A New Estimation Approach to Integrate Latent Psychological Constructs in Choice Modeling

摘要

In the current paper, we propose a new multinomial probit-based model formulation for integrated choice and latent variable (ICLV) models, which, as we show in the paper, has several important advantages relative to the traditional logit kernel-based ICLV formulation. The time for convergence in our new ICLV formulation and estimation procedure is of the order of 30 minutes to 80 minutes for sample sizes ranging from 500 observations to 2000 observations, in contrast to much longer times for convergence experienced in traditional ICLV model estimations (that is, if convergence is achieved at all in these estimations).