{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T07:37:34Z","timestamp":1785569854139,"version":"3.56.0"},"reference-count":63,"publisher":"Oxford University Press (OUP)","issue":"5","license":[{"start":{"date-parts":[[2019,8,5]],"date-time":"2019-08-05T00:00:00Z","timestamp":1564963200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,11,1]]},"abstract":"<jats:title>Summary<\/jats:title><jats:p>Choosing the number of mixture components remains an elusive challenge. Model selection criteria can be either overly liberal or conservative and return poorly separated components of limited practical use. We formalize non-local priors (NLPs) for mixtures and show how they lead to well-separated components with non-negligible weight, interpretable as distinct subpopulations. We also propose an estimator for posterior model probabilities under local priors and NLPs, showing that Bayes factors are ratios of posterior-to-prior empty cluster probabilities. The estimator is widely applicable and helps to set thresholds to drop unoccupied components in overfitted mixtures. We suggest default prior parameters based on multimodality for normal\u2013T-mixtures and minimal informativeness for categorical outcomes. We characterize theoretically the NLP-induced sparsity, derive tractable expressions and algorithms. We fully develop normal, binomial and product binomial mixtures but the theory, computation and principles hold more generally. We observed a serious lack of sensitivity of the Bayesian information criterion, insufficient parsimony of the Akaike information criterion and a local prior, and a mixed behaviour of the singular Bayesian information criterion. We also considered overfitted mixtures; their performance was competitive but depended on tuning parameters. Under our default prior elicitation NLPs offered a good compromise between sparsity and power to detect meaningfully separated components.<\/jats:p>","DOI":"10.1111\/rssb.12333","type":"journal-article","created":{"date-parts":[[2019,8,6]],"date-time":"2019-08-06T06:00:46Z","timestamp":1565071246000},"page":"809-837","source":"Crossref","is-referenced-by-count":16,"title":["On Choosing Mixture Components via Non-Local Priors"],"prefix":"10.1093","volume":"81","author":[{"given":"Jairo","family":"F\u00faquene","sequence":"first","affiliation":[{"name":"University of Warwick , Coventry , UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mark","family":"Steel","sequence":"additional","affiliation":[{"name":"University of Warwick , Coventry , UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Rossell","sequence":"additional","affiliation":[{"name":"Universitat Pompeu Fabra , Barcelona , Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2019,8,5]]},"reference":[{"key":"2023022002412683300_","first-page":"1430","volume-title":"Advances in Neural Information Processing Systems","author":"Affandi","year":"2013"},{"key":"2023022002412683300_","doi-asserted-by":"crossref","first-page":"3099","DOI":"10.1214\/09-AOS689","article-title":"Identifiability of parameters in latent structure models with many observed variables","volume":"37","author":"Allman","year":"2009","journal-title":"Ann. Statist."},{"key":"2023022002412683300_","volume-title":"The Theory of Partitions","author":"Andrews","year":"1998"},{"key":"2023022002412683300_","doi-asserted-by":"crossref","first-page":"332","DOI":"10.1198\/jcgs.2010.08111","article-title":"Combining mixture components for clustering","volume":"19","author":"Baudry","year":"2012","journal-title":"J. Computnl Graph. Statist."},{"key":"2023022002412683300_","doi-asserted-by":"crossref","first-page":"719","DOI":"10.1109\/34.865189","article-title":"Assessing a mixture model for clustering with the integrated completed likelihood","volume":"22","author":"Biernacki","year":"2000","journal-title":"IEEE Trans. Pattn Anal. Mach. Intell."},{"key":"2023022002412683300_","doi-asserted-by":"crossref","first-page":"691","DOI":"10.1016\/j.bbmt.2007.02.002","article-title":"High-content flow cytometry and temporal data analysis for defining a cellular signature of graft-versus-host disease","volume":"13","author":"Brinkman","year":"2007","journal-title":"Biol. Blood Marrow Transplantn"},{"key":"2023022002412683300_","doi-asserted-by":"crossref","first-page":"928","DOI":"10.1214\/009053607000000857","article-title":"Bounds for Bayesian order identification with application to mixtures","volume":"36","author":"Chambaz","year":"2008","journal-title":"Ann. Statist."},{"key":"2023022002412683300_","volume-title":"lda: collapsed Gibbs sampling methods for topic models","author":"Chang","year":"2015"},{"key":"2023022002412683300_","doi-asserted-by":"crossref","first-page":"2523","DOI":"10.1214\/08-AOS651","article-title":"Hypothesis test for Normal mixture models: the EM approach","volume":"37","author":"Chen","year":"2009","journal-title":"Ann. Statist."},{"key":"2023022002412683300_","doi-asserted-by":"crossref","first-page":"1313","DOI":"10.1080\/01621459.1995.10476635","article-title":"Marginal likelihood from the Gibbs output","volume":"90","author":"Chib","year":"1995","journal-title":"J. Am. Statist. Ass."},{"key":"2023022002412683300_","first-page":"1165","article-title":"A new family of non-local priors for chain event graph model selection","volume":"11","author":"Collazo","year":"2016","journal-title":"Baysn Anal."},{"key":"2023022002412683300_","doi-asserted-by":"crossref","first-page":"398","DOI":"10.1214\/13-STS433","article-title":"The whetstone and the alum block: balanced objective Bayesian comparison of nested models for discrete data","volume":"28","author":"Consonni","year":"2013","journal-title":"Statist. Sci."},{"key":"2023022002412683300_","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1080\/01621459.1994.10476467","article-title":"An application of the Laplace method to finite mixture distributions","volume":"89","author":"Crawford","year":"1994","journal-title":"J. Am. Statist. Ass."},{"key":"2023022002412683300_","volume-title":"The trouble with Bayes factors. Technical Report.","author":"Dawid","year":"1999"},{"key":"2023022002412683300_","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.2517-6161.1977.tb01600.x","article-title":"Maximum likelihood from incomplete data via the EM algorithm","volume":"39","author":"Dempster","year":"1977","journal-title":"J. R. Statist. Soc."},{"key":"2023022002412683300_","first-page":"279","article-title":"Conditions for bimodality and multimodality of a mixture of two unimodal densities","volume":"45","author":"Do\u0161l\u00e1","year":"2009","journal-title":"Kybernetika"},{"key":"2023022002412683300_","doi-asserted-by":"crossref","first-page":"323","DOI":"10.1111\/rssb.12187","article-title":"A Bayesian information criterion for singular models (with discussion)","volume":"79","author":"Drton","year":"2017","journal-title":"J. R. Statist. Soc."},{"key":"2023022002412683300_","first-page":"1","article-title":"Microarrays, empirical Bayes and the two-groups model","volume":"23","author":"Efron","year":"2008","journal-title":"Statist. Sci."},{"key":"2023022002412683300_","doi-asserted-by":"crossref","first-page":"577","DOI":"10.1080\/01621459.1995.10476550","article-title":"Bayesian density estimation and inference using mixtures","volume":"90","author":"Escobar","year":"1995","journal-title":"J. Am. Statist. Ass."},{"key":"2023022002412683300_","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1111\/j.1469-1809.1936.tb02137.x","article-title":"The use of multiple measurements in taxonomic problems","volume":"7","author":"Fisher","year":"1936","journal-title":"Ann. Eugen."},{"key":"2023022002412683300_","doi-asserted-by":"crossref","first-page":"611","DOI":"10.1198\/016214502760047131","article-title":"Model-based clustering, discriminant analysis, and density estimation","volume":"97","author":"Fraley","year":"2002","journal-title":"J. Am. Statist. Ass."},{"key":"2023022002412683300_","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1111\/j.1368-423X.2004.00125.x","article-title":"Estimating marginal likelihoods for mixture and Markov switching models using bridge sampling techniques","volume":"7","author":"Fr\u00fchwirth-Schnatter","year":"2004","journal-title":"Econmetr. J."},{"key":"2023022002412683300_","volume-title":"Finite Mixtures and Markov Switching Models","author":"Fr\u00fchwirth-Schnatter","year":"2006"},{"key":"2023022002412683300_","doi-asserted-by":"crossref","first-page":"1115","DOI":"10.1109\/TIT.2012.2221122","article-title":"Consistent order estimation and minimal penalties","volume":"59","author":"Gassiat","year":"2013","journal-title":"IEEE Trans. Inform. Theory"},{"key":"2023022002412683300_","doi-asserted-by":"crossref","DOI":"10.1201\/b16018","author":"Gelman","year":"2013","journal-title":"Bayesian Data Analysis"},{"key":"2023022002412683300_","first-page":"35","volume-title":"Proc. Varanashi Symp. Bayesian Inference","author":"Ghosal","year":"1996"},{"key":"2023022002412683300_","doi-asserted-by":"crossref","first-page":"1233","DOI":"10.1214\/aos\/1013203452","article-title":"Entropies and rates of convergence for maximum likelihood and Bayes estimation for mixture of normal densities","volume":"29","author":"Ghosal","year":"2001","journal-title":"Ann. Statist."},{"key":"2023022002412683300_","doi-asserted-by":"crossref","first-page":"697","DOI":"10.1214\/009053606000001271","article-title":"Posterior convergence rates of Dirichlet mixtures at smooth densities","volume":"35","author":"Ghosal","year":"2007","journal-title":"Ann. Statist."},{"key":"2023022002412683300_","first-page":"789","volume-title":"Proc. Berkeley Conf. in Honor of Jerzy Neyman and Jack Kiefer","author":"Ghosh","year":"1985"},{"key":"2023022002412683300_","doi-asserted-by":"crossref","first-page":"205","DOI":"10.1007\/978-3-7908-2064-5_11","volume-title":"Recent Advances in Linear Models and Related Areas","author":"Gr\u00fcn","year":"2008"},{"key":"2023022002412683300_","doi-asserted-by":"crossref","first-page":"795","DOI":"10.1214\/aos\/1176349557","article-title":"A constrained formulation of maximum-likelihood estimation for Normal mixture distributions","volume":"13","author":"Hathaway","year":"1985","journal-title":"Ann. Statist."},{"key":"2023022002412683300_","first-page":"1","article-title":"Overfitting Bayesian mixture models with an unknown number of components","volume":"10","author":"Havre","year":"2015","journal-title":"PLOS One"},{"key":"2023022002412683300_","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1002\/bimj.201200111","article-title":"Clustering in linear-mixed models with a group fused lasso penalty","volume":"56","author":"Heinzl","year":"2014","journal-title":"Biometr. J."},{"key":"2023022002412683300_","doi-asserted-by":"crossref","first-page":"2726","DOI":"10.1214\/16-AOS1444","article-title":"Convergence rates of parameter estimation for some weakly identifiable finite mixtures","volume":"44","author":"Ho","year":"2016","journal-title":"Ann. Statist."},{"key":"2023022002412683300_","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1111\/j.1467-9868.2009.00730.x","article-title":"On the use of non-local prior densities in Bayesian hypothesis tests","volume":"72","author":"Johnson","year":"2010","journal-title":"J. R. Statist. Soc."},{"key":"2023022002412683300_","doi-asserted-by":"crossref","first-page":"649","DOI":"10.1080\/01621459.2012.682536","article-title":"Bayesian model selection in high-dimensional settings","volume":"107","author":"Johnson","year":"2012","journal-title":"J. Am. Statist. Ass."},{"key":"2023022002412683300_","first-page":"573","article-title":"Importance sampling schemes for evidence approximation in mixture models","volume":"11","author":"Lee","year":"2016","journal-title":"Baysn Anal."},{"key":"2023022002412683300_","doi-asserted-by":"crossref","first-page":"1350","DOI":"10.1214\/aos\/1176348772","article-title":"Consistence estimation of a mixing distribution","volume":"20","author":"Leroux","year":"1992","journal-title":"Ann. Statist."},{"key":"2023022002412683300_","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1016\/S0378-3758(03)00138-1","article-title":"Asymptotics for likelihood ratio test in a two-component normal mixture model","volume":"123","author":"Liu","year":"2004","journal-title":"J. Statist. Planng Inf."},{"key":"2023022002412683300_","doi-asserted-by":"crossref","first-page":"285","DOI":"10.1080\/10618600.2016.1200472","article-title":"Identifying mixtures of mixtures using Bayesian estimation","volume":"26","author":"Malsiner-Walli","year":"2017","journal-title":"J. Computnl Graph. Statist."},{"key":"2023022002412683300_","first-page":"2","article-title":"Approximating the marginal likelihood in mixture models","volume":"1","author":"Marin","year":"2008","journal-title":"Bull. Ind. Chap. Int. Soc. Baysn Anal."},{"key":"2023022002412683300_","doi-asserted-by":"crossref","DOI":"10.1002\/9781119995678","volume-title":"Mixtures: Estimation and Applications","author":"Mengersen","year":"2011"},{"key":"2023022002412683300_","first-page":"1889","volume-title":"Advances in Neural Information Processing Systems","author":"Petralia","year":"2012"},{"key":"2023022002412683300_","first-page":"759","article-title":"On posterior concentration in misspecified models","volume":"10","author":"Ramamoorthi","year":"2015","journal-title":"Baysn Anal."},{"key":"2023022002412683300_","doi-asserted-by":"crossref","first-page":"2042","DOI":"10.1214\/009053605000000417","article-title":"The topography of multivariate normal mixtures","volume":"33","author":"Ray","year":"2005","journal-title":"Ann. Statist."},{"key":"2023022002412683300_","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1214\/aos\/1176345353","article-title":"Note on the consistency of the maximum likelihood estimate for nonidentifiable distributions","volume":"9","author":"Redner","year":"1981","journal-title":"Ann. Statist."},{"key":"2023022002412683300_","doi-asserted-by":"crossref","first-page":"731","DOI":"10.1111\/1467-9868.00095","article-title":"On Bayesian analysis of mixtures with an unknown number of components","volume":"59","author":"Richardson","year":"1997","journal-title":"J. R. Statist. Soc. B"},{"key":"2023022002412683300_","volume-title":"Handbook of Mixture Analysis","author":"Rossell","year":"2018"},{"key":"2023022002412683300_","doi-asserted-by":"crossref","first-page":"254","DOI":"10.1080\/01621459.2015.1130634","article-title":"Non-local priors for high-dimensional estimation","volume":"112","author":"Rossell","year":"2017","journal-title":"J. Am. Statist. Ass."},{"key":"2023022002412683300_","doi-asserted-by":"crossref","first-page":"305","DOI":"10.1007\/978-3-319-00032-9_35","volume-title":"Statistical Models for Data Analysis","author":"Rossell","year":"2013"},{"key":"2023022002412683300_","first-page":"417","volume-title":"Bayesian Statistics 8","author":"Rousseau","year":"2007"},{"key":"2023022002412683300_","doi-asserted-by":"crossref","first-page":"689","DOI":"10.1111\/j.1467-9868.2011.00781.x","article-title":"Asymptotic behaviour of the posterior distribution in overfitted models","volume":"73","author":"Rousseau","year":"2011","journal-title":"J. R. Statist. Soc."},{"key":"2023022002412683300_","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1177\/096228029600500204","article-title":"Mixture distribution in human genetics","volume":"5","author":"Schork","year":"1996","journal-title":"Statist. Meth. Med. Res."},{"key":"2023022002412683300_","doi-asserted-by":"crossref","first-page":"461","DOI":"10.1214\/aos\/1176344136","article-title":"Estimating the dimension of a model","volume":"6","author":"Schwarz","year":"1978","journal-title":"Ann. Statist."},{"key":"2023022002412683300_","first-page":"10","article-title":"Scalable Bayesian variable selection using nonlocal prior densities in ultrahigh-dimensional settings","volume":"28","author":"Shin","year":"2018","journal-title":"Statist. Sin."},{"key":"2023022002412683300_","doi-asserted-by":"crossref","first-page":"1265","DOI":"10.1214\/aoms\/1177703862","article-title":"Identifibility of finite mixtures","volume":"34","author":"Teicher","year":"1963","journal-title":"Ann. Math. Statist."},{"key":"2023022002412683300_","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511800474","volume-title":"Algebraic Geometry and Statistical Learning Theory","author":"Watanabe","year":"2009"},{"key":"2023022002412683300_","first-page":"867","article-title":"A widely applicable Bayesian information criteria","volume":"14","author":"Watanabe","year":"2013","journal-title":"J. Mach. Learn. Res."},{"key":"2023022002412683300_","volume-title":"sBIC: computing the singular BIC for multiple models","author":"Weihs","year":"2016"},{"key":"2023022002412683300_","doi-asserted-by":"crossref","first-page":"31","DOI":"10.2307\/2348930","article-title":"Deconvolution of mixtures in analysis of neural synaptic transmission","volume":"43","author":"West","year":"1994","journal-title":"Statistician"},{"key":"2023022002412683300_","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2018.1537918","article-title":"Bayesian repulsive Gaussian mixture model","volume":"114","author":"Xie","year":"2019","journal-title":"J. Am. Statist. Ass."},{"key":"2023022002412683300_","doi-asserted-by":"crossref","first-page":"955","DOI":"10.1111\/biom.12482","article-title":"Bayesian inference for latent biologic structure with determinantal point processes (dpp)","volume":"72","author":"Xu","year":"2016","journal-title":"Biometrics"},{"key":"2023022002412683300_","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1214\/aoms\/1177698520","article-title":"On the identifiability of finite mixtures","volume":"39","author":"Yakowitz","year":"1968","journal-title":"Ann. Math. Statist."}],"container-title":["Journal of the Royal Statistical Society Series B: Statistical Methodology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.wiley.com\/onlinelibrary\/tdm\/v1\/articles\/10.1111%2Frssb.12333","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/academic.oup.com\/jrsssb\/article-pdf\/81\/5\/809\/49269974\/jrsssb_81_5_809.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jrsssb\/article-pdf\/81\/5\/809\/49269974\/jrsssb_81_5_809.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,21]],"date-time":"2024-07-21T18:46:10Z","timestamp":1721587570000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jrsssb\/article\/81\/5\/809\/7048372"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,8,5]]},"references-count":63,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2019,8,5]]},"published-print":{"date-parts":[[2019,11,1]]}},"URL":"https:\/\/doi.org\/10.1111\/rssb.12333","relation":{},"ISSN":["1369-7412","1467-9868"],"issn-type":[{"value":"1369-7412","type":"print"},{"value":"1467-9868","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2019,11]]},"published":{"date-parts":[[2019,8,5]]}}}