Estimating Simultaneous Games with Incomplete Information Under Median Restrictions

17 Pages Posted: 9 Jul 2009

See all articles by Xun Tang

Xun Tang

Rice University - Department of Economics

Date Written: April 30, 2009

Abstract

I estimate a simultaneous discrete game with incomplete information where players' private information are only required to be median independent of observed states and can be correlated with observable states. This median restriction is weaker than other assumptions on players' private information in the literature (e.g. perfect knowledge of its distribution or its independence of the observable states). I show index coefficients in players' utility functions are point-identified under an exclusion restriction and fairly weak conditions on the support of states. This identification strategy is fundamentally different from that in a single-agent binary response models with median restrictions, and does not involve any parametric assumption on equilibrium selection in the presence of multiple Bayesian Nash equilibria. I then propose a two-step extreme estimator for the linear coefficients, and prove its consistency.

Keywords: Games with incomplete information, semiparametric identification, median restrictions, consistent estimation

JEL Classification: C14, C35, C51

Suggested Citation

Tang, Xun, Estimating Simultaneous Games with Incomplete Information Under Median Restrictions (April 30, 2009). PIER Working Paper No. 09-023, Available at SSRN: https://ssrn.com/abstract=1431493 or http://dx.doi.org/10.2139/ssrn.1431493

Xun Tang (Contact Author)

Rice University - Department of Economics ( email )

6100 South Main Street
Houston, TX 77005
United States