Consistent Model and Moment Selection Procedures for Gmm Estimation with Application to Dynamic Panel Data Models By

This paper develops consistent model and moment selection criteria for GMM estimation. The criteria select the correct model speci"cation and all correct moment conditions asymptotically. The selection criteria resemble the widely used likelihoodbased selection criteria BIC, HQIC, and AIC. (The latter is not consistent.) The GMM selection criteria are based on the J statistic for testing over-identifying restrictions. Bonus terms reward the use of fewer parameters for a given number of moment conditions and the use of more moment conditions for a given number of parameters. The paper also considers a consistent downward testing procedure. The paper applies the model and moment selection criteria to dynamic panel data models with unobserved individual e!ects. The paper shows how to apply the selection criteria to select the lag length for lagged dependent variables, to detect the number and locations of structural breaks, to determine the exogeneity of regressors, and/or to determine the existence of correlation between some regressors and the individual e!ect. To illustrate the "nite sample performance of the selection criteria and the testing procedures and their impact *Corresponding author. Fax: #1-203-432-6167. E-mail address: [email protected] (D.W.K. Andrews). 1The "rst version of this paper was done when the second author was studying at Department of Economics, Yale University. We thank two referees, Peter Phillips, Chris Sims, and seminar participants at Yale University and SUNY at Stony Brook for very helpful comments and suggestions. The "rst author gratefully acknowledges the research support of the National Science Foundation via grant numbers SBR-9410675 and SBR-9730277. 0304-4076/01/$ see front matter ( 2001 Elsevier Science S.A. All rights reserved. PII: S 0 3 0 4 4 0 7 6 ( 0 0 ) 0 0 0 7 7 4 on parameter estimation, the paper reports the results of a Monte Carlo experiment on a dynamic panel data model. ( 2001 Elsevier Science S.A. All rights reserved. JEL classixcation: C12; C13; C52