Dataset Information

Comparison of Criteria for Choosing the Number of Classes in Bayesian Finite Mixture Models.

ABSTRACT: Identifying the number of classes in Bayesian finite mixture models is a challenging problem. Several criteria have been proposed, such as adaptations of the deviance information criterion, marginal likelihoods, Bayes factors, and reversible jump MCMC techniques. It was recently shown that in overfitted mixture models, the overfitted latent classes will asymptotically become empty under specific conditions for the prior of the class proportions. This result may be used to construct a criterion for finding the true number of latent classes, based on the removal of latent classes that have negligible proportions. Unlike some alternative criteria, this criterion can easily be implemented in complex statistical models such as latent class mixed-effects models and multivariate mixture models using standard Bayesian software. We performed an extensive simulation study to develop practical guidelines to determine the appropriate number of latent classes based on the posterior distribution of the class proportions, and to compare this criterion with alternative criteria. The performance of the proposed criterion is illustrated using a data set of repeatedly measured hemoglobin values of blood donors.

SUBMITTER: Nasserinejad K

PROVIDER: S-EPMC5231325 | biostudies-literature | 2017

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Comparison of Criteria for Choosing the Number of Classes in Bayesian Finite Mixture Models.

Nasserinejad Kazem K van Rosmalen Joost J de Kort Wim W Lesaffre Emmanuel E

PloS one 20170112 1

Identifying the number of classes in Bayesian finite mixture models is a challenging problem. Several criteria have been proposed, such as adaptations of the deviance information criterion, marginal likelihoods, Bayes factors, and reversible jump MCMC techniques. It was recently shown that in overfitted mixture models, the overfitted latent classes will asymptotically become empty under specific conditions for the prior of the class proportions. This result may be used to construct a criterion f ...[more]

PMID: 28081166

Similar Datasets

Project description:BackgroundCluster analysis is an integral part of precision medicine and systems biology, used to define groups of patients or biomolecules. Consensus clustering is an ensemble approach that is widely used in these areas, which combines the output from multiple runs of a non-deterministic clustering algorithm. Here we consider the application of consensus clustering to a broad class of heuristic clustering algorithms that can be derived from Bayesian mixture models (and extensions thereof) by adopting an early stopping criterion when performing sampling-based inference for these models. While the resulting approach is non-Bayesian, it inherits the usual benefits of consensus clustering, particularly in terms of computational scalability and providing assessments of clustering stability/robustness.ResultsIn simulation studies, we show that our approach can successfully uncover the target clustering structure, while also exploring different plausible clusterings of the data. We show that, when a parallel computation environment is available, our approach offers significant reductions in runtime compared to performing sampling-based Bayesian inference for the underlying model, while retaining many of the practical benefits of the Bayesian approach, such as exploring different numbers of clusters. We propose a heuristic to decide upon ensemble size and the early stopping criterion, and then apply consensus clustering to a clustering algorithm derived from a Bayesian integrative clustering method. We use the resulting approach to perform an integrative analysis of three 'omics datasets for budding yeast and find clusters of co-expressed genes with shared regulatory proteins. We validate these clusters using data external to the analysis.ConclustionsOur approach can be used as a wrapper for essentially any existing sampling-based Bayesian clustering implementation, and enables meaningful clustering analyses to be performed using such implementations, even when computational Bayesian inference is not feasible, e.g. due to poor exploration of the target density (often as a result of increasing numbers of features) or a limited computational budget that does not along sufficient samples to drawn from a single chain. This enables researchers to straightforwardly extend the applicability of existing software to much larger datasets, including implementations of sophisticated models such as those that jointly model multiple datasets.

Dataset Information

Comparison of Criteria for Choosing the Number of Classes in Bayesian Finite Mixture Models.

Publications

Comparison of Criteria for Choosing the Number of Classes in Bayesian Finite Mixture Models.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets