Multinomial logit models are used to model relationships between a polytomous response variable and
a set of regressor variables. The term “multinomial logit model” includes, in a broad sense, a variety
of models. The cumulative logit model is used when the response of an individual unit is restricted
to one of a finite number of ordinal values. Generalized logit and conditional logit models are used to
model consumer choices. This article focuses on the statistical techniques for analyzing discrete choice
data and discusses fitting these models using SAS/STAT software.
Introduction