GMM estimators with improved finite sample properties using principal components of the weighting matrix, with an application to the dynamic panel data model

Doran, Howard, E. and Schmidt, Peter (2006) GMM estimators with improved finite sample properties using principal components of the weighting matrix, with an application to the dynamic panel data model. Journal of Econometrics, 133 1: 387-409. doi:10.1016/j.jeconom.2004.11.004

Attached Files (Some files may be inaccessible until you login with your UQ eSpace credentials)
Name Description MIMEType Size Downloads

Author Doran, Howard, E.
Schmidt, Peter
Title GMM estimators with improved finite sample properties using principal components of the weighting matrix, with an application to the dynamic panel data model
Journal name Journal of Econometrics   Check publisher's open access policy
ISSN 0304-4076
1872-6895
Publication date 2006
Sub-type Article (original research)
DOI 10.1016/j.jeconom.2004.11.004
Volume 133
Issue 1
Start page 387
End page 409
Total pages 23
Editor A. R. Gallant
J. F. Geweke
Place of publication Amsterdam, Netherlands
Publisher Elsevier
Language eng
Subject 140302 Econometric and Statistical Methods
Abstract GMM estimators have poor finite sample properties in highly overidentified models. With many moment conditions the optimal weighting matrix is poorly estimated. We suggest using principal components of the weighting matrix. This effectively drops some of the moment conditions. Our simulations, done in the context of the dynamic panel data model, show that the resulting GMM estimator has better finite sample properties than the usual two-step GMM estimator, in the sense of smaller bias and more reliable standard errors.
Keyword GMM
Generalized method of moments
Principal components
Dynamic panel data model
Q-Index Code C1

Document type: Journal Article
Sub-type: Article (original research)
Collections: Excellence in Research Australia (ERA) - Collection
School of Economics Publications
 
Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 11 times in Thomson Reuters Web of Science Article | Citations
Scopus Citation Count Cited 15 times in Scopus Article | Citations
Google Scholar Search Google Scholar
Created: Thu, 19 Mar 2009, 12:22:16 EST by Ms Julie Schofield on behalf of Faculty of Business, Economics & Law