Asymptotic least squares estimators for dynamic games. Forthcoming Review of Economic Studies

This paper considers the estimation problem in dynamic games with \u85nite actions. We derive the equation system that characterizes the Markovian equi-libria. The equilibrium equation system enables us to characterize conditions for identi\u85cation. We consider a class of asymptotic least squares estimators de ned by the equilibrium conditions. This class provides a uni\u85ed framework for a number of well known estimators including Hotz and Miller (1993) and Aguirregabiria and Mira (2002). We show that these estimators di¤er in the weight they assign to individual equilibrium conditions. We derive the e ¢ cient weight matrix. A Monte Carlo study compares the \u85nite sample performance of alternative estimators. This paper supersedes our earlier NBER working paper entitled Identi\u85cation and Es-timation of Dynamic Games from May 2003. We thank the editor Bernard Salanié an