Compositional data are commonly present in many disciplines. Nevertheless, it is often improperly incorporated into statistical modelling and a misleading interpretation of the results is given. This paper explains how partial least squares for discrimination is an adequate technique for compositional data when a dimensional reduction of original variables is needed and difining the variables that more influence the discrimination between the observations is the goal.
Aitchison J (1982) The statistical analysis of compositional data (with discussion) . Statistical Methodology, 44, 139–77 .
2.
Aitchison J (1986) The statistical analysis of compositional data. London: Chapman & Hall .
3.
Aitchison J (1992) On criteria for measures of compositional difference . Mathematical Geology, 22, 223–26 .
4.
Aitchison J and Greenacre M (2002) Biplots for compositional data . Applied Statistics, 51, 375–92 .
5.
Barceló-Vidal C , Martín-Fernández JA and Pawlowsky-Glahn V (2001) Mathematical foundations of compositional data analysis. In Ross G ed. Proceedings of IAMG’01— the sixth annual conference of the International Association for Mathematical Geology. Electronic publication .
6.
Barker M and Rayens W (2003) Partial least squares for discrimination . Journal of Chemometrics, 17, 166–73 .
7.
Baxter MJ (1995) Standardization and transformation in principal component analysis, with applications to archaeometry . Applied Statistics, 44, 513–27 .
8.
de Jong S (1993) SIMPLS: an alternative approach to partial least squares regression . Chemometrics and Intelligent Laboratory Systems, 33, 251–63 .
9.
de Jong S and ter Braak CJF (1994) Comments on the PLS kernel algorithm . Journal of Chemometrics, 22, 169–74 .
10.
Frank I and Friedman J (1993) A statistical views of some chemometrics regression tools . Technometrics, 35, 109–48 .
11.
Gallo M (2003) Partial least squares for compositional data: an approach based on the splines . Italian Journal of Applied Statistics, 15, 349–58 .
12.
Gallo M and Mahdi S (2008). Discriminant partial least square on compositional data: a comparison with the log-contrast principal component analysis. Proceedings of MTISD 2008. Methods, Models and Information Technologies for Decision Support Systems ( Ciavolini , et al.eds) LECCE, SIBA , pp. 45–48.
13.
Hinkle J and Rayens W (1995) Partial least squares and compositional data: problems and alternatives . Chemometrics and Intelligent Laboratory Systems, 30, 159–72 .
14.
Martin-Fernandez JA , Barcelo-Vidal C and Pawlowsky-Glahn V (1998) Measures of difference for compositional data and hierarchical clustering. Proceedings of IAMG’98 ( Bucånti,G.Nardi , and R. Potenza eds). Napoli Italy: De Frede Editore , 526–31.
15.
Mooijaart A , Van Der Heijden PGM and Van Der Ark LA (1999) A least squares algorithm for a mixture model for compositional data . Computational Statistics and Data Analysis, 30, 359–79 .
16.
Rayens W (2000) The art of maximizing covariance. University of Kentucky Technical Report 383.
17.
Tenenhaus M (1998) La régression PLS. Théorie et pratique. Paris: Editions Technip .
18.
Wold H (1966) Estimation of principal components and related models by iterative least squares. In PR Krishnaiaah ed. Multivariate analysis. New York: Academic Press , 391–420.
19.
Wold H (1975) Soft modelling by latent variables: the nonlinear iterative partial least squares (NIPALS) approach. In Honor of M. S. Bartlett—( Gani ed.) Perspectives in Probability and Statistics. London: Academic Press , 117–44.
