Stein-rule restricted regression estimator in a linear regression model with nonspherical disturbances

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journal

5 Scopus Citations
View graph of relations

Author(s)

Related Research Unit(s)

Detail(s)

Original languageEnglish
Pages (from-to)55-68
Journal / PublicationCommunications in Statistics - Theory and Methods
Volume30
Issue number1
Publication statusPublished - Jan 2001

Abstract

In the present paper, we propose a Stein-rule estimator for the general linear regression model with nonspherical disturbances and a set of linear restrictions binding the regression coefficients. The asymptotic risk properties of the proposed estimator under a quadratic loss structure are derived, and a sufficient condition for the proposed estimator to dominate the feasible generalized restricted least squares estimator in large samples is presented. The small sample behavior of the proposed estimator is studied via a Monte-Carlo experiment. Copyright © 2001 by Marcel Dekker, Inc.

Research Area(s)

  • Generalized inverse, Large sample asymptotic, Monte-Carlo experiments, Quadratic loss, Restrictions