Automatic Lag Selection in Covariance Matrix Estimation

   (1281 K)

We propose a nonparametric method for automatically selecting the number of autocovariances to use in computing a heteroskedasticity and autocorrelation consistent covariance matrix. For a given kernel for weighting the autocovariances, we prove that our procedure is asymptotically equivalent to one that is optimal under a mean squared error loss function. Monte Carlo simulations suggest that our procedure performs tolerably well, although it does result in size distortions.

Published:

• Review of Economic Studies, 1994, 61, pp 631-653 ,
• "A Comparison of Alternative Instrumental Variables Estimators of a Dynamic Linear Model," (with David Wilcox) Journal of Business and Economic Statistics 14 (1996), pp. 281-293.

This paper is available as PDF (1281 K) or via email.

Machine-readable bibliographic record - MARC, RIS, BibTeX