Fitting mixed logit random regret minimization models using maximum simulated likelihood

TL;DR

This paper introduces the mixrandregret command, enabling the estimation of mixed logit Random Regret Minimization models with random coefficients using simulated maximum likelihood, enhancing modeling flexibility.

Contribution

The paper presents a new command that extends existing RRM models by incorporating random coefficients and allowing flexible distribution specifications.

Findings

Enables inclusion of random coefficients in RRM models.

Uses simulated maximum likelihood for model estimation.

Supports normal and log-normal distributions for random coefficients.

Abstract

This article describes the mixrandregret command, which extends the randregret command introduced in Guti\'errez-Vargas et al. (2021, The Stata Journal 21: 626-658) incorporating random coefficients for Random Regret Minimization models. The newly developed command mixrandregret allows the inclusion of random coefficients in the regret function of the classical RRM model introduced in Chorus (2010, European Journal of Transport and Infrastructure Research 10: 181-196). The command allows the user to specify a combination of fixed and random coefficients. In addition, the user can specify normal and log-normal distributions for the random coefficients using the commands' options. The models are fitted using simulated maximum likelihood using numerical integration to approximate the choice probabilities.