r-d Class Estimator Under Misspecification


Siray G.

COMMUNICATIONS IN STATISTICS-THEORY AND METHODS, vol.44, no.22, pp.4742-4756, 2015 (Peer-Reviewed Journal) identifier identifier

  • Publication Type: Article / Article
  • Volume: 44 Issue: 22
  • Publication Date: 2015
  • Doi Number: 10.1080/03610926.2013.835421
  • Journal Name: COMMUNICATIONS IN STATISTICS-THEORY AND METHODS
  • Journal Indexes: Science Citation Index Expanded, Scopus
  • Page Numbers: pp.4742-4756

Abstract

Omission of some relevant explanatory variables and multicollinearity in regression models are very serious problems in applied works. There are some papers examining the multicollinearity and misspecification which is due to omission of some relevant explanatory variables, concurrently. To remedy the problem of multicollinearity, Kacranlar and Sakallolu (2001) proposed the r-d class estimator that includes the ordinary least squares, principal components regression, and Liu estimators as special cases. The aim of this paper is to examine the performance of the r-d class estimator in misspecificied linear models.