Bayesian and maximum likelihood analysis of large-scale panel choice models with unobserved heterogeneity

This paper considers the estimation and inference procedures for case of a logistic panel regression model with interactive fixed effects, where multiple individual effects are allowed is capable capturing high-dimensional cross-section dependence. The proposed also allows heterogeneous coefficients. New Bayesian non-Bayesian approaches introduced to estimate parameters. We investigate asymptotic behaviors estimated show consistency normality coefficients when both time-series dimensions go infinity. prove that dimensionality can be consistently by information criterion. Monte Carlo simulations demonstrate satisfactory performance method. Finally, method applied study York City medallion drivers in terms efficiency.