MIXMOD : a software for model-based classification with continuous and categorical dataReportar como inadecuado

MIXMOD : a software for model-based classification with continuous and categorical data - Descarga este documento en PDF. Documentación en PDF para descargar gratis. Disponible también para leer online.

1 LPP - Laboratoire Paul Painlevé 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 3 Heudiasyc - Heuristique et Diagnostic des Systèmes Complexes Compiègne 4 LMB - Laboratoire de Mathématiques de Besançon

Abstract : The MIXMOD MIXture MODeling program fits mixture models to a given data set for the purposes of density estimation, clustering or discriminant analysis. A large variety of algorithms to estimate the mixture parameters are proposed EM, Classification EM, Stochastic EM, and it is possible to combine these to yield different strategies for obtaining a sensible maximum for the likelihood or complete-data likelihood function. MIXMOD is currently intended to be used for multivariate Gaussian mixtures and also for latent class models, respectively devoted to continuous and categorical data. In both situations, numerous meaninful and parsimonious models are proposed. Moreover, different information criteria for choosing a parsimonious model the number of mixture com- ponents, for instance are included, their suitability depending on the particular perspective cluster analysis or discriminant analysis. Written in C++, MIXMOD is interfaced with S CILAB and M ATLAB. The program, the statistical documentation and the user guide are available on the internet at the following address: http:-www-math.univ-fcomte.fr-mixmod-index.php

Autor: Christophe Biernacki - Gilles Celeux - Gérard Govaert - Florent Langrognet -

Fuente: https://hal.archives-ouvertes.fr/


Documentos relacionados