A COMPARISON OF PARTIAL LEAST SQUARES REGRESSION WITH OTHER PREDICTION METHODS

Authors : Özgür YENİAY, Atilla GÖKTAŞ

Pages : 99-111

View : 23 | Download : 9

Publication Date : 2001-12-01

Article Type : Research Paper

Abstract :The aim of this study is to compare popular regression methods with the partial least squares method. The paper presents a theoretical point of view, as well as an application on a real data set. It is found that partial least squares regression yields somewhat better results in terms of the predictive ability of models obtained when compared to the other prediction methods.
Keywords : Ordinary least squares, Ridge regression, Principal component regression, Partial least squares