Skip to Main content Skip to Navigation

Estimation and Selection for the Latent Block Model on Categorical Data

Abstract : This paper is dealing with estimation and model selection in the Latent Block Model (LBM) for categorical data. First, after providing sufficient conditions ensuring the identifiability of this model, it generalises estimation procedures and model selection criteria derived for binary data. Secondly, it develops Bayesian inference through Gibbs sampling. And, with a well calibrated non informative prior distribution, Bayesian estimation is proved to avoid the traps encountered by the LBM with the maximum likelihood methodology. Then model selection criteria are presented. In particular an exact expression of the ICL criterion requiring no asymptotic approximation is derived. Finally numerical experiments on both simulated and real data sets highlight the interest of the proposed estimation and model selection procedures.
Complete list of metadata

Cited literature [35 references]  Display  Hide  Download
Contributor : Vincent Brault Connect in order to contact the contributor
Submitted on : Tuesday, February 18, 2014 - 6:31:11 PM
Last modification on : Sunday, June 26, 2022 - 12:00:52 PM
Long-term archiving on: : Sunday, April 9, 2017 - 1:33:53 PM


Files produced by the author(s)


  • HAL Id : hal-00802764, version 2


Christine Keribin, Vincent Brault, Gilles Celeux, Gérard Govaert. Estimation and Selection for the Latent Block Model on Categorical Data. [Research Report] RR-8264, INRIA. 2013, pp.30. ⟨hal-00802764v2⟩



Record views


Files downloads