This code estimates the parameters of mixed logit models, also called random-parameters or error-components logit. This model is a generalization of standard logit that does not exhibit the restrictive "independence from irrelevant alternatives" property and explicitly accounts for correlations in unobserved utility over repeated choices by each customer. The user can introduce explanatory variables associated with fixed and/or random coefficients. For random coefficients (RC), the user can choose a specific distribution for each parameter. The code displays estimated fixed coefficients, the estimated parameters of the RC distribution, standard errors and sampling covariance matrix, and the log-likelihood at convergence.
Oxford Bulletin of Economics and Statistics (2022)
Matsuoka Hideaki