Choosing Models in Model-based Clustering and Discriminant Analysis - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Reports Year : 1998

Choosing Models in Model-based Clustering and Discriminant Analysis

Gérard Govaert

Abstract

Using an eigenvalue decomposition of variance matrices, Celeux and Govaert (1993) obtained numerous and powerful models for Gaussian model-based clustering and discriminant analysis. Through Monte Carlo simulations, we compare the performances of many classical criteria to select these models: information criteria as AIC, the Bayesian criterion BIC, classification criteria as NEC and cross-validation. In the clustering context, information criteria and BIC outperform the classification criteria. In the discriminant analysis context, cross-validation shows good performance but information criteria and BIC give satisfactory results as well with, by far, less time-computing.
Fichier principal
Vignette du fichier
RR-3509.pdf (283.02 Ko) Télécharger le fichier

Dates and versions

inria-00073175 , version 1 (24-05-2006)

Identifiers

  • HAL Id : inria-00073175 , version 1

Cite

Christophe Biernacki, Gérard Govaert. Choosing Models in Model-based Clustering and Discriminant Analysis. RR-3509, INRIA. 1998. ⟨inria-00073175⟩
86 View
879 Download

Share

Gmail Facebook Twitter LinkedIn More