topic PROC CATMOD: type I or type III? in Statistical Procedures https://communities.sas.com/t5/Statistical-Procedures/PROC-CATMOD-type-I-or-type-III/m-p/41144#M1736 <HTML><HEAD></HEAD><BODY><P>Hi Sir,</P><P></P><P>The PROC CATMOD is a good method to run multinomial logit models (response variable with more than 2 categories). The estimation is usually based on maximum lilihood and a ANOVA table is produced. I am wondering if the AVOVA table is estimated based on Type I Sums of Squares or Type III. Just cannot find any reference for this.</P></BODY></HTML> Tue, 02 Aug 2011 20:05:51 GMT bncoxuk 2011-08-02T20:05:51Z PROC CATMOD: type I or type III? https://communities.sas.com/t5/Statistical-Procedures/PROC-CATMOD-type-I-or-type-III/m-p/41144#M1736 <HTML><HEAD></HEAD><BODY><P>Hi Sir,</P><P></P><P>The PROC CATMOD is a good method to run multinomial logit models (response variable with more than 2 categories). The estimation is usually based on maximum lilihood and a ANOVA table is produced. I am wondering if the AVOVA table is estimated based on Type I Sums of Squares or Type III. Just cannot find any reference for this.</P></BODY></HTML> Tue, 02 Aug 2011 20:05:51 GMT https://communities.sas.com/t5/Statistical-Procedures/PROC-CATMOD-type-I-or-type-III/m-p/41144#M1736 bncoxuk 2011-08-02T20:05:51Z PROC CATMOD: type I or type III? https://communities.sas.com/t5/Statistical-Procedures/PROC-CATMOD-type-I-or-type-III/m-p/41145#M1737 <HTML><HEAD></HEAD><BODY><P>Maximum likelihood estimation does not involve sums of squares.</P></BODY></HTML> Fri, 05 Aug 2011 20:20:11 GMT https://communities.sas.com/t5/Statistical-Procedures/PROC-CATMOD-type-I-or-type-III/m-p/41145#M1737 StatDave 2011-08-05T20:20:11Z