A fast distance based approach for determining the number of components in mixtures
A fast distance based approach for determining the number of components in mixtures
The authors propose a procedure for determining the unknown number of components in mixtures by generalizing a Bayesian testing method proposed by Mengersen & Robert (1996). The testing criterion they propose involves a Kullback-Leibler distance, which may be weighted or not. They give explicit formulas for the weighted distance for a number of mixture distributions and propose a stepwise testing procedure to select the minimum number of components adequate for the data. Their procedure, which is implemented using the BUGS software, exploits a fast collapsing approach which accelerates the search for the minimum number of components by avoiding full refitting at each step. The performance of their method is compared, using both distances, to the Bayes factor approach.
bayes factor, kullback-Leibler distance, gibbs sampler, markov chain monte carlo, mixture model, reversible jump
3-22
Sahu, S.K.
33f1386d-6d73-4b60-a796-d626721f72bf
Cheng, R.C.H.
a4296b4e-7693-4e5f-b3d5-27b617bb9d67
2003
Sahu, S.K.
33f1386d-6d73-4b60-a796-d626721f72bf
Cheng, R.C.H.
a4296b4e-7693-4e5f-b3d5-27b617bb9d67
Sahu, S.K. and Cheng, R.C.H.
(2003)
A fast distance based approach for determining the number of components in mixtures.
Canadian Journal of Statistics, 31 (1), .
Abstract
The authors propose a procedure for determining the unknown number of components in mixtures by generalizing a Bayesian testing method proposed by Mengersen & Robert (1996). The testing criterion they propose involves a Kullback-Leibler distance, which may be weighted or not. They give explicit formulas for the weighted distance for a number of mixture distributions and propose a stepwise testing procedure to select the minimum number of components adequate for the data. Their procedure, which is implemented using the BUGS software, exploits a fast collapsing approach which accelerates the search for the minimum number of components by avoiding full refitting at each step. The performance of their method is compared, using both distances, to the Bayes factor approach.
This record has no associated files available for download.
More information
Published date: 2003
Keywords:
bayes factor, kullback-Leibler distance, gibbs sampler, markov chain monte carlo, mixture model, reversible jump
Organisations:
Statistics
Identifiers
Local EPrints ID: 30043
URI: http://eprints.soton.ac.uk/id/eprint/30043
PURE UUID: 35f6683d-03f5-443d-b474-2f0e7dbda01c
Catalogue record
Date deposited: 12 May 2006
Last modified: 08 Jan 2022 02:52
Export record
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics
