--------------------------------------------------------------------------------------- name: log: C:\MyDocs\MPH\LectureNotes\ClassDoLogData\logistic regression\5.20.Esophag > ealCa.ClassVersion.log log type: text opened on: 15 Jan 2010, 17:01:50 . set more on . * 5.20.EsophagealCa.ClassVersionlog . * . * Regress esophageal cancers against age and dose of alcohol . * and tobacco using a multiplicative model. . * . use 5.5.EsophagealCa.dta, clear . sort tobacco . by tobacco: tabulate cancer alcohol [freq=patients] , column --------------------------------------------------------------------------------------- -> tobacco = 0-9 +-------------------+ | Key | |-------------------| | frequency | | column percentage | +-------------------+ Esophageal | Alcohol (gm/day) Cancer | 0-39 40-79 80-119 >= 120 | Total -----------+--------------------------------------------+---------- No | 252 145 42 8 | 447 | 96.55 81.01 68.85 33.33 | 85.14 -----------+--------------------------------------------+---------- Yes | 9 34 19 16 | 78 | 3.45 18.99 31.15 66.67 | 14.86 -----------+--------------------------------------------+---------- Total | 261 179 61 24 | 525 | 100.00 100.00 100.00 100.00 | 100.00 --------------------------------------------------------------------------------------- -> tobacco = 10-19 +-------------------+ | Key | |-------------------| | frequency | | column percentage | +-------------------+ Esophageal | Alcohol (gm/day) Cancer | 0-39 40-79 80-119 >= 120 | Total -----------+--------------------------------------------+---------- No | 74 68 30 6 | 178 | 88.10 80.00 61.22 33.33 | 75.42 -----------+--------------------------------------------+---------- Yes | 10 17 19 12 | 58 | 11.90 20.00 38.78 66.67 | 24.58 -----------+--------------------------------------------+---------- Total | 84 85 49 18 | 236 | 100.00 100.00 100.00 100.00 | 100.00 --------------------------------------------------------------------------------------- -> tobacco = 20-29 +-------------------+ | Key | |-------------------| | frequency | | column percentage | +-------------------+ Esophageal | Alcohol (gm/day) Cancer | 0-39 40-79 80-119 >= 120 | Total -----------+--------------------------------------------+---------- No | 37 47 10 5 | 99 | 88.10 75.81 62.50 41.67 | 75.00 -----------+--------------------------------------------+---------- Yes | 5 15 6 7 | 33 | 11.90 24.19 37.50 58.33 | 25.00 -----------+--------------------------------------------+---------- Total | 42 62 16 12 | 132 | 100.00 100.00 100.00 100.00 | 100.00 --------------------------------------------------------------------------------------- -> tobacco = >= 30 +-------------------+ | Key | |-------------------| | frequency | | column percentage | +-------------------+ Esophageal | Alcohol (gm/day) Cancer | 0-39 40-79 80-119 >= 120 | Total -----------+--------------------------------------------+---------- No | 23 20 5 3 | 51 | 82.14 68.97 41.67 23.08 | 62.20 -----------+--------------------------------------------+---------- Yes | 5 9 7 10 | 31 | 17.86 31.03 58.33 76.92 | 37.80 -----------+--------------------------------------------+---------- Total | 28 29 12 13 | 82 | 100.00 100.00 100.00 100.00 | 100.00 . * . * Combine tobacco levels 2 and 3 in a new variable called smoke . * . generate smoke = tobacco . recode smoke 3=2 4=3 (smoke: 96 changes made) . label variable smoke "Smoking (gm/day)" . label define smoke 1 "0-9" 2 "10-29" 3 ">= 30" . label values smoke smoke . table smoke tobacco [freq=patients], row col --------------------------------------------- Smoking | Tobacco (gm/day) (gm/day) | 0-9 10-19 20-29 >= 30 Total ----------+---------------------------------- 0-9 | 525 525 10-29 | 236 132 368 >= 30 | 82 82 | Total | 525 236 132 82 975 --------------------------------------------- . * . * Regress cancer against age, alcohol and smoke . * using a multiplicative model . * . logistic cancer i.age i.alcohol i.smoke [freq=patients] Logistic regression Number of obs = 975 LR chi2(10) = 285.55 Prob > chi2 = 0.0000 Log likelihood = -351.96823 Pseudo R2 = 0.2886 ------------------------------------------------------------------------------ cancer | Odds Ratio Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | 2 | 7.262526 8.017757 1.80 0.073 .834391 63.21291 3 | 43.65627 46.62635 3.54 0.000 5.381893 354.1263 4 | 76.3655 81.33339 4.07 0.000 9.469377 615.8472 5 | 133.7632 143.9793 4.55 0.000 16.22277 1102.93 6 | 124.4262 139.5094 4.30 0.000 13.82058 1120.205 | alcohol | 2 | 4.213304 1.05191 5.76 0.000 2.582905 6.872854 3 | 7.222005 2.053957 6.95 0.000 4.135936 12.61077 4 | 36.7912 14.17012 9.36 0.000 17.29434 78.26794 | smoke | 2 | 1.592701 .3200884 2.32 0.021 1.074154 2.361577 3 | 5.159309 1.775207 4.77 0.000 2.628521 10.12679 ------------------------------------------------------------------------------ . lincom 2.alcohol + 2.smoke, or ( 1) [cancer]2.alcohol + [cancer]2.smoke = 0 ------------------------------------------------------------------------------ cancer | Odds Ratio Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- (1) | 6.710535 2.110332 6.05 0.000 3.623021 12.42921 ------------------------------------------------------------------------------ . lincom 3.alcohol + 2.smoke, or ( 1) [cancer]3.alcohol + [cancer]2.smoke = 0 ------------------------------------------------------------------------------ cancer | Odds Ratio Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- (1) | 11.5025 3.877642 7.25 0.000 5.940746 22.27118 ------------------------------------------------------------------------------ . lincom 4.alcohol + 2.smoke, or ( 1) [cancer]4.alcohol + [cancer]2.smoke = 0 ------------------------------------------------------------------------------ cancer | Odds Ratio Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- (1) | 58.59739 25.19571 9.47 0.000 25.22775 136.1062 ------------------------------------------------------------------------------ . lincom 2.alcohol + 3.smoke, or ( 1) [cancer]2.alcohol + [cancer]3.smoke = 0 ------------------------------------------------------------------------------ cancer | Odds Ratio Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- (1) | 21.73774 9.508647 7.04 0.000 9.223097 51.23324 ------------------------------------------------------------------------------ . lincom 3.alcohol + 3.smoke, or ( 1) [cancer]3.alcohol + [cancer]3.smoke = 0 ------------------------------------------------------------------------------ cancer | Odds Ratio Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- (1) | 37.26056 17.06687 7.90 0.000 15.18323 91.43967 ------------------------------------------------------------------------------ . lincom 4.alcohol + 3.smoke, or ( 1) [cancer]4.alcohol + [cancer]3.smoke = 0 ------------------------------------------------------------------------------ cancer | Odds Ratio Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- (1) | 189.8171 100.9789 9.86 0.000 66.91342 538.4652 ------------------------------------------------------------------------------ . * . * Regress cancer against age, alcohol and smoke. . * Include alcohol-smoke interaction terms. . * . logistic cancer i.age alcohol##smoke [freq=patients] Logistic regression Number of obs = 975 LR chi2(16) = 290.90 Prob > chi2 = 0.0000 Log likelihood = -349.29335 Pseudo R2 = 0.2940 ------------------------------------------------------------------------------ cancer | Odds Ratio Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | 2 | 6.697614 7.41052 1.72 0.086 .7657997 58.57673 3 | 40.1626 42.67457 3.48 0.001 5.004744 322.3011 4 | 69.55115 73.73699 4.00 0.000 8.707117 555.5642 5 | 123.0645 131.6754 4.50 0.000 15.11374 1002.06 6 | 118.8368 133.2538 4.26 0.000 13.19724 1070.086 | alcohol | 2 | 7.554406 3.043769 5.02 0.000 3.429574 16.64028 3 | 12.71358 5.825002 5.55 0.000 5.179306 31.20788 4 | 65.07188 39.54145 6.87 0.000 19.7767 214.108 | smoke | 2 | 3.800862 1.703912 2.98 0.003 1.578671 9.151084 3 | 8.651205 5.569301 3.35 0.001 2.449667 30.55247 | alcohol#| smoke | 2 2 | .3251915 .1746668 -2.09 0.036 .1134859 .9318294 2 3 | .5033299 .4154539 -0.83 0.406 .0998302 2.53772 3 2 | .3341452 .2008274 -1.82 0.068 .1028839 1.085233 3 3 | .657279 .6598915 -0.42 0.676 .0918681 4.702563 4 2 | .3731549 .301804 -1.22 0.223 .076462 1.821095 4 3 | .3489097 .4210291 -0.87 0.383 .032777 3.714132 ------------------------------------------------------------------------------ . lincom 2.alcohol + 2.smoke + 2.alcohol#2.smoke, or ( 1) [cancer]2.alcohol + [cancer]2.smoke + [cancer]2.alcohol#2.smoke = 0 ------------------------------------------------------------------------------ cancer | Odds Ratio Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- (1) | 9.337306 3.826163 5.45 0.000 4.182379 20.84586 ------------------------------------------------------------------------------ . lincom 2.alcohol + 3.smoke + 2.alcohol#3.smoke, or ( 1) [cancer]2.alcohol + [cancer]3.smoke + [cancer]2.alcohol#3.smoke = 0 ------------------------------------------------------------------------------ cancer | Odds Ratio Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- (1) | 32.89498 19.73771 5.82 0.000 10.14823 106.6275 ------------------------------------------------------------------------------ . lincom 3.alcohol + 2.smoke + 3.alcohol#2.smoke, or ( 1) [cancer]3.alcohol + [cancer]2.smoke + [cancer]3.alcohol#2.smoke = 0 ------------------------------------------------------------------------------ cancer | Odds Ratio Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- (1) | 16.14675 7.152596 6.28 0.000 6.776801 38.47207 ------------------------------------------------------------------------------ . lincom 3.alcohol + 3.smoke + 3.alcohol#3.smoke, or ( 1) [cancer]3.alcohol + [cancer]3.smoke + [cancer]3.alcohol#3.smoke = 0 ------------------------------------------------------------------------------ cancer | Odds Ratio Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- (1) | 72.29267 57.80908 5.35 0.000 15.08093 346.5456 ------------------------------------------------------------------------------ . lincom 4.alcohol + 2.smoke + 4.alcohol#2.smoke, or ( 1) [cancer]4.alcohol + [cancer]2.smoke + [cancer]4.alcohol#2.smoke = 0 ------------------------------------------------------------------------------ cancer | Odds Ratio Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- (1) | 92.29212 53.97512 7.74 0.000 29.33305 290.3836 ------------------------------------------------------------------------------ . lincom 4.alcohol + 3.smoke + 4.alcohol#3.smoke, or ( 1) [cancer]4.alcohol + [cancer]3.smoke + [cancer]4.alcohol#3.smoke = 0 ------------------------------------------------------------------------------ cancer | Odds Ratio Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- (1) | 196.4188 189.1697 5.48 0.000 29.74377 1297.09 ------------------------------------------------------------------------------ . * . * Calculate delta deviance . * . display 2*( 351.96823 -349.29335 ) 5.34976 . display chi2tail(6, 5.34976) .49979789 . more . * . * Perform Pearson chi-squared and Hosmer-Lemeshow tests of . * goodness of fit. . * . lfit Logistic model for cancer, goodness-of-fit test number of observations = 975 number of covariate patterns = 68 Pearson chi2(51) = 55.85 Prob > chi2 = 0.2977 . lfit, group(10) table Logistic model for cancer, goodness-of-fit test (Table collapsed on quantiles of estimated probabilities) +--------------------------------------------------------+ | Group | Prob | Obs_1 | Exp_1 | Obs_0 | Exp_0 | Total | |-------+--------+-------+-------+-------+-------+-------| | 1 | 0.0046 | 0 | 0.3 | 116 | 115.7 | 116 | | 2 | 0.0273 | 2 | 2.0 | 118 | 118.0 | 120 | | 3 | 0.0418 | 4 | 3.1 | 76 | 76.9 | 80 | | 4 | 0.0765 | 4 | 5.1 | 87 | 85.9 | 91 | | 5 | 0.1332 | 5 | 7.8 | 81 | 78.2 | 86 | |-------+--------+-------+-------+-------+-------+-------| | 6 | 0.2073 | 21 | 20.2 | 91 | 91.8 | 112 | | 7 | 0.2682 | 22 | 22.5 | 65 | 64.5 | 87 | | 8 | 0.3833 | 32 | 28.5 | 56 | 59.5 | 88 | | 9 | 0.5131 | 46 | 41.6 | 52 | 56.4 | 98 | | 10 | 0.9440 | 64 | 68.9 | 33 | 28.1 | 97 | +--------------------------------------------------------+ number of observations = 975 number of groups = 10 Hosmer-Lemeshow chi2(8) = 4.73 Prob > chi2 = 0.7862 . * . * Perform residual analysis . * . predict p, p . label variable p /// > "Estimate of {&pi} for the j{superscript:th} Covariate Pattern" . predict dx2, dx2 (57 missing values generated) . predict rstandard, rstandard (57 missing values generated) . generate dx2_pos = dx2 if rstandard >= 0 (137 missing values generated) . generate dx2_neg = dx2 if rstandard < 0 (112 missing values generated) . label variable dx2_pos "Positive residual" . label variable dx2_neg "Negative residual" . predict dbeta, dbeta (57 missing values generated) . scatter dx2_pos p [weight=dbeta] /// > , msymbol(Oh) mlwidth(medthick) mcolor(red) /// > || scatter dx2_neg p [weight=dbeta] /// > , msymbol(Oh) mlwidth(medthick) mcolor(blue) /// > ||, ylabel(0(1)8, angle(0)) /// > ymtick(0(.5)8) yline(3.84, lwidth(medthick)) /// > xlabel(0(.1)1) xmtick(0(.05)1) /// > ytitle("Squared Standardized Pearson Residual") /// > xscale(titlegap(2)) (analytic weights assumed) (analytic weights assumed) (analytic weights assumed) (analytic weights assumed) . more . save temporary, replace file temporary.dta saved . drop if patients == 0 (57 observations deleted) . generate ca_no = cancer*patients . collapse (sum) n = patients ca = ca_no, by(age alcohol smoke dbeta dx2 p) . * . * Identify covariate patterns associated with large squared residuals . * . list n ca age alcohol smoke dbeta dx2 p if dx2 > 3.84, nodisplay +--------------------------------------------------------------------+ | n ca age alcohol smoke dbeta dx2 p | |--------------------------------------------------------------------| 11. | 2 1 25-34 >= 120 10-29 1.335589 7.942436 .060482 | 17. | 37 4 35-44 40-79 10-29 1.890466 5.466789 .041798 | 22. | 3 2 35-44 >= 120 0-9 .9170172 3.89631 .2331274 | 25. | 28 0 45-54 0-39 10-29 1.56448 4.114906 .0962316 | 38. | 6 4 55-64 0-39 >= 30 4.159105 6.503717 .2956251 | |--------------------------------------------------------------------| 45. | 10 5 55-64 >= 120 0-9 6.159466 6.949368 .7594333 | +--------------------------------------------------------------------+ . * . * Rerun analysis without the covariate pattern A . * . use temporary, clear . drop if age == 4 & alcohol ==4 & smoke == 1 (2 observations deleted) . logistic cancer i.age i.alcohol##i.smoke [freq=patients] Logistic regression Number of obs = 965 LR chi2(16) = 293.36 Prob > chi2 = 0.0000 Log likelihood = -338.96967 Pseudo R2 = 0.3020 ------------------------------------------------------------------------------ cancer | Odds Ratio Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | 2 | 6.634059 7.385915 1.70 0.089 .7483572 58.80981 3 | 44.03354 47.14004 3.54 0.000 5.401705 358.9519 4 | 84.68781 90.60221 4.15 0.000 10.40336 689.3954 5 | 138.0188 148.859 4.57 0.000 16.66795 1142.863 6 | 130.5084 147.6556 4.31 0.000 14.21018 1198.609 | alcohol | 2 | 7.525681 3.032793 5.01 0.000 3.416001 16.57958 3 | 12.62548 5.79008 5.53 0.000 5.139068 31.01782 4 | 273.8578 248.0893 6.20 0.000 46.38922 1616.714 | smoke | 2 | 3.76567 1.688301 2.96 0.003 1.56392 9.067134 3 | 8.65512 5.583629 3.35 0.001 2.444231 30.64813 | alcohol#| smoke | 2 2 | .3281026 .1763786 -2.07 0.038 .1144005 .9410036 2 3 | .5171836 .4296498 -0.79 0.427 .1015103 2.634994 3 2 | .3367698 .2026913 -1.81 0.071 .1035193 1.095582 3 3 | .6681017 .6755026 -0.40 0.690 .0920899 4.847004 4 2 | .0925466 .0959831 -2.29 0.022 .0121214 .706593 4 3 | .0834134 .115373 -1.80 0.073 .005545 1.254794 ------------------------------------------------------------------------------ . lincom 2.alcohol + 2.smoke + 2.alcohol#2.smoke, or ( 1) [cancer]2.alcohol + [cancer]2.smoke + [cancer]2.alcohol#2.smoke = 0 ------------------------------------------------------------------------------ cancer | Odds Ratio Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- (1) | 9.298176 3.811849 5.44 0.000 4.163341 20.76603 ------------------------------------------------------------------------------ . lincom 2.alcohol + 3.smoke + 2.alcohol#3.smoke, or ( 1) [cancer]2.alcohol + [cancer]3.smoke + [cancer]2.alcohol#3.smoke = 0 ------------------------------------------------------------------------------ cancer | Odds Ratio Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- (1) | 33.6871 20.4014 5.81 0.000 10.2793 110.3986 ------------------------------------------------------------------------------ . lincom 3.alcohol + 2.smoke + 3.alcohol#2.smoke, or ( 1) [cancer]3.alcohol + [cancer]2.smoke + [cancer]3.alcohol#2.smoke = 0 ------------------------------------------------------------------------------ cancer | Odds Ratio Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- (1) | 16.01118 7.097925 6.26 0.000 6.715471 38.1742 ------------------------------------------------------------------------------ . lincom 3.alcohol + 3.smoke + 3.alcohol#3.smoke, or ( 1) [cancer]3.alcohol + [cancer]3.smoke + [cancer]3.alcohol#3.smoke = 0 ------------------------------------------------------------------------------ cancer | Odds Ratio Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- (1) | 73.00683 58.92617 5.32 0.000 15.00829 355.1368 ------------------------------------------------------------------------------ . lincom 4.alcohol + 2.smoke + 4.alcohol#2.smoke, or ( 1) [cancer]4.alcohol + [cancer]2.smoke + [cancer]4.alcohol#2.smoke = 0 ------------------------------------------------------------------------------ cancer | Odds Ratio Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- (1) | 95.43948 56.55251 7.69 0.000 29.87789 304.864 ------------------------------------------------------------------------------ . lincom 4.alcohol + 3.smoke + 4.alcohol#3.smoke, or ( 1) [cancer]4.alcohol + [cancer]3.smoke + [cancer]4.alcohol#3.smoke = 0 ------------------------------------------------------------------------------ cancer | Odds Ratio Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- (1) | 197.7124 192.6577 5.43 0.000 29.28155 1334.977 ------------------------------------------------------------------------------ . * . * Rerun analysis without the covariate pattern B . * . use temporary, clear . drop if age == 4 & alcohol ==1 & smoke == 3 (2 observations deleted) . logistic cancer i.age i.alcohol##i.smoke [freq=patients] Logistic regression Number of obs = 969 LR chi2(16) = 291.50 Prob > chi2 = 0.0000 Log likelihood = -342.17265 Pseudo R2 = 0.2987 ------------------------------------------------------------------------------ cancer | Odds Ratio Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- age | 2 | 6.757334 7.494504 1.72 0.085 .7686255 59.40678 3 | 40.05664 42.66669 3.46 0.001 4.966032 323.1019 4 | 64.05842 68.0934 3.91 0.000 7.975507 514.5104 5 | 122.9679 131.9052 4.49 0.000 15.02189 1006.604 6 | 132.9431 149.7842 4.34 0.000 14.60947 1209.754 | alcohol | 2 | 7.695185 3.109017 5.05 0.000 3.485907 16.98722 3 | 13.04068 5.99202 5.59 0.000 5.298881 32.09343 4 | 66.83578 40.63583 6.91 0.000 20.29937 220.0572 | smoke | 2 | 3.864114 1.735158 3.01 0.003 1.602592 9.317019 3 | 1.875407 2.10721 0.56 0.576 .2073404 16.96317 | alcohol#| smoke | 2 2 | .3203897 .172348 -2.12 0.034 .1116323 .9195333 2 3 | 2.32032 2.87258 0.68 0.497 .2049991 26.26297 3 2 | .329099 .1979799 -1.85 0.065 .1012184 1.070025 3 3 | 3.035175 4.134585 0.82 0.415 .2102119 43.8238 4 2 | .3639918 .2937924 -1.25 0.211 .074826 1.770641 4 3 | 1.616647 2.451736 0.32 0.751 .0827409 31.58713 ------------------------------------------------------------------------------ . lincom 2.alcohol + 2.smoke + 2.alcohol#2.smoke, or ( 1) [cancer]2.alcohol + [cancer]2.smoke + [cancer]2.alcohol#2.smoke = 0 ------------------------------------------------------------------------------ cancer | Odds Ratio Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- (1) | 9.526812 3.914528 5.49 0.000 4.257869 21.31586 ------------------------------------------------------------------------------ . lincom 2.alcohol + 3.smoke + 2.alcohol#3.smoke, or ( 1) [cancer]2.alcohol + [cancer]3.smoke + [cancer]2.alcohol#3.smoke = 0 ------------------------------------------------------------------------------ cancer | Odds Ratio Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- (1) | 33.48594 20.08868 5.85 0.000 10.33272 108.5201 ------------------------------------------------------------------------------ . lincom 3.alcohol + 2.smoke + 3.alcohol#2.smoke, or ( 1) [cancer]3.alcohol + [cancer]2.smoke + [cancer]3.alcohol#2.smoke = 0 ------------------------------------------------------------------------------ cancer | Odds Ratio Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- (1) | 16.58352 7.369458 6.32 0.000 6.940902 39.62209 ------------------------------------------------------------------------------ . lincom 3.alcohol + 3.smoke + 3.alcohol#3.smoke, or ( 1) [cancer]3.alcohol + [cancer]3.smoke + [cancer]3.alcohol#3.smoke = 0 ------------------------------------------------------------------------------ cancer | Odds Ratio Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- (1) | 74.22997 59.24198 5.40 0.000 15.53268 354.7417 ------------------------------------------------------------------------------ . lincom 4.alcohol + 2.smoke + 4.alcohol#2.smoke, or ( 1) [cancer]4.alcohol + [cancer]2.smoke + [cancer]4.alcohol#2.smoke = 0 ------------------------------------------------------------------------------ cancer | Odds Ratio Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- (1) | 94.0049 54.92418 7.78 0.000 29.91021 295.4483 ------------------------------------------------------------------------------ . lincom 4.alcohol + 3.smoke + 4.alcohol#3.smoke, or ( 1) [cancer]4.alcohol + [cancer]3.smoke + [cancer]4.alcohol#3.smoke = 0 ------------------------------------------------------------------------------ cancer | Odds Ratio Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- (1) | 202.6374 194.6198 5.53 0.000 30.84587 1331.197 ------------------------------------------------------------------------------ . log close name: log: C:\MyDocs\MPH\LectureNotes\ClassDoLogData\logistic regression\5.20.Esophag > ealCa.ClassVersion.log log type: text closed on: 15 Jan 2010, 17:02:13 ---------------------------------------------------------------------------------------