Investigation of the widely applicable Bayesian information criterion

DSpace/Manakin Repository

Show simple item record

dc.contributor.author Friel, Nial
dc.contributor.author McKeone, J. P.
dc.contributor.author Oates, Chris J.
dc.contributor.author Pettitt, Anthony
dc.date.accessioned 2017-03-10T17:12:03Z
dc.date.copyright 2016 Springer en
dc.date.issued 2017-05
dc.identifier.citation Statistics and Computing en
dc.identifier.uri http://hdl.handle.net/10197/8392
dc.description.abstract The widely applicable Bayesian information criterion (WBIC) is a simple and fast approximation to the model evidence that has received little practical consideration. WBIC uses the fact that the log evidence can be written as an expectation, with respect to a powered posterior proportional to the likelihood raised to a power t(0,1)t(0,1) , of the log deviance. Finding this temperature value tt is generally an intractable problem. We find that for a particular tractable statistical model that the mean squared error of an optimally-tuned version of WBIC with correct temperature tt is lower than an optimally-tuned version of thermodynamic integration (power posteriors). However in practice WBIC uses the a canonical choice of t=1/log(n)t=1/log(n) . Here we investigate the performance of WBIC in practice, for a range of statistical models, both regular models and singular models such as latent variable models or those with a hierarchical structure for which BIC cannot provide an adequate solution. Our findings are that, generally WBIC performs adequately when one uses informative priors, but it can systematically overestimate the evidence, particularly for small sample sizes. en
dc.description.sponsorship Science Foundation Ireland en
dc.language.iso en en
dc.publisher Springer en
dc.rights The final publication is available at Springer via http://dx.doi.org/10.1007/s11222-016-9657-y. en
dc.subject Machine learning en
dc.subject Statistics en
dc.subject Marginal likelihood en
dc.subject Evidence en
dc.subject Power posteriors en
dc.subject Widely applicable Bayesian information criterion en
dc.title Investigation of the widely applicable Bayesian information criterion en
dc.type Journal Article en
dc.status Peer reviewed en
dc.identifier.volume 27 en
dc.identifier.issue 3 en
dc.identifier.startpage 833 en
dc.identifier.endpage 844 en
dc.identifier.doi 10.1007/s11222-016-9657-y
dc.neeo.contributor Friel|Nial|aut|
dc.neeo.contributor McKeone|J. P.|aut|
dc.neeo.contributor Oates|Chris J.|aut|
dc.neeo.contributor Pettitt|Anthony|aut|
dc.date.embargo 2017-05-19
dc.description.othersponsorship Australian Postgraduate Award (APA) en
dc.description.othersponsorship Australian Research Council Discovery Grant en
dc.date.updated 2016-12-05T11:36:16Z
 Access to this item has been restricted by the copyright holder until: 2017-05-19

This item appears in the following Collection(s)

Show simple item record

This item is available under the Attribution-NonCommercial-NoDerivs 3.0 Ireland. No item may be reproduced for commercial purposes. For other possible restrictions on use please refer to the publisher's URL where this is made available, or to notes contained in the item itself. Other terms may apply.

If you are a publisher or author and have copyright concerns for any item, please email research.repository@ucd.ie and the item will be withdrawn immediately. The author or person responsible for depositing the article will be contacted within one business day.

Search Research Repository


Advanced Search

Browse