Discriminant Partial Least Square on Compositional Data: a Comparison with the Log-Contrast Principal Component Analysis

Gallo, Michele and Mahdi, Smail (2008) Discriminant Partial Least Square on Compositional Data: a Comparison with the Log-Contrast Principal Component Analysis. In: MTISD 2008. Methods, Models and Information Technologies for Decision Support Systems, 18-20 settembre 2008, Lecce.

PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
207Kb

Official URL: http://siba-ese.unisalento.it/index.php/MTISD2008/issue/current

Abstract

Discriminant Partial Least Squares for Compositional data (DPLS-CO) was recently proposed by Gallo (2008). The aim of this paper is to show that DPLS-CO is a better dimensionality reduction technique than the LogContrats Principal Component Analysis (LCPCA) for dimensional reduction aimed at discrimination when a compositional training dataset is available.

Item Type:Conference or Workshop Item (Paper)
Uncontrolled Keywords:Compositional observation, Dimension reduction, Linear discrimination.
Subjects:AREA 13 - Scienze economiche e statistiche > STATISTICA
ID Code:694
Deposited By:Prof. Michele Gallo
Deposited On:19 Aug 2011 09:44
Last Modified:19 Aug 2011 09:44

Repository Staff Only: item control page