Events

Prof. Katsumi Shimotsu
Professor,
University of Tokyo

We study the identification of the discount factor and payoff function in standard stationary infinite-horizon dynamic discrete choice models. In single-agent models with an exclusion restriction, we show that the discount factor is identified up to a finite set, with its cardinality bounded by that of the state space. We demonstrate that commonly imposed nonparametric assumptions on per-period payoffs – such as homogeneity, monotonicity, concavity, and zero cross-differences – provide identifying restrictions on the discount factor through equality and inequality constraints. In dynamic game models, we show that standard nonparametric assumptions – such as irrelevance of other firms’ lagged actions, exchangeability of other firms’ actions, and independence of entry cost from other firms’ actions – enable identification of the firm-specific discount factors. Our results highlight how commonly used nonparametric and semiparametric modeling assumptions in economic analysis help identify the discount factor and payoff functions.