RESEARCH ARTICLE


An Unusual Preferences Among Regression Designs



Krystyna Maciag*
Department of Statistics and Econometrics, Maria Curie-Sk􀀁odowska University, Pl. Marii Curie-Sk􀀁odowskiej 5, 20-031 Lublin, Poland.


© 2009 Maciag et al.;

open-access license: This is an open access article distributed under the terms of the Creative Commons Attribution 4.0 International Public License (CC-BY 4.0), a copy of which is available at: https://creativecommons.org/licenses/by/4.0/legalcode. This license permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

* Address correspondence to this author at the Department of Statistics and Econometrics, Maria Curie-Sk􀀁odowska University, Pl. Marii Curie-Sk􀀁odowskiej 5, 20-031 Lublin, Poland. E-mail: maciag@hektor.umcs.lublin.pl


Abstract

Consider the classical regression design with one explanatory variable taking values x = (x1 ,…, xn)' and an alternative design based on Tx, where T = In - 1/n 1n 1'n. We reveal an interesting phenomenon that the second design is better, from many reasonable points of view, than the initial one.

Keywords: Linear regression, one explanatory variable, variable transformation, design preference.