Dynamic discrete choice models are non-parametrically not identified without restrictions on payoff functions, yet counterfactuals may be identified even when payoffs are not. We provide necessary and sufficient conditions for the identification of a wide range of counterfactuals for models with nonparametric payoffs, as well as for commonly used parametric functions, and we obtain both positive and negative results. We show that access to extra data of asset resale prices (when applicable) can solve non-identifiability of both payoffs and counterfactuals. The theoretical findings are illustrated empirically in the context of agricultural land use. First, we provide identification results for models with unobserved market-level state variables. Then, using a unique spatial dataset of land use choices and land resale prices, we estimate the model and investigate two policy counterfactuals: long run land use elasticity (identified) and a fertilizer tax (not identified, affected dramatically by restrictions).
Identification; Dynamic Discrete Choice; Counterfactual; Land Use;
Myrto Kalouptsidi, Paul Scott, and Edouardo Souza-Rodrigues, “Identification of Counterfactuals and Payoffs in Dynamic Discrete Choice with an Application to Land Use”, TSE Working Paper, n. 15-596, August 2015.
TSE Working Paper, n. 15-596, August 2015