Affordable Access

Publisher Website

A further theoretical result for generalized ridge regression estimators

Authors
Journal
Economics Letters
0165-1765
Publisher
Elsevier
Publication Date
Volume
26
Issue
2
Identifiers
DOI: 10.1016/0165-1765(88)90028-6

Abstract

Abstract This paper derives a sufficient condition for the generalized ridge regression (GRR) estimator to be preferred to the ordinary least squares (OLS) estimator for all non-negative values of the biasing factors, when the performance of an estimator is measured by its mean squared error matrix. A test of this sufficient condition is outlined.

There are no comments yet on this publication. Be the first to share your thoughts.