Skip to Main content Skip to Navigation
Journal articles

Maximum Smoothed Likelihood for Multivariate Mixtures

Abstract : We introduce an algorithm for estimating the parameters in a finite mixture of completely unspecified multivariate components in at least three dimensions under the assumption of conditionally independent coordinate dimensions. We prove that this algorithm, based on a majorization-minimization idea, possesses a desirable descent property just as any EM algorithm does. We discuss the similarities between our algorithm and a related one - the so-called nonlinearly smoothed EM, or NEMS, algorithm for the non-mixture setting. We also demonstrate via simulation studies that the new algorithm gives very similar results to another algorithm that does not satisfy any descent algorithm, thus validating the latter algorithm, which can be simpler to program. We provide code for implementing the new algorithm in a publicly-available R package.
Complete list of metadatas

Cited literature [24 references]  Display  Hide  Download
Contributor : Didier Chauveau <>
Submitted on : Thursday, September 9, 2010 - 2:50:18 PM
Last modification on : Thursday, May 3, 2018 - 3:32:06 PM
Document(s) archivé(s) le : Tuesday, October 23, 2012 - 3:46:41 PM


Files produced by the author(s)




Michael Levine, David Hunter, Didier Chauveau. Maximum Smoothed Likelihood for Multivariate Mixtures. Biometrika, Oxford University Press (OUP), 2011, 98 (2), pp.403-416. ⟨10.1093/biomet/asq079⟩. ⟨hal-00516391⟩



Record views


Files downloads