A Bayesian sparse finite mixture model for clustering data from a heterogeneous population

Abstract. In this paper we introduce a Bayesian approach for clustering data using a sparse finite mixture model (SFMM). The SFMM is a finite mixture model with a large number of components k previously fixed where many components can be empty. In this model, the number of components k can be interpreted as the maximum number of distinct mixture components. Then, we explore the use of a prior distribution for the weights of the mixture model that take into account the possibility that the number of clusters kc (e.g. non empty components) can be random and smaller than the number of components k of the finite mixture model. In order to determine clusters we develop a MCMC algorithm denominated Split-Merge allocation sampler. In this algorithm the split-merge strategy is data-driven and was inserted within the algorithm in order to increase the mixing of the Markov chain in relation to the number of clusters. The performance of the method is verified using simulated datasets and three real datasets. The first real data set is the benchmark galaxy data, while second and third are the publicly available data set on Enzyme and Acidity, respectively.

• Publication year

  2020

• Venue

  Brazilian Journal of Probability and Statistics

• Publication date

  2020-05-01

• Fields of study

  Mathematics, Computer Science

• Identifiers
  DOI 10.1214/18-bjps425
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• From here to infinity: sparse finite versus Dirichlet process mixtures in model-based clustering

  2018influential reference
• Partitioning gene expression data by data-driven Markov chain Monte Carlo

  2015cited by this paper
• Mixture models with an unknown number of components via a new posterior split-merge MCMC algorithm

  2014cited by this paper
• Model-based clustering based on sparse finite Gaussian mixtures

  2014cited by this paper
• Model-based clustering of high-dimensional data: A review

  2014cited by this paper
• A Framework for Feature Selection in Clustering

  2010cited by this paper
• Bayesian finite mixtures with an unknown number of components: The allocation sampler

  2007cited by this paper
• Model-Based Clustering With Dissimilarities: A Bayesian Approach

  2007cited by this paper
• Markov Chain Monte Carlo Methods and the Label Switching Problem in Bayesian Mixture Modeling

  2005cited by this paper
• Mixture models, latent variables and partitioned importance sampling

  2004influential reference
• Bayesian measures of model complexity and fit

  2002cited by this paper
• Model-Based Clustering, Discriminant Analysis, and Density Estimation

  2002cited by this paper
• Finite Mixture Models

  2000cited by this paper
• Dealing with label switching in mixture models

  2000influential reference
• Computational and Inferential Difficulties with Mixture Posterior Distributions

  2000cited by this paper
• Practical Bayesian Density Estimation Using Mixtures of Normals

  1997influential reference
• Inference in model-based cluster analysis

  1997cited by this paper
• Bayesian Density Estimation and Inference Using Mixtures

  1995influential reference
• Understanding the Metropolis-Hastings Algorithm

  1995cited by this paper
• Summary of the

  1994influential reference
• Model-based Gaussian and non-Gaussian clustering

  1993cited by this paper
• Mixture Models: Inference and Applications to Clustering

  1989cited by this paper
• Model selection and Akaike's Information Criterion (AIC): The general theory and its analytical extensions

  1987cited by this paper
• Estimating the Dimension of a Model

  1978cited by this paper
• Bayesian cluster analysis

  1978cited by this paper
• A new look at the statistical model identification

  1974influential reference
• Some methods for classification and analysis of multivariate observations

  1967cited by this paper
• Hierarchical Grouping to Optimize an Objective Function

  1963cited by this paper
• A statistical method for evaluating systematic relationships

  1958cited by this paper
• The application of computers to taxonomy.

  1957cited by this paper

• A Bayesian semiparametric mixture model for clustering zero-inflated microbiome data.

  2025cites this paper
• Bayesian Repulsive Mixture Modeling with Mat\'ern Point Processes

  2022cites this paper
• An Integrated Approach for Making Inference on the Number of Clusters in a Mixture Model

  2019cites this paper