The SAS System The FREQ Procedure Table of pview by choice pview choice Frequency| Expected | Percent |bush |clinton |perot | Total ---------+--------+--------+--------+ lib | 70 | 324 | 56 | 450 | 163.94 | 216.64 | 69.426 | | 3.94 | 18.24 | 3.15 | 25.34 ---------+--------+--------+--------+ mod | 195 | 332 | 101 | 628 | 228.78 | 302.33 | 96.887 | | 10.98 | 18.69 | 5.69 | 35.36 ---------+--------+--------+--------+ cons | 382 | 199 | 117 | 698 | 254.28 | 336.03 | 107.69 | | 21.51 | 11.20 | 6.59 | 39.30 ---------+--------+--------+--------+ Total 647 855 274 1776 36.43 48.14 15.43 100.00 Statistics for Table of pview by choice Statistic DF Value Prob ------------------------------------------------------ Chi-Square 4 238.5354 <.0001 Likelihood Ratio Chi-Square 4 247.6951 <.0001 Mantel-Haenszel Chi-Square 1 74.8580 <.0001 Phi Coefficient 0.3665 Contingency Coefficient 0.3441 Cramer's V 0.2591 Sample Size = 1776 The SAS System The GENMOD Procedure Model Information Data Set WORK.VOTE Distribution Poisson Link Function Log Dependent Variable count Observations Used 9 Class Level Information Class Levels Values pview 3 lib mod cons choice 3 bush clinton perot Criteria For Assessing Goodness Of Fit Criterion DF Value Value/DF Deviance 4 247.6951 61.9238 Scaled Deviance 4 247.6951 61.9238 Pearson Chi-Square 4 238.5354 59.6339 Scaled Pearson X2 4 238.5354 59.6339 Log Likelihood 7799.2873 Algorithm converged. Analysis Of Parameter Estimates Standard Likelihood Ratio 95% Chi- Parameter DF Estimate Error Confidence Limits Square Pr > ChiSq Intercept 1 4.6792 0.0672 4.5453 4.8089 4844.88 <.0001 pview lib 1 -0.4390 0.0605 -0.5580 -0.3210 52.72 <.0001 pview mod 1 -0.1057 0.0550 -0.2136 0.0020 3.69 0.0547 pview cons 0 0.0000 0.0000 0.0000 0.0000 . . choice bush 1 0.8592 0.0721 0.7192 1.0019 142.10 <.0001 choice clinton 1 1.1380 0.0694 1.0034 1.2757 268.71 <.0001 choice perot 0 0.0000 0.0000 0.0000 0.0000 . . Scale 0 1.0000 0.0000 1.0000 1.0000 NOTE: The scale parameter was held fixed. LR Statistics For Type 3 Analysis Chi- Source DF Square Pr > ChiSq pview 2 57.25 <.0001 choice 2 321.38 <.0001 The SAS System The GENMOD Procedure Observation Statistics Observation count pview choice Pred Xbeta Std HessWgt Lower Upper Resraw Reschi Resdev StResdev StReschi Reslik 1 70 lib bush 163.93581 5.099475 0.0566105 163.93581 146.71917 183.17273 -93.93581 -7.33659 -8.290625 -12.03404 -10.64924 -11.32763 2 324 lib clinton 216.63851 5.3782301 0.053186 216.63851 195.19274 240.44052 107.36149 7.2942506 6.790118 10.91236 11.722549 11.415681 3 56 lib perot 69.425676 4.2402568 0.0728615 69.425676 60.18667 80.082922 -13.42568 -1.611299 -1.667928 -2.099005 -2.02774 -2.073024 4 195 mod bush 228.78153 5.4327675 0.0507434 228.78153 207.12291 252.70497 -33.78153 -2.233412 -2.292063 -3.575621 -3.484126 -3.522011 5 332 mod clinton 302.33108 5.7115227 0.0468923 302.33108 275.78334 331.43439 29.668919 1.7063194 1.6794942 2.9008196 2.9471519 2.9317025 6 101 mod perot 96.887387 4.5735493 0.0684027 96.887387 84.731085 110.78775 4.1126126 0.4178151 0.4149104 0.561166 0.5650947 0.5629504 7 382 cons bush 254.28266 5.5384465 0.0491447 254.28266 230.93233 279.99401 127.71734 8.0092436 7.4493996 11.992449 12.893716 12.553625 8 199 cons clinton 336.03041 5.8172016 0.0451574 336.03041 307.56755 367.12727 -137.0304 -7.475283 -8.096288 -14.43078 -13.3239 -13.68197 9 117 cons perot 107.68694 4.6792283 0.0672253 107.68694 94.393214 122.85286 9.3130631 0.8974516 0.8849609 1.2351585 1.252592 1.2436733 The SAS System The CATMOD Procedure Data Summary Response pview*choice Response Levels 9 Weight Variable count Populations 1 Data Set VOTE Total Frequency 1776 Frequency Missing 0 Observations 9 Population Profiles Sample Sample Size --------------------- 1 1776 Response Profiles Response pview choice ---------------------------- 1 lib bush 2 lib clinton 3 lib perot 4 mod bush 5 mod clinton 6 mod perot 7 cons bush 8 cons clinton 9 cons perot _Response_ Matrix 1 2 3 4 --------------------------------------- 1 1 0 1 0 2 1 0 0 1 3 1 0 -1 -1 4 0 1 1 0 5 0 1 0 1 6 0 1 -1 -1 7 -1 -1 1 0 8 -1 -1 0 1 9 -1 -1 -1 -1 Maximum Likelihood Analysis Sub -2 Log Convergence Parameter Estimates Iteration Iteration Likelihood Criterion 1 2 3 4 ------------------------------------------------------------------------------------------------------- 0 0 7804.5417 1.0000 0 0 0 0 1 0 7436.6001 0.0471 -0.2399 0.0608 0.0929 0.4443 2 0 7425.9396 0.001434 -0.2573 0.0759 0.1915 0.4675 3 0 7425.9119 3.7347E-6 -0.2574 0.0759 0.1935 0.4722 4 0 7425.9119 4.122E-11 -0.2574 0.0759 0.1935 0.4722 The SAS System The CATMOD Procedure Maximum likelihood computations converged. Maximum Likelihood Analysis of Variance Source DF Chi-Square Pr > ChiSq -------------------------------------------------- pview 2 54.51 <.0001 choice 2 268.72 <.0001 Likelihood Ratio 4 247.70 <.0001 Analysis of Maximum Likelihood Estimates Standard Chi- Parameter Estimate Error Square Pr > ChiSq ------------------------------------------------------------------ pview lib -0.2574 0.0364 50.06 <.0001 mod 0.0759 0.0334 5.17 0.0230 choice bush 0.1935 0.0350 30.63 <.0001 clinton 0.4722 0.0331 203.28 <.0001 The SAS System The GENMOD Procedure Model Information Data Set WORK.VOTE Distribution Poisson Link Function Log Dependent Variable count Observations Used 9 Class Level Information Class Levels Values pview 3 lib mod cons choice 3 bush clinton perot Criteria For Assessing Goodness Of Fit Criterion DF Value Value/DF Deviance 0 0.0000 . Scaled Deviance 0 0.0000 . Pearson Chi-Square 0 0.0000 . Scaled Pearson X2 0 0.0000 . Log Likelihood 7923.1348 Algorithm converged. Analysis Of Parameter Estimates Standard Likelihood Ratio 95% Chi- Parameter DF Estimate Error Confidence Limits Square Pr > ChiSq Intercept 1 4.7622 0.0925 4.5753 4.9381 2653.36 <.0001 pview*choice lib bush 1 -0.5137 0.1511 -0.8141 -0.2207 11.56 0.0007 pview*choice lib clinton 1 1.0186 0.1079 0.8105 1.2337 89.18 <.0001 pview*choice lib perot 1 -0.7368 0.1625 -1.0620 -0.4236 20.56 <.0001 pview*choice mod bush 1 0.5108 0.1169 0.2836 0.7425 19.08 <.0001 pview*choice mod clinton 1 1.0430 0.1075 0.8356 1.2574 94.11 <.0001 pview*choice mod perot 1 -0.1471 0.1358 -0.4145 0.1187 1.17 0.2790 pview*choice cons bush 1 1.1832 0.1057 0.9797 1.3943 125.40 <.0001 pview*choice cons clinton 1 0.5311 0.1165 0.3048 0.7620 20.79 <.0001 pview*choice cons perot 0 0.0000 0.0000 0.0000 0.0000 . . Scale 0 1.0000 0.0000 1.0000 1.0000 NOTE: The scale parameter was held fixed. The SAS System The GENMOD Procedure LR Statistics For Type 3 Analysis Chi- Source DF Square Pr > ChiSq pview*choice 8 626.32 <.0001 Observation Statistics Observation count pview choice Pred Xbeta Std HessWgt Lower Upper Resraw Reschi Resdev StResdev StReschi Reslik 1 70 lib bush 70 4.2484952 0.1195229 70 55.380898 88.47816 4.263E-14 5.096E-15 0 0 4.0988E-7 4.0988E-7 2 324 lib clinton 324 5.7807435 0.0555556 324 290.57352 361.27174 1.137E-13 6.316E-15 0 . . . 3 56 lib perot 56 4.0253517 0.1336306 56 43.096444 72.767025 -2.13E-14 -2.85E-15 0 . . . 4 195 mod bush 195 5.2729996 0.0716115 195 169.46453 224.38324 0 0 0 . . . 5 332 mod clinton 332 5.805135 0.0548821 332 298.14143 369.70373 1.137E-13 6.239E-15 1.0861E-8 . . . 6 101 mod perot 101 4.6151205 0.0995037 101 83.10433 122.74932 -2.84E-14 -2.83E-15 0 . . . 7 382 cons bush 382 5.9454206 0.0511645 382 345.55096 422.29372 -5.68E-14 -2.91E-15 -6.317E-9 -0.572318 -2.635E-7 -2.636E-7 8 199 cons clinton 199 5.2933048 0.0708881 199 173.18609 228.66156 2.842E-14 2.015E-15 0 0 1.1619E-7 1.1619E-7 9 117 cons perot 117 4.7621739 0.09245 117 97.609537 140.24244 9.095E-13 8.408E-14 0 0 3.5245E-6 3.5245E-6