Choosing the number of clusters in a finite mixture model using an exact integrated completed likelihood criterion

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.

• Publication year

  2014

• Venue

  Metron

• Publication date

  2014-11-16

• Fields of study

  Mathematics, Computer Science

• Identifiers
  DOI 10.1007/s40300-015-0064-5arXiv 1411.4257
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Inferring structure in bipartite networks using the latent blockmodel and exact ICL

  2014influential reference
• Model selection and clustering in stochastic block models with the exact integrated complete data likelihood

  2013cited by this paper
• Bayesian model selection for the latent position cluster model for social networks

  2013cited by this paper
• Model-based clustering in networks with Stochastic Community Finding

  2012cited by this paper
• Mixtures: Estimation and Applications

  2011cited by this paper
• Block clustering with collapsed latent block models

  2010cited by this paper
• Combining Mixture Components for Clustering

  2010cited by this paper
• Exact and Monte Carlo calculations of integrated likelihoods for the latent class model

  2010cited by this paper
• Fast unfolding of communities in large networks

  2008cited by this paper
• Bayesian finite mixtures with an unknown number of components: The allocation sampler

  2007cited by this paper
• MCLUST Version 3: An R Package for Normal Mixture Modeling and Model-Based Clustering

  2006influential reference
• Evolutionary Latent Class Clustering of Qualitative Data

  2006cited by this paper
• Markov Chain Monte Carlo Methods and the Label Switching Problem in Bayesian Mixture Modeling

  2005cited by this paper
• An attempt to define the nature of chemical diabetes using a multidimensional analysis

  2004cited by this paper
• Fast algorithm for detecting community structure in networks.

  2003cited by this paper
• Model-Based Clustering, Discriminant Analysis, and Density Estimation

  2002cited by this paper
• Likelihood and Bayesian analysis of mixtures

  2001influential reference
• Assessing a Mixture Model for Clustering with the Integrated Completed Likelihood

  2000cited by this paper
• Assessing a Mixture Model for Clustering with the Integrated Classification Likelihood

  1998influential reference
• How Many Clusters? Which Clustering Method? Answers Via Model-Based Cluster Analysis

  1998cited by this paper
• Reversible jump Markov chain Monte Carlo computation and Bayesian model determination

  1995cited by this paper
• Density estimation with confidence sets exemplified by superclusters and voids in the galaxies

  1990cited by this paper
• On the Statistical Analysis of Dirty Pictures

  1986cited by this paper
• An invariant form for the prior probability in estimation problems

  1946cited by this paper
• Computational Statistics and Data Analysis

  year unknowncited by this paper

• Smart Planning of PV and Battery Systems under Uncertain Demand and Generation: A Data-Driven Robust Optimization Approach

  2026cites this paper
• Exploring and explaining changes in secondary students’ well-being at school: a person-centered approach by applying latent transition analysis

  2026cites this paper
• Characterization and clustering of intra-day physical activity patterns using accelerometry among sexual and gender minority adults

  2025cites this paper
• k -spaces: Mixtures of Gaussian latent variable models

  2025cites this paper
• Comprehensive dietary patterns explain acquired cystic kidney disease risk through genetic and metabolomic mechanisms

  2025cites this paper
• Extending finite mixture models with skew-normal distributions and hidden Markov models for time series

  2025influential citation
• Clustering Patterns of 24-Hour Physical Activity in Children 6-36 Months Old.

  2024cites this paper
• Investigating risk profiles of smartphone activities and psychosocial factors in adolescents during the COVID‐19 pandemic

  2024cites this paper
• Identifying subgroups of individuals based on their epistemic stance, attachment dimensions and childhood trauma: A latent profile analysis.

  2024cites this paper
• Bayesian clustering of spatially distributed compositional data with application to the Great Barrier Reef

  2024cites this paper
• Barriers of the CNS transfer rate dynamics in patients with vascular cognitive impairment and dementia

  2024cites this paper
• Model Based Clustering for Regency/City Grouping Based on Community Welfare Indicators in North Sumatra

  2024cites this paper
• A Bayesian approach for clustering and exact finite-sample model selection in longitudinal data mixtures

  2024cites this paper
• Profile identification and characterization of risk perceptions and preventive behaviors during the COVID-19 pandemic: A latent profile analysis

  2023cites this paper
• The Imbalance of Wanting and Liking Contributes to a Bias of Internal Attention Towards Positive Consequences of Tobacco Smoking

  2023cites this paper
• Young people’s happiness in the context of negative life events and coping strategies: a latent profile and latent class analysis

  2023cites this paper
• Trajectories and risk factors of fatigue following colorectal cancer diagnosis

  2023cites this paper
• Bayesian Nonparametric Multivariate Mixture of Autoregressive Processes with Application to Brain Signals

  2023cites this paper
• The Development and Validation of the First German Open Scale of Social Information Processing

  2022cites this paper
• Dynamics of hidden brain states when people solve verbal puzzles

  2022cites this paper
• Latent Profile/Class Analysis Identifying Differentiated Intervention Effects

  2022cites this paper
• greed: An R Package for Model-Based Clustering by Greedy Maximization of the Integrated Classification Likelihood

  2022cites this paper
• An observational study of Internet behaviours for adolescent females following sexual abuse

  2021cites this paper
• Identification of transdiagnostic psychiatric disorder subtypes using unsupervised learning

  2021cites this paper
• Understanding eating choices among university students: A study using data from cafeteria cashiers' transactions.

  2021cites this paper
• Revisiting the recombinant history of HIV-1 group M with dynamic network community detection

  2021cites this paper
• A Bayesian latent allocation model for clustering compositional data with application to the Great Barrier Reef

  2021cites this paper
• The Impact of Parenting Style on Attitudes toward Masturbation: A Latent Profile Analysis

  2021cites this paper
• How to Use Model-Based Cluster Analysis Efficiently in Person-Oriented Research

  2021cites this paper
• Who feels good in school? Exploring profiles of scholastic well-being in secondary-school students and the effect on achievement

  2021cites this paper
• A novel computational strategy for DNA methylation imputation using mixture regression model (MRM)

  2020cites this paper
• Hierarchical clustering with discrete latent variable models and the integrated classification likelihood

  2020influential citation
• Estimating heterogeneous reactions to experimental treatments

  2020cites this paper
• Collective Goods Bonn 2019 / 1 Estimating Heterogeneous Reactions to Experimental Treatments

  2019cites this paper
• Clustering Approach toward Large Truck Crash Analysis

  2019cites this paper
• Nonparametric Hierarchical Bayesian Models for Positive Data Clustering Based on Inverted Dirichlet-Based Distributions

  2019cites this paper
• ePubWU Institutional Repository

  2019cites this paper
• Investigating Complex Isochron Data Using Mixture Models Geochemistry, Geophysics, Geosystems

  2018cites this paper
• Investigating Complex Isochron Data Using Mixture Models

  2018cites this paper
• Latent Markovian Modelling and Clustering for Continuous Data Sequences

  2018cites this paper
• A deterministic inference framework for discrete nonparametric latent variable models : learning complex probabilistic models with simple algorithms

  2017cites this paper
• Coupling spectral analysis and hidden Markov models for the segmentation of behavioural patterns

  2017cites this paper
• Choosing the number of groups in a latent stochastic blockmodel for dynamic networks

  2017influential citation
• Exact integrated completed likelihood maximisation in a stochastic block transition model for dynamic networks

  2017influential citation
• Model selection for sparse high-dimensional learning

  2017cites this paper
• Optimal Bayesian estimators for latent variable cluster models

  2016influential citation
• Latent variable models for the analysis of socio-economic data

  2015cites this paper
• Variable selection for model-based clustering using the integrated complete-data likelihood

  2015influential citation