Show simple item record

dc.contributor.authorHainy, Markus
dc.contributor.authorPrice, David J
dc.contributor.authorRestif, Olivier
dc.contributor.authorDrovandi, Christopher
dc.date.accessioned2022-04-21T01:03:19Z
dc.date.available2022-04-21T01:03:19Z
dc.date.issued2022-02-22
dc.identifier.issn0960-3174
dc.identifier.other35310544
dc.identifier.otherPMC8924111
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/336295
dc.description.abstractPerforming optimal Bayesian design for discriminating between competing models is computationally intensive as it involves estimating posterior model probabilities for thousands of simulated data sets. This issue is compounded further when the likelihood functions for the rival models are computationally expensive. A new approach using supervised classification methods is developed to perform Bayesian optimal model discrimination design. This approach requires considerably fewer simulations from the candidate models than previous approaches using approximate Bayesian computation. Further, it is easy to assess the performance of the optimal design through the misclassification error rate. The approach is particularly useful in the presence of models with intractable likelihoods but can also provide computational advantages when the likelihoods are manageable.<h4>Supplementary information</h4>The online version contains supplementary material available at 10.1007/s11222-022-10078-2.
dc.languageeng
dc.rightsAttribution 4.0 International
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.sourcenlmid: 101473218
dc.subjectRandom Forest
dc.subjectBayesian Model Selection
dc.subjectApproximate Bayesian Computation
dc.subjectClassification And Regression Tree
dc.subjectContinuous-time Markov Process
dc.subjectSimulation-Based Bayesian Experimental Design
dc.titleOptimal Bayesian design for model discrimination via classification.
dc.typeArticle
dc.date.updated2022-04-21T01:03:19Z
prism.issueIdentifier2
prism.publicationNameStatistics and computing
prism.volume32
dc.identifier.doi10.17863/CAM.83713
rioxxterms.versionofrecord10.1007/s11222-022-10078-2
rioxxterms.versionVoR
rioxxterms.licenseref.urihttps://creativecommons.org/licenses/by/4.0/
dc.contributor.orcidHainy, Markus [0000-0003-4834-0250]
dc.contributor.orcidPrice, David J [0000-0003-0076-3123]
dc.contributor.orcidRestif, Olivier [0000-0001-9158-853X]
dc.contributor.orcidDrovandi, Christopher [0000-0001-9222-8763]
pubs.funder-project-idAustralian Research Council (DE160100741)
pubs.funder-project-idBiotechnology and Biological Sciences Research Council (BB/M020193/1)
pubs.funder-project-idAustrian Science Fund FWF (J 3959, J3959-N32)


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

Attribution 4.0 International
Except where otherwise noted, this item's licence is described as Attribution 4.0 International