Method = 1 (Strong Hierarchy) was chosen. The program 1. Standardizes all predictors to have mean 0 and variance 1 and renames them as x1-xp (see table below), numbered as they occur in the data set. 2. Fits main effects, interactions, and squared terms according to a modified forward selection procedure that on average has False Selection Rate (FSR) = .05. Developed by Hugh Crews, August 2008. Macro call parameters: Dataset = pbc Model = drug|age|sex|ascites|hepato|spiders|edema|bili|chol|albumin|copper|alk_phos|sgot|trig|platel et|protime|stage @q Y = futime Censor = status Censorvalue = 0 Gamma = .05 Method = 1 Terms = 20 Include = 0 Cbound = none The number of effects forced into the model is 0. Note: The terms=k option was used. Suboptimal results may occur if k is so small that gammahat never reaches its maximum. Variable names Variable Original Obs name name 1 censor status 2 x1 drug 3 x2 age 4 x3 sex 5 x4 ascites 6 x5 hepato 7 x6 spiders 8 x7 edema 9 x8 bili 10 x9 chol 11 x10 albumin 12 x11 copper 13 x12 alk_phos 14 x13 sgot 15 x14 trig 16 x15 platelet 17 x16 protime 18 x17 stage 308 y futime Forward Sequence Selection Effect p-to- monotonized Obs Step 1+S Entered enter p-to-enter 1 0 1 Intercept <.0001 0.000000 2 1 2 x8 <.0001 0.000000 3 2 3 x4 <.0001 0.000000 4 3 4 x17 <.0001 0.000009 5 4 5 x11 0.0001 0.000131 6 5 6 x4_x11 0.0005 0.000490 7 6 7 x2 0.0013 0.001268 8 7 8 x7 0.0007 0.001268 9 8 9 x13 0.0019 0.001907 10 9 10 x4_x7 0.0031 0.003095 11 10 11 x10 0.0220 0.021989 12 11 12 x16 0.0097 0.021989 13 12 13 x4_x10 0.0579 0.057931 14 13 14 x2_x7 0.0291 0.057931 15 14 15 x8_x8 0.0485 0.057931 16 15 16 x10_x16 0.0836 0.083569 17 16 17 x7_x16 0.0290 0.083569 18 17 18 x6 0.0578 0.083569 19 18 19 x6_x16 0.0597 0.083569 20 19 20 x6_x8 0.0244 0.083569 21 20 21 x6_x17 0.0195 0.083569 Sequence of Possible Models Obs alpha gammahat 1+S 1 0.000000 0.00000 1 2 0.000000 0.00000 2 3 0.000000 0.00000 3 4 0.000009 0.00004 4 5 0.000131 0.00047 5 6 0.000490 0.00172 6 7 0.001268 0.00380 8 8 0.001907 0.00614 9 9 0.003095 0.01083 10 10 0.021989 0.07513 12 11 0.057931 0.18152 15 12 0.083569 0.19897 21 Fast FSR estimates alpha Obs estimate 1+S 1 0.011905 10 The PHREG Procedure Model Information Data Set WORK.PBC_FFSR Dependent Variable y futime Censoring Variable censor status Censoring Value(s) 0 Ties Handling BRESLOW Number of Observations Read 276 Number of Observations Used 276 Summary of the Number of Event and Censored Values Percent Total Event Censored Censored 276 111 165 59.78 Convergence Status Convergence criterion (GCONV=1E-8) satisfied. Model Fit Statistics Without With Criterion Covariates Covariates -2 LOG L 1100.404 918.903 AIC 1100.404 936.903 SBC 1100.404 961.289 Testing Global Null Hypothesis: BETA=0 Test Chi-Square DF Pr > ChiSq Likelihood Ratio 181.5007 9 <.0001 Score 341.5636 9 <.0001 Wald 171.3039 9 <.0001 Analysis of Maximum Likelihood Estimates Parameter Standard Hazard Variable Variable DF Estimate Error Chi-Square Pr > ChiSq Ratio Label x8 1 0.46053 0.08697 28.0424 <.0001 1.585 bili x4 1 0.07474 0.14646 0.2604 0.6098 1.078 ascites x17 1 0.45137 0.13059 11.9472 0.0005 1.570 stage x11 1 0.44617 0.08965 24.7695 <.0001 1.562 copper x4_x11 1 -0.20290 0.05275 14.7931 0.0001 0.816 x2 1 0.46378 0.10921 18.0343 <.0001 1.590 age x7 1 0.16865 0.11309 2.2241 0.1359 1.184 edema x13 1 0.30094 0.09699 9.6273 0.0019 1.351 sgot x4_x7 1 0.16729 0.05891 8.0650 0.0045 1.182