Choosing the number of clusters in a finite mixture model using an exact integrated completed likelihood criterion
From MaRDI portal
Publication:497086
DOI10.1007/S40300-015-0064-5zbMATH Open1329.62277arXiv1411.4257OpenAlexW1652114617MaRDI QIDQ497086FDOQ497086
Authors: Marco Bertoletti, Riccardo Rastelli, Nial Friel 
Publication date: 23 September 2015
Published in: Metron (Search for Journal in Brave)
Abstract: The integrated completed likelihood (ICL) criterion has proven to be a very popular approach in model-based clustering through automatically choosing the number of clusters in a mixture model. This approach effectively maximises the complete data likelihood, thereby including the allocation of observations to clusters in the model selection criterion. However for practical implementation one needs to introduce an approximation in order to estimate the ICL. Our contribution here is to illustrate that through the use of conjugate priors one can derive an exact expression for ICL and so avoiding any approximation. Moreover, we illustrate how one can find both the number of clusters and the best allocation of observations in one algorithmic framework. The performance of our algorithm is presented on several simulated and real examples.
Full work available at URL: https://arxiv.org/abs/1411.4257
Recommendations
- Estimation and model selection for model-based clustering with the conditional classification likelihood
- Order selection in finite mixture models: complete or observed likelihood information criteria?
- Variable selection for model-based clustering using the integrated complete-data likelihood
- An entropy criterion for assessing the number of clusters in a mixture model
- How Many Clusters? Which Clustering Method? Answers Via Model-Based Cluster Analysis
Cites Work
- Model-Based Clustering, Discriminant Analysis, and Density Estimation
- Model selection and clustering in stochastic block models based on the exact integrated complete data likelihood
- Reversible jump Markov chain Monte Carlo computation and Bayesian model determination
- Markov chain Monte Carlo methods and the label switching problem in Bayesian mixture modeling
- Title not available (Why is that?)
- Block clustering with collapsed latent block models
- Exact and Monte Carlo calculations of integrated likelihoods for the latent class model
- Improved Bayesian inference for the stochastic block model with application to large networks
- Title not available (Why is that?)
- Density Estimation With Confidence Sets Exemplified by Superclusters and Voids in the Galaxies
- An invariant form for the prior probability in estimation problems
- Finite mixture models and model-based clustering
- Mixtures
Cited In (8)
- Estimation and model selection for model-based clustering with the conditional classification likelihood
- Hierarchical clustering with discrete latent variable models and the integrated classification likelihood
- The sensitivity of the number of clusters in a Gaussian mixture model to prior distributions
- Comparing classical criteria for selecting intra-class correlated features in Multimix
- Variable selection for model-based clustering using the integrated complete-data likelihood
- Finding the Number of Normal Groups in Model-Based Clustering via Constrained Likelihoods
- Latent variable models for the analysis of socio-economic data
- Optimal Bayesian estimators for latent variable cluster models
Uses Software
This page was built for publication: Choosing the number of clusters in a finite mixture model using an exact integrated completed likelihood criterion
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q497086)
