The extended two-type parameter estimator in linear regression model

Abstract

In this article, a new two-type parameter estimator is introduced. This estimator is an extension of the two-parameter (TP) estimator presented by Özkale and Kaçiranlar (2007), which includes the ordinary least squares (OLS), the generalized ridge, and the generalized Liu estimators, as special cases. Here, the performance of this new estimator over the OLS and TP estimators is, theoretically, evaluated in terms of quadratic bias and mean squared error matrix criteria, and the optimal biasing parameters are obtained to minimize the scalar mean squared error (MSE). Then a numerical example is given and a simulation study is done to illustrate the theoretical results of the article.

Keywords:

• Generalized Liu estimator
• generalized ridge estimator
• Lagrange method
• mean squared error matrix
• two-parameter estimator