Conditional Choice Probability Estimation of Dynamic Discrete Choice Models with 2-Period Finite Dependence

Yu Hao is an Assistant Professor at the Faculty of Business and Economics, University of Hong Kong. Her research focuses on industrial organization and structural econometrics, with interests in dynamic games, demand estimation, and firm strategy identification. She specializes in theoretical and empirical analysis of dynamic discrete choice models, studying how discount factor identification and market policy interventions—such as advertising bans—affect firm behavior and market efficiency.

This paper introduces a novel approach for characterizing and handling finite dependence in dynamic discrete choice models. Building on the framework of Arcidiacono and Miller (2011, 2019), the paper demonstrates that a wide range of models possess 2-period finite dependence, and recasts the identification of finite dependence as a sequential search for decision weights. The talk presents a computationally efficient method to determine these weights using the Kronecker product structure found in state transitions. Leveraging these weights, the proposed Conditional Choice Probability estimator allows for practical and scalable estimation in models exhibiting 2-period finite dependence. The computational efficiency of this estimator is illustrated through Monte Carlo simulations, making it highly relevant for researchers working with high-dimensional dynamic economic models.