Semiparametric Bayesian Estimation of Dynamic Discrete Choice Models

TL;DR

This paper introduces a flexible semiparametric Bayesian estimation method for dynamic discrete choice models, addressing limitations of traditional models by modeling utility shocks with mixtures of extreme value distributions.

Contribution

It develops a novel semiparametric approach using location-scale mixtures and Bayesian inference techniques, improving reliability over standard models in non-extreme value shock scenarios.

Findings

Standard dynamic logit models can be misleading with non-extreme value shocks.

The proposed method provides more reliable inference in such cases.

Theoretical results support the approximation and posterior concentration of the model.

Abstract

We propose a tractable semiparametric estimation method for structural dynamic discrete choice models. The distribution of additive utility shocks in the proposed framework is modeled by location-scale mixtures of extreme value distributions with varying numbers of mixture components. Our approach exploits the analytical tractability of extreme value distributions in the multinomial choice settings and the flexibility of the location-scale mixtures. We implement the Bayesian approach to inference using Hamiltonian Monte Carlo and an approximately optimal reversible jump algorithm. In our simulation experiments, we show that the standard dynamic logit model can deliver misleading results, especially about counterfactuals, when the shocks are not extreme value distributed. Our semiparametric approach delivers reliable inference in these settings. We develop theoretical results on approximations by location-scale mixtures in an appropriate distance and posterior concentration of the set identified utility parameters and the distribution of shocks in the model.