Skip navigation
Skip navigation

Defining Predictive Probability Functions for Species Sampling Models

Müller, Samuel; Scealy, J. L.; Welsh, A. H.

Description

Linear mixed effects models are highly flexible in handling a broad range of data types and are therefore widely used in applications. A key part in the analysis of data is model selection, which often aims to choose a parsimonious model with other desirable properties from a possibly very large set of candidate statistical models. Over the last 5–10 years the literature on model selection in linear mixed models has grown extremely rapidly. The problem is much more complicated than in...[Show more]

dc.contributor.authorMüller, Samuel
dc.contributor.authorScealy, J. L.
dc.contributor.authorWelsh, A. H.
dc.date.accessioned2015-12-04T04:52:03Z
dc.date.available2015-12-04T04:52:03Z
dc.identifier.issn0883-4237
dc.identifier.urihttp://hdl.handle.net/1885/17018
dc.description.abstractLinear mixed effects models are highly flexible in handling a broad range of data types and are therefore widely used in applications. A key part in the analysis of data is model selection, which often aims to choose a parsimonious model with other desirable properties from a possibly very large set of candidate statistical models. Over the last 5–10 years the literature on model selection in linear mixed models has grown extremely rapidly. The problem is much more complicated than in linear regression because selection on the covariance structure is not straightforward due to computational issues and boundary problems arising from positive semidefinite constraints on covariance matrices. To obtain a better understanding of the available methods, their properties and the relationships between them, we review a large body of literature on linear mixed model selection. We arrange, implement, discuss and compare model selection methods based on four major approaches: information criteria such as AIC or BIC, shrinkage methods based on penalized loss functions such as LASSO, the Fence procedure and Bayesian techniques.
dc.description.sponsorshipThis research was supported by an Australian Research Council discovery project grant.
dc.publisherInstitute of Mathematical Statistics
dc.rights© Institute of Mathematical Statistics, 2013. http://www.sherpa.ac.uk/romeo/issn/0883-4237/Author can archive publishers version/pdf. Sherpa/Romeo as at 4/12/15.
dc.sourceStatistical Science
dc.subjectmodel selection
dc.subjectlinear mixed models
dc.subjectAIC
dc.subjectBayes factor
dc.subjectBIC
dc.subjectCholesky decomposition
dc.subjectfence
dc.subjectinformation criteria
dc.subjectLASSO
dc.subjectshrinkage methods
dc.titleDefining Predictive Probability Functions for Species Sampling Models
dc.typeJournal article
local.description.notesImported from ARIES
local.identifier.citationvolume28
dc.date.issued2013
local.identifier.absfor010405
local.identifier.ariespublicationf5625xPUB3519
local.type.statusPublished Version
local.contributor.affiliationMuller, Samuel, School of Mathematics and Statistics F07, University of Sydney
local.contributor.affiliationScealy, J.L., Centre for Mathematics and its Applications, The Australian National University
local.contributor.affiliationWelsh, A. H., Centre for Mathematics and its Applications, The Australian National University
local.bibliographicCitation.issue2
local.bibliographicCitation.startpage135
local.bibliographicCitation.lastpage167
local.identifier.doi10.1214/12-STS410
local.identifier.absseo970101
dc.date.updated2015-12-11T08:11:56Z
local.identifier.scopusID2-s2.0-84878968479
local.identifier.thomsonID000319892300004
CollectionsANU Research Publications

Download

File Description SizeFormat Image
01_Müller_Defining_Predictive_2013.pdfPublished Version514.81 kBAdobe PDFThumbnail


Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.

Updated:  19 May 2020/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator