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) = 0.05. Developed by Hugh Crews, August 2008. Macro call parameters: Dataset = lucency Model = blade_size|rarea|rwidth|age|wt_kg|pin|unibi @q Y = lucency Gamma = 0.05 Method = 1 Terms = full Include = 0 Cbound = none The number of effects forced into the model is 0. Variable names Variable Original Obs name name 1 x1 blade_size 2 x2 age 3 x3 wt_kg 4 x4 pin 5 x5 unibi 6 x6 rwidth 7 x7 rarea 8 y lucency Forward Sequence Selection Effect p-to- monotonized Obs Step 1+S Entered enter p-to-enter 1 0 1 Intercept <.0001 0.00000 2 1 2 x5 0.0002 0.00021 3 2 3 x4 0.0058 0.00584 4 3 4 x6 0.0290 0.02902 5 4 5 x3 0.0300 0.03003 6 5 6 x2 0.0349 0.03487 7 6 7 x3*x3 0.0365 0.03653 8 7 8 x2*x6 0.1815 0.18151 9 8 9 x2*x2 0.1689 0.18151 10 9 10 x4*x5 0.2473 0.24734 11 10 11 x3*x5 0.2280 0.24734 12 11 12 x2*x5 0.1829 0.24734 13 12 13 x6*x6 0.5346 0.53461 14 13 14 x3*x6 0.3380 0.53461 15 14 15 x2*x4 0.5116 0.53461 16 15 16 x3*x4 0.2704 0.53461 17 16 17 x1 0.7727 0.77274 18 17 18 x1*x5 0.0350 0.77274 19 18 19 x1*x3 0.3755 0.77274 20 19 20 x1*x6 0.5639 0.77274 21 20 21 x7 0.7028 0.77274 22 21 22 x2*x7 0.0274 0.77274 23 22 23 x1*x2 0.1405 0.77274 24 23 24 x5*x7 0.2575 0.77274 25 24 25 x6*x7 0.4592 0.77274 26 25 26 x7*x7 0.0547 0.77274 27 26 27 x3*x7 0.1686 0.77274 28 27 28 x2*x3 0.1731 0.77274 29 28 29 x4*x6 0.3639 0.77274 30 29 30 x5*x6 0.4364 0.77274 31 30 31 x1*x7 0.2952 0.77274 32 31 32 x4*x7 0.6126 0.77274 33 32 33 x1*x1 0.6277 0.77274 34 33 34 x1*x4 0.8960 0.89601 Sequence of Possible Models Obs alpha gammahat 1+S 1 0.00000 0.00000 1 2 0.00021 0.00064 2 3 0.00584 0.00973 3 4 0.02902 0.03627 4 5 0.03003 0.04204 5 6 0.03487 0.05812 6 7 0.03653 0.07306 7 8 0.18151 0.24202 9 9 0.24734 0.18550 12 10 0.53461 0.16707 16 11 0.77274 0.02342 33 12 0.89601 0.00000 34 Fast FSR estimates alpha Obs estimate 1+S 1 0.030028 5 The LOGISTIC Procedure Model Information Data Set WORK.LUCENCY_FFSR Response Variable y lucency Number of Response Levels 2 Model binary logit Optimization Technique Fisher's scoring Number of Observations Read 219 Number of Observations Used 219 Response Profile Ordered Total Value y Frequency 1 0 200 2 1 19 Probability modeled is y=0. Model Convergence Status Convergence criterion (GCONV=1E-8) satisfied. Model Fit Statistics Intercept Intercept and Criterion Only Covariates AIC 131.198 112.843 SC 134.587 129.788 -2 Log L 129.198 102.843 Testing Global Null Hypothesis: BETA=0 Test Chi-Square DF Pr > ChiSq Likelihood Ratio 26.3548 4 <.0001 Score 29.4783 4 <.0001 Wald 20.7378 4 0.0004 Analysis of Maximum Likelihood Estimates Standard Wald Parameter DF Estimate Error Chi-Square Pr > ChiSq Intercept 1 2.9656 0.3644 66.2134 <.0001 x5 1 -0.9496 0.2408 15.5513 <.0001 x4 1 -0.6336 0.2559 6.1283 0.0133 x6 1 -0.7735 0.2805 7.6017 0.0058 x3 1 -0.5570 0.2732 4.1574 0.0415 Odds Ratio Estimates Point 95% Wald Effect Estimate Confidence Limits x5 0.387 0.241 0.620 x4 0.531 0.321 0.876 x6 0.461 0.266 0.800 x3 0.573 0.335 0.979 Association of Predicted Probabilities and Observed Responses Percent Concordant 82.5 Somers' D 0.657 Percent Discordant 16.8 Gamma 0.661 Percent Tied 0.7 Tau-a 0.105 Pairs 3800 c 0.828