The SAS System 1 15:13 Tuesday, April 25, 2006 The GENMOD Procedure Model Information Data Set WORK.FRAMING Distribution Binomial Link Function Logit Dependent Variable chdny Number of Observations Read 1406 Number of Observations Used 1363 Number of Events 268 Number of Trials 1363 Missing Values 43 Class Level Information Class Levels Values ageny 4 0 1 2 3 Response Profile Ordered Total Value chdny Frequency 1 1 268 2 0 1095 PROC GENMOD is modeling the probability that chdny='1'. Parameter Information Parameter Effect ageny Prm1 Intercept Prm2 ageny 0 Prm3 ageny 1 Prm4 ageny 2 Prm5 ageny 3 Criteria For Assessing Goodness Of Fit Criterion DF Value Value/DF Deviance 1359 1328.6504 0.9777 Scaled Deviance 1359 1328.6504 0.9777 Pearson Chi-Square 1359 1363.0000 1.0029 Scaled Pearson X2 1359 1363.0000 1.0029 Log Likelihood -664.3252 Algorithm converged. The SAS System 2 15:13 Tuesday, April 25, 2006 The GENMOD Procedure Analysis Of Parameter Estimates Standard Wald 95% Chi- Parameter DF Estimate Error Confidence Limits Square Intercept 1 -0.9378 0.1230 -1.1788 -0.6968 58.15 ageny 0 1 -0.8605 0.1949 -1.2424 -0.4785 19.50 ageny 1 1 -0.6484 0.1867 -1.0144 -0.2824 12.06 ageny 2 1 -0.4407 0.1862 -0.8057 -0.0756 5.60 ageny 3 0 0.0000 0.0000 0.0000 0.0000 . Scale 0 1.0000 0.0000 1.0000 1.0000 Analysis Of Parameter Estimates Parameter Pr > ChiSq Intercept <.0001 ageny 0 <.0001 ageny 1 0.0005 ageny 2 0.0180 ageny 3 . Scale NOTE: The scale parameter was held fixed. LR Statistics For Type 3 Analysis Chi- Source DF Square Pr > ChiSq ageny 3 22.60 <.0001 Contrast Estimate Results Standard Label Estimate Error Alpha Confidence Limits alder 1 vs. 0 0.2121 0.2064 0.05 -0.1925 0.6166 Exp(alder 1 vs. 0) 1.2362 0.2552 0.05 0.8249 1.8526 alder 2 vs. 0 0.4198 0.2060 0.05 0.0162 0.8235 Exp(alder 2 vs. 0) 1.5217 0.3134 0.05 1.0163 2.2784 alder 3 vs. 0 0.8605 0.1949 0.05 0.4785 1.2424 Exp(alder 3 vs. 0) 2.3643 0.4608 0.05 1.6137 3.4641 Contrast Estimate Results Chi- Label Square Pr > ChiSq alder 1 vs. 0 1.06 0.3042 Exp(alder 1 vs. 0) alder 2 vs. 0 4.16 0.0415 Exp(alder 2 vs. 0) alder 3 vs. 0 19.50 <.0001 Exp(alder 3 vs. 0) The SAS System 3 15:13 Tuesday, April 25, 2006 The GENMOD Procedure Model Information Data Set WORK.FRAMING Distribution Binomial Link Function Logit Dependent Variable chdny Number of Observations Read 1406 Number of Observations Used 1363 Number of Events 268 Number of Trials 1363 Missing Values 43 Response Profile Ordered Total Value chdny Frequency 1 1 268 2 0 1095 PROC GENMOD is modeling the probability that chdny='1'. Parameter Information Parameter Effect Prm1 Intercept Prm2 ageny Criteria For Assessing Goodness Of Fit Criterion DF Value Value/DF Deviance 1361 1329.5080 0.9769 Scaled Deviance 1361 1329.5080 0.9769 Pearson Chi-Square 1361 1364.9128 1.0029 Scaled Pearson X2 1361 1364.9128 1.0029 Log Likelihood -664.7540 Algorithm converged. Analysis Of Parameter Estimates Standard Wald 95% Confidence Chi- Parameter DF Estimate Error Limits Square Intercept 1 -1.8532 0.1240 -2.0962 -1.6101 223.33 ageny 1 0.2860 0.0620 0.1645 0.4075 21.29 Scale 0 1.0000 0.0000 1.0000 1.0000 The SAS System 4 15:13 Tuesday, April 25, 2006 The GENMOD Procedure Analysis Of Parameter Estimates Parameter Pr > ChiSq Intercept <.0001 ageny <.0001 Scale NOTE: The scale parameter was held fixed. LR Statistics For Type 3 Analysis Chi- Source DF Square Pr > ChiSq ageny 1 21.74 <.0001 Contrast Estimate Results Standard Label Estimate Error Alpha Confidence Limits age odds ratio 0.2860 0.0620 0.05 0.1645 0.4075 Exp(age odds ratio) 1.3311 0.0825 0.05 1.1788 1.5031 Contrast Estimate Results Chi- Label Square Pr > ChiSq age odds ratio 21.29 <.0001 Exp(age odds ratio) The SAS System 5 15:13 Tuesday, April 25, 2006 The GENMOD Procedure Model Information Data Set WORK.FRAMING Distribution Binomial Link Function Logit Dependent Variable chdny Number of Observations Read 1406 Number of Observations Used 1363 Number of Events 268 Number of Trials 1363 Missing Values 43 Response Profile Ordered Total Value chdny Frequency 1 1 268 2 0 1095 PROC GENMOD is modeling the probability that chdny='1'. Parameter Information Parameter Effect Prm1 Intercept Prm2 age Criteria For Assessing Goodness Of Fit Criterion DF Value Value/DF Deviance 1361 1330.1647 0.9773 Scaled Deviance 1361 1330.1647 0.9773 Pearson Chi-Square 1361 1363.1952 1.0016 Scaled Pearson X2 1361 1363.1952 1.0016 Log Likelihood -665.0824 Algorithm converged. Analysis Of Parameter Estimates Standard Wald 95% Confidence Chi- Parameter DF Estimate Error Limits Square Intercept 1 -4.8843 0.7737 -6.4008 -3.3678 39.85 age 1 0.0658 0.0145 0.0375 0.0942 20.70 Scale 0 1.0000 0.0000 1.0000 1.0000 The SAS System 6 15:13 Tuesday, April 25, 2006 The GENMOD Procedure Analysis Of Parameter Estimates Parameter Pr > ChiSq Intercept <.0001 age <.0001 Scale NOTE: The scale parameter was held fixed. LR Statistics For Type 3 Analysis Chi- Source DF Square Pr > ChiSq age 1 21.08 <.0001 Contrast Estimate Results Standard Label Estimate Error Alpha age odds ratio pr år. 0.0658 0.0145 0.05 Exp(age odds ratio pr år.) 1.0680 0.0154 0.05 Contrast Estimate Results Chi- Label Confidence Limits Square Pr > ChiSq age odds ratio pr år. 0.0375 0.0942 20.70 <.0001 Exp(age odds ratio pr år.) 1.0382 1.0987 The SAS System 7 15:13 Tuesday, April 25, 2006 The GENMOD Procedure Model Information Data Set WORK.FRAMING Distribution Binomial Link Function Logit Dependent Variable chdny Number of Observations Read 1406 Number of Observations Used 1363 Number of Events 268 Number of Trials 1363 Missing Values 43 Response Profile Ordered Total Value chdny Frequency 1 1 268 2 0 1095 PROC GENMOD is modeling the probability that chdny='1'. Criteria For Assessing Goodness Of Fit Criterion DF Value Value/DF Deviance 1360 1330.1641 0.9781 Scaled Deviance 1360 1330.1641 0.9781 Pearson Chi-Square 1360 1363.1248 1.0023 Scaled Pearson X2 1360 1363.1248 1.0023 Log Likelihood -665.0821 Algorithm converged. Analysis Of Parameter Estimates Standard Wald 95% Confidence Chi- Parameter DF Estimate Error Limits Square Intercept 1 -4.6723 9.0295 -22.3699 13.0252 0.27 age 1 0.0577 0.3424 -0.6134 0.7289 0.03 agesq 1 0.0001 0.0032 -0.0062 0.0064 0.00 Scale 0 1.0000 0.0000 1.0000 1.0000 Analysis Of Parameter Estimates Parameter Pr > ChiSq Intercept 0.6048 age 0.8661 agesq 0.9812 Scale The SAS System 8 15:13 Tuesday, April 25, 2006 The GENMOD Procedure NOTE: The scale parameter was held fixed. LR Statistics For Type 3 Analysis Chi- Source DF Square Pr > ChiSq age 1 0.03 0.8660 agesq 1 0.00 0.9812 The SAS System 9 15:13 Tuesday, April 25, 2006 The GENMOD Procedure Model Information Data Set WORK.FRAMING Distribution Binomial Link Function Logit Dependent Variable chdny Number of Observations Read 1406 Number of Observations Used 1363 Number of Events 268 Number of Trials 1363 Missing Values 43 Class Level Information Class Levels Values ageny 4 0 1 2 3 sex 2 1 2 Response Profile Ordered Total Value chdny Frequency 1 1 268 2 0 1095 PROC GENMOD is modeling the probability that chdny='1'. Criteria For Assessing Goodness Of Fit Criterion DF Value Value/DF Deviance 1355 1296.9653 0.9572 Scaled Deviance 1355 1296.9653 0.9572 Pearson Chi-Square 1355 1363.0000 1.0059 Scaled Pearson X2 1355 1363.0000 1.0059 Log Likelihood -648.4826 Algorithm converged. Analysis Of Parameter Estimates Standard Wald 95% Chi- Parameter DF Estimate Error Confidence Limits Square Intercept 1 -1.1314 0.1818 -1.4878 -0.7750 38.71 ageny 0 1 -1.5017 0.3498 -2.1874 -0.8160 18.43 ageny 1 1 -0.7867 0.2778 -1.3311 -0.2422 8.02 ageny 2 1 -0.6077 0.2798 -1.1561 -0.0593 4.72 ageny 3 0 0.0000 0.0000 0.0000 0.0000 . sex 1 1 0.3731 0.2476 -0.1122 0.8584 2.27 sex 2 0 0.0000 0.0000 0.0000 0.0000 . The SAS System 10 15:13 Tuesday, April 25, 2006 The GENMOD Procedure Analysis Of Parameter Estimates Standard Wald 95% Chi- Parameter DF Estimate Error Confidence Limits Square ageny*sex 0 1 1 0.9748 0.4282 0.1355 1.8140 5.18 ageny*sex 0 2 0 0.0000 0.0000 0.0000 0.0000 . ageny*sex 1 1 1 0.3045 0.3772 -0.4347 1.0437 0.65 ageny*sex 1 2 0 0.0000 0.0000 0.0000 0.0000 . ageny*sex 2 1 1 0.3401 0.3772 -0.3991 1.0794 0.81 ageny*sex 2 2 0 0.0000 0.0000 0.0000 0.0000 . ageny*sex 3 1 0 0.0000 0.0000 0.0000 0.0000 . ageny*sex 3 2 0 0.0000 0.0000 0.0000 0.0000 . Scale 0 1.0000 0.0000 1.0000 1.0000 Analysis Of Parameter Estimates Parameter Pr > ChiSq Intercept <.0001 ageny 0 <.0001 ageny 1 0.0046 ageny 2 0.0299 ageny 3 . sex 1 0.1318 sex 2 . ageny*sex 0 1 0.0228 ageny*sex 0 2 . ageny*sex 1 1 0.4195 ageny*sex 1 2 . ageny*sex 2 1 0.3672 ageny*sex 2 2 . ageny*sex 3 1 . ageny*sex 3 2 . Scale NOTE: The scale parameter was held fixed. LR Statistics For Type 3 Analysis Chi- Source DF Square Pr > ChiSq ageny 3 26.32 <.0001 sex 1 29.49 <.0001 ageny*sex 3 5.46 0.1410 The SAS System 11 15:13 Tuesday, April 25, 2006 The GENMOD Procedure Model Information Data Set WORK.FRAMING Distribution Binomial Link Function Logit Dependent Variable chdny Number of Observations Read 1406 Number of Observations Used 1363 Number of Events 268 Number of Trials 1363 Missing Values 43 Class Level Information Class Levels Values sex 2 1 2 Response Profile Ordered Total Value chdny Frequency 1 1 268 2 0 1095 PROC GENMOD is modeling the probability that chdny='1'. Criteria For Assessing Goodness Of Fit Criterion DF Value Value/DF Deviance 1359 1298.3672 0.9554 Scaled Deviance 1359 1298.3672 0.9554 Pearson Chi-Square 1359 1362.0804 1.0023 Scaled Pearson X2 1359 1362.0804 1.0023 Log Likelihood -649.1836 Algorithm converged. Analysis Of Parameter Estimates Standard Wald 95% Chi- Parameter DF Estimate Error Confidence Limits Square Intercept 1 -2.5278 0.2150 -2.9492 -2.1065 138.25 ageny 1 0.4564 0.1018 0.2569 0.6560 20.09 sex 1 1 1.1822 0.2645 0.6638 1.7007 19.97 sex 2 0 0.0000 0.0000 0.0000 0.0000 . ageny*sex 1 1 -0.2750 0.1291 -0.5281 -0.0219 4.53 ageny*sex 2 0 0.0000 0.0000 0.0000 0.0000 . Scale 0 1.0000 0.0000 1.0000 1.0000 The SAS System 12 15:13 Tuesday, April 25, 2006 The GENMOD Procedure Analysis Of Parameter Estimates Parameter Pr > ChiSq Intercept <.0001 ageny <.0001 sex 1 <.0001 sex 2 . ageny*sex 1 0.0332 ageny*sex 2 . Scale NOTE: The scale parameter was held fixed. LR Statistics For Type 3 Analysis Chi- Source DF Square Pr > ChiSq ageny 1 25.24 <.0001 sex 1 21.34 <.0001 ageny*sex 1 4.59 0.0321 The SAS System 13 15:13 Tuesday, April 25, 2006 The GENMOD Procedure Model Information Data Set WORK.FRAMING Distribution Binomial Link Function Logit Dependent Variable chdny Number of Observations Read 1406 Number of Observations Used 1363 Number of Events 268 Number of Trials 1363 Missing Values 43 Class Level Information Class Levels Values sex 2 1 2 Response Profile Ordered Total Value chdny Frequency 1 1 268 2 0 1095 PROC GENMOD is modeling the probability that chdny='1'. Criteria For Assessing Goodness Of Fit Criterion DF Value Value/DF Deviance 1359 1300.3638 0.9569 Scaled Deviance 1359 1300.3638 0.9569 Pearson Chi-Square 1359 1358.4599 0.9996 Scaled Pearson X2 1359 1358.4599 0.9996 Log Likelihood -650.1819 Algorithm converged. Analysis Of Parameter Estimates Standard Wald 95% Chi- Parameter DF Estimate Error Confidence Limits Square Intercept 1 -6.9975 1.2546 -9.4564 -4.5386 31.11 age 1 0.0982 0.0232 0.0527 0.1437 17.93 sex 1 1 3.5446 1.6044 0.4000 6.6892 4.88 sex 2 0 0.0000 0.0000 0.0000 0.0000 . age*sex 1 1 -0.0530 0.0299 -0.1115 0.0056 3.14 age*sex 2 0 0.0000 0.0000 0.0000 0.0000 . Scale 0 1.0000 0.0000 1.0000 1.0000 The SAS System 14 15:13 Tuesday, April 25, 2006 The GENMOD Procedure Analysis Of Parameter Estimates Parameter Pr > ChiSq Intercept <.0001 age <.0001 sex 1 0.0272 sex 2 . age*sex 1 0.0762 age*sex 2 . Scale NOTE: The scale parameter was held fixed. LR Statistics For Type 3 Analysis Chi- Source DF Square Pr > ChiSq age 1 23.67 <.0001 sex 1 4.95 0.0261 age*sex 1 3.17 0.0751 The SAS System 15 15:13 Tuesday, April 25, 2006 The GENMOD Procedure Model Information Data Set WORK.FRAMING Distribution Binomial Link Function Logit Dependent Variable chdny Number of Observations Read 1406 Number of Observations Used 1363 Number of Events 268 Number of Trials 1363 Missing Values 43 Class Level Information Class Levels Values sex 2 1 2 ageny 4 0 1 2 3 Response Profile Ordered Total Value chdny Frequency 1 1 268 2 0 1095 PROC GENMOD is modeling the probability that chdny='1'. Parameter Information Parameter Effect sex ageny Prm1 Intercept Prm2 sex 1 Prm3 sex 2 Prm4 sex*ageny 1 0 Prm5 sex*ageny 1 1 Prm6 sex*ageny 1 2 Prm7 sex*ageny 1 3 Prm8 sex*ageny 2 0 Prm9 sex*ageny 2 1 Prm10 sex*ageny 2 2 Prm11 sex*ageny 2 3 Criteria For Assessing Goodness Of Fit Criterion DF Value Value/DF Deviance 1355 1296.9653 0.9572 Scaled Deviance 1355 1296.9653 0.9572 Pearson Chi-Square 1355 1363.0000 1.0059 Scaled Pearson X2 1355 1363.0000 1.0059 Log Likelihood -648.4826 The SAS System 16 15:13 Tuesday, April 25, 2006 The GENMOD Procedure Algorithm converged. Analysis Of Parameter Estimates Standard Wald 95% Chi- Parameter DF Estimate Error Confidence Limits Square Intercept 1 -1.1314 0.1818 -1.4878 -0.7750 38.71 sex 1 1 0.3731 0.2476 -0.1122 0.8584 2.27 sex 2 0 0.0000 0.0000 0.0000 0.0000 . sex*ageny 1 0 1 -0.5269 0.2469 -1.0109 -0.0429 4.55 sex*ageny 1 1 1 -0.4822 0.2551 -0.9821 0.0178 3.57 sex*ageny 1 2 1 -0.2676 0.2530 -0.7634 0.2282 1.12 sex*ageny 1 3 0 0.0000 0.0000 0.0000 0.0000 . sex*ageny 2 0 1 -1.5017 0.3498 -2.1874 -0.8160 18.43 sex*ageny 2 1 1 -0.7867 0.2778 -1.3311 -0.2422 8.02 sex*ageny 2 2 1 -0.6077 0.2798 -1.1561 -0.0593 4.72 sex*ageny 2 3 0 0.0000 0.0000 0.0000 0.0000 . Scale 0 1.0000 0.0000 1.0000 1.0000 Analysis Of Parameter Estimates Parameter Pr > ChiSq Intercept <.0001 sex 1 0.1318 sex 2 . sex*ageny 1 0 0.0329 sex*ageny 1 1 0.0587 sex*ageny 1 2 0.2902 sex*ageny 1 3 . sex*ageny 2 0 <.0001 sex*ageny 2 1 0.0046 sex*ageny 2 2 0.0299 sex*ageny 2 3 . Scale NOTE: The scale parameter was held fixed. LR Statistics For Type 3 Analysis Chi- Source DF Square Pr > ChiSq sex 1 29.49 <.0001 sex*ageny 6 27.90 <.0001 Contrast Estimate Results Standard Label Estimate Error Alpha Confidence Limits alder 1 vs. 0: M 0.0448 0.2638 0.05 -0.4722 0.5617 Exp(alder 1 vs. 0: M) 1.0458 0.2758 0.05 0.6236 1.7537 alder 2 vs. 0: M 0.2593 0.2617 0.05 -0.2536 0.7723 Exp(alder 2 vs. 0: M) 1.2961 0.3392 0.05 0.7760 2.1646 The SAS System 17 15:13 Tuesday, April 25, 2006 The GENMOD Procedure Contrast Estimate Results Standard Label Estimate Error Alpha Confidence Limits alder 3 vs. 0: M 0.5269 0.2469 0.05 0.0429 1.0109 Exp(alder 3 vs. 0: M) 1.6937 0.4182 0.05 1.0439 2.7480 alder 1 vs. 0: K 0.7150 0.3653 0.05 -0.0009 1.4310 Exp(alder 1 vs. 0: K) 2.0443 0.7467 0.05 0.9991 4.1828 alder 2 vs. 0: K 0.8940 0.3668 0.05 0.1751 1.6129 Exp(alder 2 vs. 0: K) 2.4448 0.8968 0.05 1.1913 5.0172 alder 3 vs. 0: K 1.5017 0.3498 0.05 0.8160 2.1874 Exp(alder 3 vs. 0: K) 4.4892 1.5705 0.05 2.2615 8.9116 Contrast Estimate Results Chi- Label Square Pr > ChiSq alder 1 vs. 0: M 0.03 0.8653 Exp(alder 1 vs. 0: M) alder 2 vs. 0: M 0.98 0.3217 Exp(alder 2 vs. 0: M) alder 3 vs. 0: M 4.55 0.0329 Exp(alder 3 vs. 0: M) alder 1 vs. 0: K 3.83 0.0503 Exp(alder 1 vs. 0: K) alder 2 vs. 0: K 5.94 0.0148 Exp(alder 2 vs. 0: K) alder 3 vs. 0: K 18.43 <.0001 Exp(alder 3 vs. 0: K) The SAS System 18 15:13 Tuesday, April 25, 2006 The GENMOD Procedure Model Information Data Set WORK.FRAMING Distribution Binomial Link Function Logit Dependent Variable chdny Number of Observations Read 1406 Number of Observations Used 1363 Number of Events 268 Number of Trials 1363 Missing Values 43 Class Level Information Class Levels Values sex 2 1 2 Response Profile Ordered Total Value chdny Frequency 1 1 268 2 0 1095 PROC GENMOD is modeling the probability that chdny='1'. Parameter Information Parameter Effect sex Prm1 Intercept Prm2 sex 1 Prm3 sex 2 Prm4 ageny*sex 1 Prm5 ageny*sex 2 Criteria For Assessing Goodness Of Fit Criterion DF Value Value/DF Deviance 1359 1298.3672 0.9554 Scaled Deviance 1359 1298.3672 0.9554 Pearson Chi-Square 1359 1362.0804 1.0023 Scaled Pearson X2 1359 1362.0804 1.0023 Log Likelihood -649.1836 Algorithm converged. The SAS System 19 15:13 Tuesday, April 25, 2006 The GENMOD Procedure Analysis Of Parameter Estimates Standard Wald 95% Chi- Parameter DF Estimate Error Confidence Limits Square Intercept 1 -2.5278 0.2150 -2.9492 -2.1065 138.25 sex 1 1 1.1822 0.2645 0.6638 1.7007 19.97 sex 2 0 0.0000 0.0000 0.0000 0.0000 . ageny*sex 1 1 0.1814 0.0794 0.0257 0.3371 5.21 ageny*sex 2 1 0.4564 0.1018 0.2569 0.6560 20.09 Scale 0 1.0000 0.0000 1.0000 1.0000 Analysis Of Parameter Estimates Parameter Pr > ChiSq Intercept <.0001 sex 1 <.0001 sex 2 . ageny*sex 1 0.0224 ageny*sex 2 <.0001 Scale NOTE: The scale parameter was held fixed. LR Statistics For Type 3 Analysis Chi- Source DF Square Pr > ChiSq sex 1 21.34 <.0001 ageny*sex 2 26.50 <.0001 Contrast Estimate Results Standard Label Estimate Error Alpha alder, OR pr. gruppe: M 0.1814 0.0794 0.05 Exp(alder, OR pr. gruppe: M) 1.1989 0.0952 0.05 alder, OR pr. gruppe: K 0.4564 0.1018 0.05 Exp(alder, OR pr. gruppe: K) 1.5784 0.1607 0.05 Contrast Estimate Results Chi- Label Confidence Limits Square Pr > ChiSq alder, OR pr. gruppe: M 0.0257 0.3371 5.21 0.0224 Exp(alder, OR pr. gruppe: M) 1.0260 1.4009 alder, OR pr. gruppe: K 0.2569 0.6560 20.09 <.0001 Exp(alder, OR pr. gruppe: K) 1.2929 1.9270