Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network

  Advanced Search  

Discriminant Correspondence Herv Abdi1

Summary: Discriminant Correspondence
Hervé Abdi1
1 Overview
As the name indicates, discriminant correspondence analysis (DCA)
is an extension of discriminant analysis (DA) and correspondence
analysis (CA). Like discriminant analysis, the goal of DCA is to cat-
egorize observations in pre-defined groups, and like correspon-
dence analysis, it is used with nominal variables.
The main idea behind DCA is to represent each group by the
sum of its observations and to perform a simple CA on the groups
by variables matrix. The original observations are then projected
as supplementary elements and each observation is assigned to
the closest group. The comparison between the a priori and the
a posteriori classifications can be used to assess the quality of the
discrimination. A similar procedure can be used to assign new ob-
servations to categories. The stability of the analysis can be evalu-
ated using cross-validation techniques such as jackknifing or boot-


Source: Abdi, Hervé - School of Behavioral and Brain Sciences, University of Texas at Dallas


Collections: Biology and Medicine; Computer Technologies and Information Sciences