Estimating Dynamic Discrete Choice Models Via Convex Analysis

Using results from convex analysis, we characterize the identification and estimation of dynamic discrete-choice models based on the random utility framework. Based on these insights, we propose a new two-step estimator for these models, which is easily applicable to models in which the utility shocks may not derive from an extreme- value distribution, and may be mutually correlated with each other and with the state variables. Monte Carlo results demonstrate the good performance of this estimator, and we provide a short application using the dynamic bus engine replacement model in Rust (1987).