A jackknifed ridge estimator in the linear regression model with heteroscedastic or correlated errors


Oezkale M. R.

STATISTICS & PROBABILITY LETTERS, vol.78, no.18, pp.3159-3169, 2008 (Journal Indexed in SCI) identifier identifier

  • Publication Type: Article / Article
  • Volume: 78 Issue: 18
  • Publication Date: 2008
  • Doi Number: 10.1016/j.spl.2008.05.039
  • Title of Journal : STATISTICS & PROBABILITY LETTERS
  • Page Numbers: pp.3159-3169

Abstract

Trenkler [Trenkler, G., 1984. On the performance of biased estimators in the linear regression model with correlated or heteroscedastic errors. journal of Econometrics 25, 179-190] proposed a ridge estimator in the linear regression model when the assumption of homoscedasticity and/or Uncorrelatedness is not satisfied. In this paper, a new estimator is introduced by jackknifing the ridge estimator which Trenkler proposed, as referred to above. The performance of this new estimator over the ridge and generalized least squares estimators in terms of matrix and scalar mean square error criteria are investigated and a simulation Study is done. (C) 2008 Elsevier B.V. All rights reserved.