This paper derives limit distributions of empirical likelihood estimators for models in which inequality moment conditions provide overidentifying information. We show that the use of this information leads to a reduction of the asymptotic mean-squared estimation error and propose asymptotically uniformly valid tests and confidence sets for the parameters of interest. While inequality moment conditions arise in many important economic models, we use a dynamic macroeconomic model as a data generating process and illustrate our methods with instrumental variable estimators of monetary policy rules. The results obtained in this paper extend to conventional GMM estimators.
Bibliographical noteFunding Information:
An earlier version of this paper was circulated under the title “Empirical Likelihood Estimation with Inequality Moment Constraints”. We thank Ron Gallant (co-editor), two anonymous referees, Sungbae An, Donald Andrews, Jinyong Hahn, Shakeeb Khan, Yuichi Kitamura, Masao Ogaki, Nick Souleles, and seminar participants at the 2003 Econometrics Society Winter Meetings, the 2006 European Econometrics Society Meetings, Columbia University, the Federal Reserve Bank of Atlanta, London School of Economics, Michigan State University, New York University, Penn State University, Princeton University, UC Irvine, UC Riverside, UT Austin, Texas A&M, and the universities of Chicago, Montreal, Pennsylvania, and Virginia for helpful comments. Moon gratefully acknowledges financial support from the USC Faculty Development Award. Schorfheide gratefully acknowledges financial support from the Alfred P. Sloan Foundation. GAUSS programs that implement the Monte Carlo simulation are available at http://www.ssc.upenn.edu/~schorf .
All Science Journal Classification (ASJC) codes
- Economics and Econometrics