No abstract

This paper introduces new forms, sampling and estimation approaches for discrete choice models. The new models include behavioral specifications of latent class choice models, multinomial probit, hybrid logit, and non-parametric methods. Recent contributions also include new specialized choice based sample designs that permit greater efficiency in data collection. Finally, the paper describes recent developments in the use of simulation methods for model estimation. These developments are designed to allow the applications of discrete choice models to a wider variety of discrete choice problems.