The SAS System The LOGISTIC Procedure Model Information Data Set WORK.GATOR Response Variable food Number of Response Levels 5 Frequency Variable count Model generalized logit Optimization Technique Newton-Raphson Number of Observations Read 80 Number of Observations Used 56 Sum of Frequencies Read 219 Sum of Frequencies Used 219 Response Profile Ordered Total Value food Frequency 1 bird 13 2 fish 94 3 invert 61 4 other 32 5 reptile 19 Logits modeled use food='fish' as the reference category. NOTE: 24 observations having nonpositive frequencies or weights were excluded since they do not contribute to the analysis. Class Level Information Class Value Design Variables lake Hancock 0 0 0 Oklawaha 1 0 0 Trafford 0 1 0 George 0 0 1 size small 0 large 1 sex male 0 female 1 The SAS System The LOGISTIC Procedure Model Convergence Status Convergence criterion (GCONV=1E-8) satisfied. Deviance and Pearson Goodness-of-Fit Statistics Criterion Value DF Value/DF Pr > ChiSq Deviance 50.2637 40 1.2566 0.1282 Pearson 52.5643 40 1.3141 0.0881 Number of unique profiles: 16 Model Fit Statistics Intercept Intercept and Criterion Only Covariates AIC 612.363 585.865 SC 625.919 667.203 -2 Log L 604.363 537.865 Testing Global Null Hypothesis: BETA=0 Test Chi-Square DF Pr > ChiSq Likelihood Ratio 66.4974 20 <.0001 Score 59.4616 20 <.0001 Wald 51.2336 20 0.0001 Type 3 Analysis of Effects Wald Effect DF Chi-Square Pr > ChiSq lake 12 36.2293 0.0003 size 4 15.8873 0.0032 sex 4 2.1850 0.7018 The SAS System The LOGISTIC Procedure Analysis of Maximum Likelihood Estimates Standard Wald Parameter food DF Estimate Error Chi-Square Pr > ChiSq Intercept bird 1 -2.4633 0.7739 10.1310 0.0015 Intercept invert 1 -2.0744 0.6116 11.5025 0.0007 Intercept other 1 -0.9167 0.4782 3.6755 0.0552 Intercept reptile 1 -2.9141 0.8856 10.8275 0.0010 lake Oklawaha bird 1 -1.1256 1.1924 0.8912 0.3452 lake Oklawaha invert 1 2.6937 0.6692 16.2000 <.0001 lake Oklawaha other 1 -0.7405 0.7422 0.9956 0.3184 lake Oklawaha reptile 1 1.4008 0.8105 2.9872 0.0839 lake Trafford bird 1 0.6617 0.8461 0.6117 0.4341 lake Trafford invert 1 2.9363 0.6874 18.2469 <.0001 lake Trafford other 1 0.7912 0.5879 1.8109 0.1784 lake Trafford reptile 1 1.9316 0.8253 5.4775 0.0193 lake George bird 1 -0.5753 0.7952 0.5233 0.4694 lake George invert 1 1.7805 0.6232 8.1623 0.0043 lake George other 1 -0.7666 0.5686 1.8179 0.1776 lake George reptile 1 -1.1287 1.1925 0.8959 0.3439 size large bird 1 0.7302 0.6523 1.2533 0.2629 size large invert 1 -1.3363 0.4112 10.5606 0.0012 size large other 1 -0.2906 0.4599 0.3992 0.5275 size large reptile 1 0.5570 0.6466 0.7421 0.3890 sex female bird 1 0.6064 0.6888 0.7750 0.3787 sex female invert 1 0.4630 0.3955 1.3701 0.2418 sex female other 1 0.2526 0.4663 0.2933 0.5881 sex female reptile 1 0.6275 0.6852 0.8387 0.3598 Odds Ratio Estimates Point 95% Wald Effect food Estimate Confidence Limits lake Oklawaha vs Hancock bird 0.324 0.031 3.358 lake Oklawaha vs Hancock invert 14.786 3.983 54.893 lake Oklawaha vs Hancock other 0.477 0.111 2.042 lake Oklawaha vs Hancock reptile 4.058 0.829 19.872 lake Trafford vs Hancock bird 1.938 0.369 10.176 lake Trafford vs Hancock invert 18.846 4.899 72.500 lake Trafford vs Hancock other 2.206 0.697 6.983 lake Trafford vs Hancock reptile 6.900 1.369 34.784 lake George vs Hancock bird 0.563 0.118 2.673 lake George vs Hancock invert 5.933 1.749 20.125 lake George vs Hancock other 0.465 0.152 1.416 lake George vs Hancock reptile 0.323 0.031 3.349 size large vs small bird 2.076 0.578 7.454 size large vs small invert 0.263 0.117 0.588 size large vs small other 0.748 0.304 1.842 size large vs small reptile 1.745 0.492 6.198 The SAS System The LOGISTIC Procedure Odds Ratio Estimates Point 95% Wald Effect food Estimate Confidence Limits sex female vs male bird 1.834 0.475 7.075 sex female vs male invert 1.589 0.732 3.449 sex female vs male other 1.287 0.516 3.211 sex female vs male reptile 1.873 0.489 7.175 The SAS System The LOGISTIC Procedure Model Information Data Set WORK.GATOR Response Variable food Number of Response Levels 5 Frequency Variable count Model generalized logit Optimization Technique Newton-Raphson Number of Observations Read 80 Number of Observations Used 56 Sum of Frequencies Read 219 Sum of Frequencies Used 219 Response Profile Ordered Total Value food Frequency 1 bird 13 2 fish 94 3 invert 61 4 other 32 5 reptile 19 Logits modeled use food='fish' as the reference category. NOTE: 24 observations having nonpositive frequencies or weights were excluded since they do not contribute to the analysis. Model Convergence Status Convergence criterion (GCONV=1E-8) satisfied. -2 Log L = 604.363 Deviance and Pearson Goodness-of-Fit Statistics Criterion Value DF Value/DF Pr > ChiSq Deviance 0.0000 0 . . Pearson 0.0000 0 . . Number of unique profiles: 1 The SAS System The LOGISTIC Procedure Analysis of Maximum Likelihood Estimates Standard Wald Parameter food DF Estimate Error Chi-Square Pr > ChiSq Intercept bird 1 -1.9783 0.2959 44.6984 <.0001 Intercept invert 1 -0.4324 0.1644 6.9173 0.0085 Intercept other 1 -1.0776 0.2047 27.7197 <.0001 Intercept reptile 1 -1.5989 0.2515 40.4037 <.0001 The SAS System The LOGISTIC Procedure Model Information Data Set WORK.GATOR Response Variable food Number of Response Levels 5 Frequency Variable count Model generalized logit Optimization Technique Newton-Raphson Number of Observations Read 80 Number of Observations Used 56 Sum of Frequencies Read 219 Sum of Frequencies Used 219 Response Profile Ordered Total Value food Frequency 1 bird 13 2 fish 94 3 invert 61 4 other 32 5 reptile 19 Logits modeled use food='fish' as the reference category. NOTE: 24 observations having nonpositive frequencies or weights were excluded since they do not contribute to the analysis. Model Convergence Status Convergence criterion (GCONV=1E-8) satisfied. -2 Log L = 604.363 Deviance and Pearson Goodness-of-Fit Statistics Criterion Value DF Value/DF Pr > ChiSq Deviance 116.7611 60 1.9460 <.0001 Pearson 106.4922 60 1.7749 0.0002 Number of unique profiles: 16 The SAS System The LOGISTIC Procedure Analysis of Maximum Likelihood Estimates Standard Wald Parameter food DF Estimate Error Chi-Square Pr > ChiSq Intercept bird 1 -1.9783 0.2959 44.6984 <.0001 Intercept invert 1 -0.4324 0.1644 6.9173 0.0085 Intercept other 1 -1.0776 0.2047 27.7197 <.0001 Intercept reptile 1 -1.5989 0.2515 40.4037 <.0001 The SAS System The LOGISTIC Procedure Model Information Data Set WORK.GATOR Response Variable food Number of Response Levels 5 Frequency Variable count Model generalized logit Optimization Technique Newton-Raphson Number of Observations Read 80 Number of Observations Used 56 Sum of Frequencies Read 219 Sum of Frequencies Used 219 Response Profile Ordered Total Value food Frequency 1 bird 13 2 fish 94 3 invert 61 4 other 32 5 reptile 19 Logits modeled use food='fish' as the reference category. NOTE: 24 observations having nonpositive frequencies or weights were excluded since they do not contribute to the analysis. Model Convergence Status Convergence criterion (GCONV=1E-8) satisfied. -2 Log L = 604.363 Deviance and Pearson Goodness-of-Fit Statistics Criterion Value DF Value/DF Pr > ChiSq Deviance 116.7611 60 1.9460 <.0001 Pearson 106.4922 60 1.7749 0.0002 Number of unique profiles: 16 NOTE: The covariance matrix has been multiplied by the heterogeneity factor (square of SCALE=1.148) 1.3179. The SAS System The LOGISTIC Procedure Analysis of Maximum Likelihood Estimates Standard Wald Parameter food DF Estimate Error Chi-Square Pr > ChiSq Intercept bird 1 -1.9783 0.3397 33.9163 <.0001 Intercept invert 1 -0.4324 0.1887 5.2487 0.0220 Intercept other 1 -1.0776 0.2350 21.0332 <.0001 Intercept reptile 1 -1.5989 0.2888 30.6576 <.0001 The SAS System The LOGISTIC Procedure Model Information Data Set WORK.GATOR Response Variable food Number of Response Levels 5 Frequency Variable count Model generalized logit Optimization Technique Newton-Raphson Number of Observations Read 80 Number of Observations Used 56 Sum of Frequencies Read 219 Sum of Frequencies Used 219 Response Profile Ordered Total Value food Frequency 1 bird 13 2 fish 94 3 invert 61 4 other 32 5 reptile 19 Logits modeled use food='fish' as the reference category. NOTE: 24 observations having nonpositive frequencies or weights were excluded since they do not contribute to the analysis. Class Level Information Class Value Design Variables lake Hancock 0 0 0 Oklawaha 1 0 0 Trafford 0 1 0 George 0 0 1 size small 0 large 1 Model Convergence Status Convergence criterion (GCONV=1E-8) satisfied. The SAS System The LOGISTIC Procedure Deviance and Pearson Goodness-of-Fit Statistics Criterion Value DF Value/DF Pr > ChiSq Deviance 52.4785 44 1.1927 0.1784 Pearson 58.0140 44 1.3185 0.0765 Number of unique profiles: 16 Model Fit Statistics Intercept Intercept and Criterion Only Covariates AIC 612.363 580.080 SC 625.919 647.862 -2 Log L 604.363 540.080 Testing Global Null Hypothesis: BETA=0 Test Chi-Square DF Pr > ChiSq Likelihood Ratio 64.2826 16 <.0001 Score 57.2475 16 <.0001 Wald 49.7584 16 <.0001 Type 3 Analysis of Effects Wald Effect DF Chi-Square Pr > ChiSq lake 12 35.4890 0.0004 size 4 18.7593 0.0009 Analysis of Maximum Likelihood Estimates Standard Wald Parameter food DF Estimate Error Chi-Square Pr > ChiSq Intercept bird 1 -2.0286 0.5581 13.2144 0.0003 Intercept invert 1 -1.7492 0.5392 10.5242 0.0012 Intercept other 1 -0.7465 0.3520 4.4983 0.0339 Intercept reptile 1 -2.4230 0.6436 14.1732 0.0002 lake Oklawaha bird 1 -1.3483 1.1635 1.3429 0.2465 lake Oklawaha invert 1 2.5956 0.6597 15.4797 <.0001 lake Oklawaha other 1 -0.8205 0.7296 1.2647 0.2608 lake Oklawaha reptile 1 1.2161 0.7860 2.3937 0.1218 The SAS System The LOGISTIC Procedure Analysis of Maximum Likelihood Estimates Standard Wald Parameter food DF Estimate Error Chi-Square Pr > ChiSq lake Trafford bird 1 0.3926 0.7818 0.2523 0.6155 lake Trafford invert 1 2.7803 0.6712 17.1578 <.0001 lake Trafford other 1 0.6902 0.5597 1.5207 0.2175 lake Trafford reptile 1 1.6925 0.7804 4.7028 0.0301 lake George bird 1 -0.6951 0.7813 0.7916 0.3736 lake George invert 1 1.6583 0.6129 7.3216 0.0068 lake George other 1 -0.8262 0.5575 2.1959 0.1384 lake George reptile 1 -1.2422 1.1852 1.0985 0.2946 size large bird 1 0.6307 0.6425 0.9635 0.3263 size large invert 1 -1.4582 0.3959 13.5634 0.0002 size large other 1 -0.3316 0.4483 0.5471 0.4595 size large reptile 1 0.3513 0.5800 0.3668 0.5448 Odds Ratio Estimates Point 95% Wald Effect food Estimate Confidence Limits lake Oklawaha vs Hancock bird 0.260 0.027 2.540 lake Oklawaha vs Hancock invert 13.404 3.679 48.840 lake Oklawaha vs Hancock other 0.440 0.105 1.840 lake Oklawaha vs Hancock reptile 3.374 0.723 15.747 lake Trafford vs Hancock bird 1.481 0.320 6.854 lake Trafford vs Hancock invert 16.124 4.326 60.093 lake Trafford vs Hancock other 1.994 0.666 5.972 lake Trafford vs Hancock reptile 5.433 1.177 25.081 lake George vs Hancock bird 0.499 0.108 2.307 lake George vs Hancock invert 5.251 1.580 17.454 lake George vs Hancock other 0.438 0.147 1.305 lake George vs Hancock reptile 0.289 0.028 2.947 size large vs small bird 1.879 0.533 6.619 size large vs small invert 0.233 0.107 0.506 size large vs small other 0.718 0.298 1.728 size large vs small reptile 1.421 0.456 4.429