A Comparison among generalized ridge regression parameter estimating with application on chronic renal insufficiency

Abstract

The regression model is a well-known model in several real applications. However, it is known that multicollinearity negatively affects the ordinary least squared estimator. To address this problem, a generalized ridge regression estimator has been proposed. The performance of this estimator is fully depending on the biasing parameter. In this paper, numerous selection methods of the biasing parameter are explored and investigated. Our real application results suggest that our proposed methods can bring significant improvement relative to others, in terms of mean squared error.