A tractable Multi-Partitions Clustering

Marbac, Matthieu; Vandewalle, Vincent

Type de document :

Compte-rendu et recension critique d'ouvrage

DOI :

10.1016/j.csda.2018.06.013

Titre :

A tractable Multi-Partitions Clustering

Auteur(s) :

Marbac, Matthieu [Auteur]
Centre de Recherche en Economie et Statistique [Bruz] [CREST]
Ecole Nationale de la Statistique et de l'Analyse de l'Information [Bruz] [ENSAI]
Vandewalle, Vincent [Auteur]

MOdel for Data Analysis and Learning [MODAL]
Evaluation des technologies de santé et des pratiques médicales - ULR 2694 [METRICS]

Titre de la revue :

Computational Statistics and Data Analysis

Éditeur :

Elsevier

Date de publication :

2018-07-03

ISSN :

0167-9473

Mot(s)-clé(s) en anglais :

Variables selection
Mixed-data
Model choice
Mixture model
Model-based clustering

Discipline(s) HAL :

Statistiques [stat]/Méthodologie [stat.ME]

Résumé en anglais : [en]

In the framework of model-based clustering, a model allowing several latent class variables is proposed. This model assumes that the distribution of the observed data can be factorized into several independent blocks of ...
Lire la suite >In the framework of model-based clustering, a model allowing several latent class variables is proposed. This model assumes that the distribution of the observed data can be factorized into several independent blocks of variables. Each block is assumed to follow a latent class model ({\it i.e.,} mixture with conditional independence assumption). The proposed model includes variable selection, as a special case, and is able to cope with the mixed-data setting. The simplicity of the model allows to estimate the repartition of the variables into blocks and the mixture parameters simultaneously, thus avoiding to run EM algorithms for each possible repartition of variables into blocks. For the proposed method, a model is defined by the number of blocks, the number of clusters inside each block and the repartition of variables into block. Model selection can be done with two information criteria, the BIC and the MICL, for which an efficient optimization is proposed. The performances of the model are investigated on simulated and real data. It is shown that the proposed method gives a rich interpretation of the dataset at hand ({\it i.e.,} analysis of the repartition of the variables into blocks and analysis of the clusters produced by each block of variables).Lire moins >

Langue :

Anglais

Vulgarisation :

Non

Collections :

Laboratoire Paul Painlevé - UMR 8524

Source :

Harvested from HAL

Fichiers

1801.07063
Accès libre
Accéder au document

A tractable Multi-Partitions Clustering BibTeX CSV Excel RIS

Fichiers

A tractable Multi-Partitions Clustering

BibTeX

CSV

Excel

RIS