Identifying the Discount Factor in Dynamic Discrete Choice Models (with Øystein Daljord)

Abstract:
Empirical applications of stationary dynamic discrete choice models usually either take the discount factor to be known or rely on high level exclusion restrictions that are difficult to interpret and hard to satisfy. We provide identification results under an intuitively appealing exclusion restriction on primitive utilities that is more directly useful to applied researchers. We show that such an exclusion restriction, even with corresponding variation in future expected payoffs, does not suffice for point identification. It does however identify the discount factor up to a discrete set, with only finitely many points outside a neighborhood of one. Moreover, this identified set is easy to characterize by solving a simple moment condition. We also show that our and existing exclusion restrictions limit the choice and state transition probability data in different ways; that is, they give the model nontrivial and distinct empirical content.