5.4. Estimation with CATMOD

CATMOD is a very general procedure for categorical data analysis. In addition to the multinomial logit model, it does loglinear analysis and a variety of specialized models by using either maximum likelihood (ML) or weighted least squares estimation. Although the weighted least squares algorithm only works for grouped data, it can estimate a somewhat wider class of models than maximum likelihood. I consider only ML here, however.

ML estimation of the multinomial logit model is the default in CATMOD so the syntax is relatively simple. One thing to remember, however, is that CATMOD (by default) treats all variables as categorical. If you want to treat an explanatory variable as quantitative, you must put it in a DIRECT ...

Get Logistic Regression Using SAS®: Theory and Application now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.