Variable selection in model-based discriminant analysis

Cathy Maugis 1, * Gilles Celeux 2 Marie-Laure Martin-Magniette 3, 4
* Auteur correspondant
2 SELECT - Model selection in statistical learning
Inria Saclay - Ile de France, LMO - Laboratoire de Mathématiques d'Orsay, CNRS - Centre National de la Recherche Scientifique : UMR
Abstract : A general methodology for selecting predictors for Gaussian generative classification models is presented. The problem is regarded as a model selection problem. Three different roles for each possible predictor are considered: a variable can be a relevant classification predictor or not, and the irrelevant classification variables can be linearly dependent on a part of the relevant predictors or independent variables. This variable selection model was inspired by the model-based clustering model of Maugis, Celeux and Martin-Magniette (2009) in a previous work on variable selection in model-based clustering. A BIC-like model selection criterion is proposed. It is optimized through two embedded forward stepwise variable selection algorithms for classification and linear regression. The model identifiability and the consistency of the variable selection criterion are proved. Numerical experiments on simulated and real data sets illustrate the interest of this variable selection methodology. In particular, it is shown that this well ground variable selection model can be of great interest to improve the classification performance of the quadratic discriminant analysis in a high dimension context
Type de document :
Rapport
[Research Report] RR-7290, INRIA. 2010
Liste complète des métadonnées

Littérature citée [23 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00483229
Contributeur : Gilles Celeux <>
Soumis le : mercredi 12 mai 2010 - 18:50:24
Dernière modification le : mercredi 23 mai 2018 - 17:58:04
Document(s) archivé(s) le : jeudi 16 septembre 2010 - 14:42:19

Fichier

RR-7290.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : inria-00483229, version 1

Citation

Cathy Maugis, Gilles Celeux, Marie-Laure Martin-Magniette. Variable selection in model-based discriminant analysis. [Research Report] RR-7290, INRIA. 2010. 〈inria-00483229〉

Partager

Métriques

Consultations de la notice

624

Téléchargements de fichiers

1035