. use ratnoselong . list irritate conc count drug 1. 0 2 18 1 2. 1 2 2 1 3. 2 2 0 1 4. 3 2 0 1 5. 0 5 12 1 6. 1 5 6 1 7. 2 5 2 1 8. 3 5 0 1 9. 0 10 3 1 10. 1 10 7 1 11. 2 10 6 1 12. 3 10 4 1 13. 0 2 16 2 14. 1 2 3 2 15. 2 2 1 2 16. 3 2 0 2 17. 0 5 8 2 18. 1 5 8 2 19. 2 5 3 2 20. 3 5 1 2 21. 0 10 1 2 22. 1 10 5 2 23. 2 10 8 2 24. 3 10 6 2 . table conc irritate drug [freq=count] ----------+------------------------------------------------- | drug and Irritation Score Concentra | ---------- 1 --------- ---------- 2 --------- tion, ppm | 0 1 2 3 0 1 2 3 ----------+------------------------------------------------- 2 | 18 2 16 3 1 5 | 12 6 2 8 8 3 1 10 | 3 7 6 4 1 5 8 6 ----------+------------------------------------------------- *** Model [1] ***** . loglin count irritate conc drug, fit(irritate, conc, drug) Variable irritate = A Variable conc = B Variable drug = C Margins fit: irritate, conc, drug Note: Regression-like constraints are assumed. The first level of each variable (and all iteractions with it) will be dropped from estimation. Poisson regression Number of obs = 24 Goodness-of-fit chi2(17) = 69.999 Model chi2(6) = 40.214 Prob > chi2 = 0.0000 Prob > chi2 = 0.0000 Log Likelihood = -68.619 Pseudo R2 = 0.2266 ------------------------------------------------------------------------------ count | Coef. Std. Err. z P>|z| [95% Conf. Interval] ---------+-------------------------------------------------------------------- A2 | -.6264558 .2224847 -2.816 0.005 -1.062518 -.1903938 A3 | -1.064711 .2593094 -4.106 0.000 -1.572948 -.5564736 A4 | -1.662548 .3288624 -5.055 0.000 -2.307106 -1.017989 B2 | 8.13e-08 .2236068 0.000 1.000 -.4382612 .4382613 B3 | 2.82e-08 .2236068 0.000 1.000 -.4382612 .4382613 C2 | 1.08e-09 .1825742 0.000 1.000 -.3578388 .3578388 _cons | 2.268683 .2055271 11.038 0.000 1.865858 2.671509 ------------------------------------------------------------------------------ *** Model [2] ***** . loglin count irritate conc drug, fit(irritate conc, irritate drug, drug conc) > keep Variable irritate = A Variable conc = B Variable drug = C Margins fit: irritate conc, irritate drug, drug conc Note: Regression-like constraints are assumed. The first level of each variable (and all iteractions with it) will be dropped from estimation. Poisson regression Number of obs = 24 Goodness-of-fit chi2(6) = 1.410 Model chi2(17) = 108.803 Prob > chi2 = 0.9652 Prob > chi2 = 0.0000 Log Likelihood = -34.324 Pseudo R2 = 0.6131 ------------------------------------------------------------------------------ count | Coef. Std. Err. z P>|z| [95% Conf. Interval] ---------+-------------------------------------------------------------------- A2 | -2.29336 .5768962 -3.975 0.000 -3.424055 -1.162664 A3 | -4.306237 1.132086 -3.804 0.000 -6.525085 -2.087389 A4 | -18.41285 626.1843 -0.029 0.977 -1245.711 1208.886 AB22 | 1.612957 .6009135 2.684 0.007 .435188 2.790726 AB23 | 3.165697 .7717253 4.102 0.000 1.653143 4.678251 AB32 | 2.232878 1.142456 1.954 0.051 -.006294 4.472051 AB33 | 5.054484 1.196996 4.223 0.000 2.708415 7.400552 AB42 | 14.51961 626.1848 0.023 0.982 -1212.78 1241.819 AB43 | 18.65342 626.1843 0.030 0.976 -1208.645 1245.952 AC22 | .6770574 .514628 1.316 0.188 -.3315951 1.68571 AC32 | 1.253254 .666875 1.879 0.060 -.0537966 2.560305 AC42 | 1.543477 .8406153 1.836 0.066 -.1040989 3.191052 B2 | -.3939965 .3502443 -1.125 0.261 -1.080463 .2924697 B3 | -1.80532 .5658341 -3.191 0.001 -2.914335 -.6963059 C2 | -.1114918 .3262906 -0.342 0.733 -.7510095 .528026 CB22 | -.3153682 .4878299 -0.646 0.518 -1.271497 .6407608 CB23 | -.922593 .6302994 -1.464 0.143 -2.157957 .3127711 _cons | 2.887406 .2305347 12.525 0.000 2.435566 3.339246 ------------------------------------------------------------------------------ *** Model [3] ***** . poisson count A2-A4 B2-B3 C2 AB22- AB43 Poisson regression Number of obs = 24 Goodness-of-fit chi2(11) = 6.456 Model chi2(12) = 103.757 Prob > chi2 = 0.8413 Prob > chi2 = 0.0000 Log Likelihood = -36.847 Pseudo R2 = 0.5847 ------------------------------------------------------------------------------ count | Coef. Std. Err. z P>|z| [95% Conf. Interval] ---------+-------------------------------------------------------------------- A2 | -1.916923 .4789695 -4.002 0.000 -2.855686 -.9781597 A3 | -3.526361 1.014599 -3.476 0.001 -5.514939 -1.537782 A4 | -17.52636 665.1413 -0.026 0.979 -1321.179 1286.127 B2 | -.5306282 .2818009 -1.883 0.060 -1.082948 .0216915 B3 | -2.140066 .5285941 -4.049 0.000 -3.176092 -1.104041 C2 | -5.33e-08 .1825742 -0.000 1.000 -.3578389 .3578388 AB22 | 1.560248 .5923178 2.634 0.008 .3993261 2.721169 AB23 | 3.015535 .7501634 4.020 0.000 1.545242 4.485828 AB32 | 2.140066 1.131111 1.892 0.058 -.0768704 4.357003 AB33 | 4.779123 1.162257 4.112 0.000 2.501142 7.057104 AB42 | 14.53063 665.1421 0.022 0.983 -1289.124 1318.185 AB43 | 18.44265 665.1416 0.028 0.978 -1285.211 1322.096 _cons | 2.833213 .194281 14.583 0.000 2.45243 3.213997 ------------------------------------------------------------------------------ ----------+------------------------------------------------- | drug and Irritation Score Concentra | ---------- 1 --------- ---------- 2 --------- tion, ppm | 0 1 2 3 0 1 2 3 ----------+------------------------------------------------- 2 | 18.0 2.0 0.0 0.0 16.0 3.0 1.0 0.0 <-- count | 17.0 2.5 0.5 0.0 17.0 2.5 0.5 0.0 fit | 0.2 -0.3 -0.7 -0.0 -0.2 0.3 0.7 -0.0 Pearson res | 5 | 12.0 6.0 2.0 0.0 8.0 8.0 3.0 1.0 | 10.0 7.0 2.5 0.5 10.0 7.0 2.5 0.5 | 0.6 -0.4 -0.3 -0.7 -0.6 0.4 0.3 0.7 | 10 | 3.0 7.0 6.0 4.0 1.0 5.0 8.0 6.0 | 2.0 6.0 7.0 5.0 2.0 6.0 7.0 5.0 | 0.7 0.4 -0.4 -0.4 -0.7 -0.4 0.4 0.4 ----------+------------------------------------------------- . gen conclevl = (conc==2) + 2*(conc==5) + 3*(conc==10) . gen ic = irritate * conclevl . gen id = irritate * drug . gen cd = drug*conclevl . gen icd = ic*drug *** Model [4] ***** . poisson count A2-A4 B2-B3 C2 ic AC22-AC42 Poisson regression Number of obs = 24 Goodness-of-fit chi2(13) = 4.364 Model chi2(10) = 105.849 Prob > chi2 = 0.9867 Prob > chi2 = 0.0000 Log Likelihood = -35.801 Pseudo R2 = 0.5965 ------------------------------------------------------------------------------ count | Coef. Std. Err. z P>|z| [95% Conf. Interval] ---------+-------------------------------------------------------------------- A2 | -3.178848 .5180907 -6.136 0.000 -4.194287 -2.163409 A3 | -7.045192 1.120186 -6.289 0.000 -9.240717 -4.849667 A4 | -11.45835 1.836194 -6.240 0.000 -15.05722 -7.859476 B2 | -.4932236 .2377866 -2.074 0.038 -.9592768 -.0271705 B3 | -2.036607 .4364068 -4.667 0.000 -2.891948 -1.181265 C2 | -.2776318 .2651472 -1.047 0.295 -.7973107 .2420472 ic | 1.316711 .2293565 5.741 0.000 .8671801 1.766241 AC22 | .3421703 .4466203 0.766 0.444 -.5331894 1.21753 AC32 | .6830968 .5278602 1.294 0.196 -.3514901 1.717684 AC42 | .8372475 .6805587 1.230 0.219 -.4966231 2.171118 _cons | 2.941976 .2021266 14.555 0.000 2.545815 3.338137 ------------------------------------------------------------------------------ ----------+------------------------------------------------- | drug and Irritation Score Concentra | ---------- 1 --------- ---------- 2 --------- tion, ppm | 0 1 2 3 0 1 2 3 ----------+------------------------------------------------- 2 | 18.0 2.0 0.0 0.0 16.0 3.0 1.0 0.0 <-- count | 19.0 2.9 0.2 0.0 14.4 3.1 0.3 0.0 fit | -0.2 -0.6 -0.5 -0.1 0.4 -0.1 1.1 -0.1 Pearson res | 5 | 12.0 6.0 2.0 0.0 8.0 8.0 3.0 1.0 | 11.6 6.7 2.0 0.3 8.8 7.2 2.9 0.6 | 0.1 -0.3 0.0 -0.6 -0.3 0.3 0.0 0.6 | 10 | 3.0 7.0 6.0 4.0 1.0 5.0 8.0 6.0 | 2.5 5.3 5.8 3.7 1.9 5.7 8.7 6.4 | 0.3 0.7 0.1 0.2 -0.6 -0.3 -0.2 -0.2 ----------+------------------------------------------------- *** Model [5] ***** . poisson count A2-A4 B2-B3 C2 ic id Poisson regression Number of obs = 24 Goodness-of-fit chi2(15) = 4.409 Model chi2(8) = 105.804 Prob > chi2 = 0.9961 Prob > chi2 = 0.0000 Log Likelihood = -35.824 Pseudo R2 = 0.5962 ------------------------------------------------------------------------------ count | Coef. Std. Err. z P>|z| [95% Conf. Interval] ---------+-------------------------------------------------------------------- A2 | -3.467461 .5431094 -6.384 0.000 -4.531936 -2.402986 A3 | -7.617377 1.222545 -6.231 0.000 -10.01352 -5.221233 A4 | -12.43178 2.002323 -6.209 0.000 -16.35627 -8.507303 B2 | -.4932236 .2377866 -2.074 0.038 -.9592767 -.0271704 B3 | -2.036607 .4364068 -4.667 0.000 -2.891948 -1.181265 C2 | -.2633069 .2439284 -1.079 0.280 -.7413977 .2147839 ic | 1.316711 .2293565 5.741 0.000 .8671801 1.766241 id | .3060189 .1878861 1.629 0.103 -.0622312 .6742689 _cons | 2.935776 .1975585 14.860 0.000 2.548569 3.322984 ------------------------------------------------------------------------------ ----------+------------------------------------------------- | drug and Irritation Score Concentra | ---------- 1 --------- ---------- 2 --------- tion, ppm | 0 1 2 3 0 1 2 3 ----------+------------------------------------------------- 2 | 18.0 2.0 0.0 0.0 16.0 3.0 1.0 0.0 <-- count | 18.8 3.0 0.2 0.0 14.5 3.1 0.3 0.0 fit | -0.2 -0.6 -0.5 -0.1 0.4 -0.1 1.1 -0.1 Pearson res | 5 | 12.0 6.0 2.0 0.0 8.0 8.0 3.0 1.0 | 11.5 6.8 2.0 0.3 8.8 7.1 2.9 0.6 | 0.1 -0.3 -0.0 -0.6 -0.3 0.3 0.1 0.5 | 10 | 3.0 7.0 6.0 4.0 1.0 5.0 8.0 6.0 | 2.5 5.4 6.0 3.4 1.9 5.6 8.5 6.6 | 0.3 0.7 -0.0 0.3 -0.6 -0.3 -0.2 -0.2 ----------+------------------------------------------------- *** Model [6] ***** . ologit irritate [freq=count] Ordered Logit Estimates Number of obs = 120 chi2(0) = 0.00 Prob > chi2 = . Log Likelihood = -146.24822 Pseudo R2 = 0.0000 ------------------------------------------------------------------------------ irritate | Coef. Std. Err. z P>|z| [95% Conf. Interval] ---------+-------------------------------------------------------------------- ---------+-------------------------------------------------------------------- _cut1 | -.0666914 .1826757 (Ancillary parameters) _cut2 | 1.054649 .2085522 _cut3 | 2.293453 .3163596 ------------------------------------------------------------------------------ ----------+------------------------------------------------- | drug and Irritation Score Concentra | ---------- 1 --------- ---------- 2 --------- tion, ppm | 0 1 2 3 0 1 2 3 ----------+------------------------------------------------- 2 | 18.0 2.0 0.0 0.0 16.0 3.0 1.0 0.0 | 9.7 5.2 3.3 1.8 9.7 5.2 3.3 1.8 | 2.7 -1.4 -1.8 -1.4 2.0 -1.0 -1.3 -1.4 | 5 | 12.0 6.0 2.0 0.0 8.0 8.0 3.0 1.0 | 9.7 5.2 3.3 1.8 9.7 5.2 3.3 1.8 | 0.8 0.4 -0.7 -1.4 -0.5 1.2 -0.2 -0.6 | 10 | 3.0 7.0 6.0 4.0 1.0 5.0 8.0 6.0 | 9.7 5.2 3.3 1.8 9.7 5.2 3.3 1.8 | -2.1 0.8 1.5 1.6 -2.8 -0.1 2.6 3.1 ----------+------------------------------------------------- *** Model [7] ***** . ologit irritate conc [freq=count] Ordered Logit Estimates Number of obs = 120 chi2(1) = 62.45 Prob > chi2 = 0.0000 Log Likelihood = -115.0209 Pseudo R2 = 0.2135 ------------------------------------------------------------------------------ irritate | Coef. Std. Err. z P>|z| [95% Conf. Interval] ---------+-------------------------------------------------------------------- conc | .4825487 .0703163 6.863 0.000 .3447312 .6203661 ---------+-------------------------------------------------------------------- _cut1 | 2.537263 .4389045 (Ancillary parameters) _cut2 | 4.332566 .5806568 _cut3 | 5.951015 .683615 ------------------------------------------------------------------------------ ----------+------------------------------------------------- | drug and Irritation Score Concentra | ---------- 1 --------- ---------- 2 --------- tion, ppm | 0 1 2 3 0 1 2 3 ----------+------------------------------------------------- 2 | 18.0 2.0 0.0 0.0 16.0 3.0 1.0 0.0 | 16.6 2.8 0.5 0.1 16.6 2.8 0.5 0.1 | 0.4 -0.5 -0.7 -0.4 -0.1 0.1 0.6 -0.4 | 5 | 12.0 6.0 2.0 0.0 8.0 8.0 3.0 1.0 | 10.6 6.8 2.0 0.6 10.6 6.8 2.0 0.6 | 0.4 -0.3 0.0 -0.8 -0.8 0.5 0.7 0.6 | 10 | 3.0 7.0 6.0 4.0 1.0 5.0 8.0 6.0 | 1.8 5.7 7.5 4.9 1.8 5.7 7.5 4.9 | 0.9 0.5 -0.6 -0.4 -0.6 -0.3 0.2 0.5 ----------+------------------------------------------------- *** Model [8] ***** . ologit irritate conc drug [freq=count] Ordered Logit Estimates Number of obs = 120 chi2(2) = 66.96 Prob > chi2 = 0.0000 Log Likelihood = -112.76665 Pseudo R2 = 0.2289 ------------------------------------------------------------------------------ irritate | Coef. Std. Err. z P>|z| [95% Conf. Interval] ---------+-------------------------------------------------------------------- conc | .4941521 .0713122 6.929 0.000 .3543826 .6339215 drug | .8079859 .3850663 2.098 0.036 .0532699 1.562702 ---------+-------------------------------------------------------------------- _cut1 | 3.813741 .7769283 (Ancillary parameters) _cut2 | 5.657965 .8893055 _cut3 | 7.325177 .9861556 ------------------------------------------------------------------------------ ----------+------------------------------------------------- | drug and Irritation Score Concentra | ---------- 1 --------- ---------- 2 --------- tion, ppm | 0 1 2 3 0 1 2 3 ----------+------------------------------------------------- 2 | 18.0 2.0 0.0 0.0 16.0 3.0 1.0 0.0 | 17.7 1.9 0.3 0.1 15.4 3.7 0.7 0.2 | 0.1 0.0 -0.6 -0.3 0.2 -0.4 0.3 -0.4 | 5 | 12.0 6.0 2.0 0.0 8.0 8.0 3.0 1.0 | 12.6 5.7 1.4 0.3 8.6 7.9 2.7 0.8 | -0.2 0.1 0.6 -0.6 -0.2 0.0 0.2 0.3 | 10 | 3.0 7.0 6.0 4.0 1.0 5.0 8.0 6.0 | 2.5 7.0 7.0 3.4 1.2 4.6 7.9 6.3 | 0.3 -0.0 -0.4 0.3 -0.2 0.2 0.0 -0.1 ----------+------------------------------------------------- . gen conclevl = (conc==2) + 2*(conc==5) + 3*(conc==10) *** Model [9] ***** . ologit irritate conclevl drug [freq=count] Ordered Logit Estimates Number of obs = 120 chi2(2) = 67.06 Prob > chi2 = 0.0000 Log Likelihood = -112.7195 Pseudo R2 = 0.2293 ------------------------------------------------------------------------------ irritate | Coef. Std. Err. z P>|z| [95% Conf. Interval] ---------+-------------------------------------------------------------------- conclevl | 2.060755 .3036566 6.786 0.000 1.465599 2.655911 drug | .818688 .3882137 2.109 0.035 .0578031 1.579573 ---------+-------------------------------------------------------------------- _cut1 | 5.224382 .9377801 (Ancillary parameters) _cut2 | 7.030257 1.052794 _cut3 | 8.655955 1.142557 ------------------------------------------------------------------------------ ----------+------------------------------------------------- | drug and Irritation Score Concentra | ---------- 1 --------- ---------- 2 --------- tion, ppm | 0 1 2 3 0 1 2 3 ----------+------------------------------------------------- 2 | 18.0 2.0 0.0 0.0 16.0 3.0 1.0 0.0 | 18.3 1.4 0.2 0.1 16.4 2.9 0.6 0.1 | -0.1 0.5 -0.5 -0.2 -0.1 0.1 0.6 -0.4 | 5 | 12.0 6.0 2.0 0.0 8.0 8.0 3.0 1.0 | 11.4 6.4 1.7 0.5 7.4 8.2 3.3 1.0 | 0.2 -0.2 0.2 -0.7 0.2 -0.1 -0.2 -0.0 | 10 | 3.0 7.0 6.0 4.0 1.0 5.0 8.0 6.0 | 2.9 7.3 6.6 3.2 1.4 4.9 7.7 6.0 | 0.1 -0.1 -0.3 0.4 -0.3 0.1 0.1 -0.0 ----------+------------------------------------------------- *** Model [10] ***** . xi: ologit irritate i.conclevl drug [freq=count] i.conclevl Iconcl_1-3 (naturally coded; Iconcl_1 omitted) Ordered Logit Estimates Number of obs = 120 chi2(3) = 67.38 Prob > chi2 = 0.0000 Log Likelihood = -112.56013 Pseudo R2 = 0.2303 ------------------------------------------------------------------------------ irritate | Coef. Std. Err. z P>|z| [95% Conf. Interval] ---------+-------------------------------------------------------------------- Iconcl_2 | 1.798493 .54562 3.296 0.001 .7290971 2.867888 Iconcl_3 | 4.063291 .6059677 6.705 0.000 2.875616 5.250966 drug | .8152188 .3871055 2.106 0.035 .056506 1.573932 ---------+-------------------------------------------------------------------- _cut1 | 3.014587 .7735303 (Ancillary parameters) _cut2 | 4.843755 .8535858 _cut3 | 6.491787 .933387 ------------------------------------------------------------------------------ ----------+------------------------------------------------- | drug and Irritation Score Concentra | ---------- 1 --------- ---------- 2 --------- tion, ppm | 0 1 2 3 0 1 2 3 ----------+------------------------------------------------- 2 | 18.0 2.0 0.0 0.0 16.0 3.0 1.0 0.0 | 18.0 1.6 0.3 0.1 16.0 3.2 0.6 0.2 | -0.0 0.3 -0.5 -0.3 0.0 -0.1 0.5 -0.4 | 5 | 12.0 6.0 2.0 0.0 8.0 8.0 3.0 1.0 | 12.0 6.1 1.5 0.4 8.0 8.1 3.0 0.9 | 0.0 -0.0 0.4 -0.6 0.0 -0.0 -0.0 0.1 | 10 | 3.0 7.0 6.0 4.0 1.0 5.0 8.0 6.0 | 2.7 7.1 6.9 3.3 1.3 4.7 7.8 6.2 | 0.2 -0.1 -0.3 0.4 -0.3 0.1 0.1 -0.1 ----------+------------------------------------------------- *** Model [11] ***** . xi: ologit irritate i.drug*conclevl [freq=count] i.drug Idrug_1-2 (naturally coded; Idrug_1 omitted) i.drug*conclevl IdXcon_# (coded as above) Ordered Logit Estimates Number of obs = 120 chi2(3) = 67.07 Prob > chi2 = 0.0000 Log Likelihood = -112.71266 Pseudo R2 = 0.2293 ------------------------------------------------------------------------------ irritate | Coef. Std. Err. z P>|z| [95% Conf. Interval] ---------+-------------------------------------------------------------------- Idrug_2 | .9615218 1.283425 0.749 0.454 -1.553945 3.476989 conclevl | 2.096727 .4343191 4.828 0.000 1.245477 2.947977 IdXcon_2 | -.0626849 .5363265 -0.117 0.907 -1.113866 .9884957 ---------+-------------------------------------------------------------------- _cut1 | 4.489972 1.019457 (Ancillary parameters) _cut2 | 6.295934 1.115265 _cut3 | 7.918717 1.174761 ------------------------------------------------------------------------------ ----------+------------------------------------------------- | drug and Irritation Score Concentra | ---------- 1 --------- ---------- 2 --------- tion, ppm | 0 1 2 3 0 1 2 3 ----------+------------------------------------------------- 2 | 18.0 2.0 0.0 0.0 16.0 3.0 1.0 0.0 | 18.3 1.4 0.2 0.1 16.3 3.0 0.6 0.1 | -0.1 0.5 -0.5 -0.2 -0.1 0.0 0.6 -0.4 | 5 | 12.0 6.0 2.0 0.0 8.0 8.0 3.0 1.0 | 11.5 6.4 1.7 0.5 7.4 8.2 3.3 1.1 | 0.2 -0.1 0.2 -0.7 0.2 -0.1 -0.2 -0.1 | 10 | 3.0 7.0 6.0 4.0 1.0 5.0 8.0 6.0 | 2.8 7.2 6.7 3.3 1.4 4.9 7.7 6.0 | 0.1 -0.1 -0.3 0.4 -0.4 0.0 0.1 0.0 ----------+-------------------------------------------------