The SAS System 11:06 Monday, March 6, 2000 1 The FREQ Procedure Table of sex by ldose sex ldose Frequency| 0| 1| 2| 3| 4| 5| Total ---------+--------+--------+--------+--------+--------+--------+ F | 0 | 2 | 6 | 10 | 12 | 16 | 46 ---------+--------+--------+--------+--------+--------+--------+ M | 1 | 4 | 9 | 13 | 18 | 20 | 65 ---------+--------+--------+--------+--------+--------+--------+ Total 1 6 15 23 30 36 111 The SAS System 11:06 Monday, March 6, 2000 2 The GENMOD Procedure Model Information Data Set WORK.DAT Distribution Binomial Link Function Logit Response Variable (Events) dead Response Variable (Trials) total Observations Used 12 Number Of Events 111 Number Of Trials 240 Class Level Information Class Levels Values sex 2 F M pctdead 12 0 1 0.1 0.2 0.3 0.5 0.6 0.8 0.9 0.05 0.45 0.65 Criteria For Assessing Goodness Of Fit Criterion DF Value Value/DF Deviance 8 4.9937 0.6242 Scaled Deviance 8 4.9937 0.6242 Pearson Chi-Square 8 3.5047 0.4381 Scaled Pearson X2 8 3.5047 0.4381 Log Likelihood -105.7388 Algorithm converged. Analysis Of Parameter Estimates Wald 95% Standard Confidence Limits Chi- Parameter DF Estimate Error Lower Upper Square Pr > ChiSq Intercept 1 -2.8186 0.5480 -3.8926 -1.7445 26.46 <.0001 ldose 1 1.2589 0.2121 0.8433 1.6746 35.24 <.0001 sex F 1 -0.1750 0.7783 -1.7004 1.3505 0.05 0.8221 sex M 0 0.0000 0.0000 0.0000 0.0000 . . ldose*sex F 1 -0.3529 0.2700 -0.8821 0.1763 1.71 0.1912 ldose*sex M 0 0.0000 0.0000 0.0000 0.0000 . . The SAS System 11:06 Monday, March 6, 2000 3 The GENMOD Procedure Analysis Of Parameter Estimates Wald 95% Standard Confidence Limits Chi- Parameter DF Estimate Error Lower Upper Square Pr > ChiSq Scale 0 1.0000 0.0000 1.0000 1.0000 NOTE: The scale parameter was held fixed. LR Statistics For Type 1 Analysis Chi- Source Deviance DF Square Pr > ChiSq Intercept 124.8756 ldose 16.9840 1 107.89 <.0001 sex 6.7571 1 10.23 0.0014 ldose*sex 4.9937 1 1.76 0.1842 LR Statistics For Type 3 Analysis Chi- Source DF Square Pr > ChiSq ldose 1 112.73 <.0001 sex 1 0.05 0.8221 ldose*sex 1 1.76 0.1842 The SAS System 11:06 Monday, March 6, 2000 4 Plot of ldose*pdead. Symbol used is '*'. Plot of ldose*pctdead. Symbol is value of sex. ldose | | 5 + * * F M | | | | | | 4 + * * F M | | | | | | 3 + * * F M | | | | | | 2 + * * F M | | | | | | 1 + * * F M | | | | | | 0 + ** F M | -+-------------+-------------+-------------+-------------+-------------+- 0.0 0.2 0.4 0.6 0.8 1.0 Predicted Value The SAS System 11:06 Monday, March 6, 2000 5 The GENMOD Procedure Model Information Data Set WORK.PLOT Predicted Values and Diagnostic Statistics Distribution Binomial Link Function Logit Response Variable (Events) dead Response Variable (Trials) total Observations Used 12 Number Of Events 111 Number Of Trials 240 Class Level Information Class Levels Values sex 2 F M Criteria For Assessing Goodness Of Fit Criterion DF Value Value/DF Deviance 9 6.7571 0.7508 Scaled Deviance 9 6.7571 0.7508 Pearson Chi-Square 9 5.3060 0.5896 Scaled Pearson X2 9 5.3060 0.5896 Log Likelihood -106.6204 Algorithm converged. Analysis Of Parameter Estimates Wald 95% Standard Confidence Limits Chi- Parameter DF Estimate Error Lower Upper Square Pr > ChiSq Intercept 0 0.0000 0.0000 0.0000 0.0000 . . ldose 1 1.0642 0.1311 0.8073 1.3211 65.92 <.0001 sex F 1 -3.4732 0.4685 -4.3914 -2.5549 54.95 <.0001 sex M 1 -2.3724 0.3855 -3.1280 -1.6168 37.87 <.0001 Scale 0 1.0000 0.0000 1.0000 1.0000 The SAS System 11:06 Monday, March 6, 2000 6 The GENMOD Procedure NOTE: The scale parameter was held fixed. Lagrange Multiplier Statistics Parameter Chi-Square Pr > ChiSq Intercept . .