Feature Selection on Supervised Classification Using Wilks Lambda Statistic
Abdeljalil El Ouardighi, Ali El Akadi, Driss Aboutajdine · 2007
Variable and feature selection have become the focus of much research in areas of application for which datasets with tens or hundreds of thousands of variables are available. This paper addresses the feature selection problem for supervised classification. We operate this feature selection step by step, which leads to search for a criterion to quantify the most relevant variable and its contribution compared to the others already selected. In this article we present a feature selection method based on the Wilk's lambda criterion which is a statistical one used in discriminant analysis. Our objective is to evaluate the performances of this method when used in another application different from its classical one i.e. the discriminant analysis. This criterion is compared to other very known algorithms in the field of the feature selection on various real data sets. The obtained results with the criterion of Wilk's lambda are satisfactory and even better in some cases.