Difference based ridge and Liu type estimators in semiparametric regression models


Creative Commons License

AKDENİZ DURAN E., Haerdle W. K. , Osipenko M.

JOURNAL OF MULTIVARIATE ANALYSIS, vol.105, no.1, pp.164-175, 2012 (Peer-Reviewed Journal) identifier

  • Publication Type: Article / Article
  • Volume: 105 Issue: 1
  • Publication Date: 2012
  • Doi Number: 10.1016/j.jmva.2011.08.018
  • Journal Name: JOURNAL OF MULTIVARIATE ANALYSIS
  • Journal Indexes: Science Citation Index Expanded, Scopus
  • Page Numbers: pp.164-175

Abstract

We consider a difference based ridge regression estimator and a Liu type estimator of the regression parameters in the partial linear semiparametric regression model, y = X beta + f + epsilon . Both estimators are analyzed and compared in the sense of mean-squared error. We consider the case of independent errors with equal variance and give conditions under which the proposed estimators are superior to the unbiased difference based estimation technique. We extend the results to account for heteroscedasticity and autocovariance in the error terms. Finally, we illustrate the performance of these estimators with an application to the determinants of electricity consumption in Germany. (C) 2011 Elsevier Inc. All rights reserved.