The Cramer-Ridder test is a popular procedure for testing if some outcome states can be pooled into one state in the multinomial logit model. We show that, in the presence of binary regressors, the test is overly stringent and poolability may not be tested unambiguously.

The problem of unstable coecients in the rank-ordered logit model has been traditionally interpreted as a sign that survey respondents fail to provide reliable ranking responses. This paper shows that the problem may embody the inherent sensitivity of the model to stochastic misspecification...

Several empirical studies conclude that a majority of economic agents ignore some of observed product attributes when choosing among discrete alternatives. Many of these ndings are based on latent class logit with partially constrained support points wherein the share of each point is...

This paper describes lclogit, a Stata module for estimating a discrete mixture or latent class logit model via the EM algorithm.

We analyse stated preference data over nursing jobs collected from two leading types of best-worst discrete choice experiments (DCEs): a traditional DCE involving choice over alternative jobs (BWL) and a newly-developed DCE where respondents choose best and worst job attributes (BWT). The latter...