Choosing models in model-based clustering and discriminant analysis
- 1 August 1999
- journal article
- research article
- Published by Taylor & Francis in Journal of Statistical Computation and Simulation
- Vol. 64 (1) , 49-71
- https://doi.org/10.1080/00949659908811966
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.Keywords
This publication has 17 references indexed in Scilit:
- Regularized Gaussian Discriminant Analysis Through Eigenvalue DecompositionJournal of the American Statistical Association, 1996
- An entropy criterion for assessing the number of clusters in a mixture modelJournal of Classification, 1996
- Bayes FactorsJournal of the American Statistical Association, 1995
- Gaussian parsimonious clustering modelsPattern Recognition, 1995
- Error rates in quadratic discrimination with constraints on the covariance matricesJournal of Classification, 1994
- Information-Based Validity Functionals for Mixture AnalysisPublished by Springer Nature ,1994
- Model-Based Gaussian and Non-Gaussian ClusteringPublished by JSTOR ,1993
- On the information-based measure of covariance complexity and its application to the evaluation of multivariate linear modelsCommunications in Statistics - Theory and Methods, 1990
- Another interpretation of the EM algorithm for mixture distributionsStatistics & Probability Letters, 1986
- A new look at the statistical model identificationIEEE Transactions on Automatic Control, 1974