Revisiting The Solution Of Dynamic Discrete Choice Models PDF Download

This paper provides a method for estimating large-scale dynamic discrete choice models within a continuous time framework. An advantage of our model is that state changes occur sequentially, rather than simultaneously, avoiding a substantial curse of dimensionality that arises in multi-agent settings. Eliminating this computational bottleneck is the key to providing a seamless link between estimating the model and performing post-estimation counterfactuals. While recently developed two-step estimation techniques have made it possible to estimate large-scale problems, solving for equilibria remains computationally challenging. By modeling decisions in continuous time, we are able to take advantage of the recent advances in estimation while preserving a tight link between estimation and policy experiments. We address the most commonly encountered situation in empirical work in which only discrete-time data are available and the actual sequence of events that occur between two points in time is unobserved. We apply our techniques to examine the effects of Walmart's entry into the retail grocery industry, showing that even the threat of entry by Walmart has a substantial effect on market structure.