoseMEinthob = no sxlifeMedFw2 = age illw2 radhlw2 bf4 bf4m sxlifeMedMw2 = age illw2 SxLifeModFw2 = no SigDoseSxlifeFw2 = no MainEffsxlifeFw2 = age radhlw2 bf4 bf4m sxlifeModFw2 = none sxlifeModMw2 = none SigDosesxlifeMw2 = no MainEffsxlifeMw2 = age bf4 PrbfmhmMedFw2 = age bf4 PrbfmhmMedMw2 = age PrbfmhmModFw2 = none MainEffPrbfmhmFw2 = age bf4 bf40 SigDosePrbfmhmFw2 = no PrbfmhmModw2 = none SigDosePrbfmhmMw2 = no SigDosePrbfhmMw2 = no MainEffPrbfhmMw2 = bf4 bf6 bf7 MainEffPrbsocMw2 = age radhlw2 shjobw2 MainEffhmcareMw2 = b4 MainEffwkFw2 = age MainEffwkMw2 = workM: age ProbsocMedFw2 = age radhlw2 ProbsocMedMw2 = age ProbsocModFw2 = none MainEffProbSocFw2 = age avgcomdosew2 radhlw2 avgcumodsew2 b4 SigDoseProbsocFw2 = yes ProbSocModMw2 = none SigDoseProbsocMw2 = no PrbsocModMw2 = none SigdoseMw2 = none hmcareMedFw2 = age hmcareMedMw2 = age hmcareModFw2 = none MainEffhmcarew2 = age SigdoseHmcareFw2 = no hmcareModMw2 = none SigDoseHmcareMw2 = no wkMedFw2 = radhlw2 age bf40 bf4m bf1 NameMedMw2 = age ageXillw2 NumModMw2 = none SigDosehmcareMw2 = no SigDoseWKMw2 = no WkMedFw2 = age bf4 WkMedMw2 = age ageXillw2 WkModFw2 = none WKModMw2 = none SigDoseWkMw2 = no SigDoseWkFw2 = no SigDoseFw2 = no wkModFw2 = none wkModMw2 = none 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 1350 . pwd /Users/robertyaffee/Documents/data/research/chwk/phase3/Htests/h1tests/h1pt2 1351 . di c(filename) chwide16june2012.dta 1352 . 1353 . sjlog close, replace