Publicación:
Model Selection and Model Averaging for Mixed-Effects Models with Crossed Random Effects for Subjects and Items

Vista sencilla de ítem
dc.contributor.authorOlmos, Ricardo
dc.contributor.authorFerrer, Emilio
dc.contributor.authorMartínez Huertas, José Ángel::virtual::4270::600
dc.contributor.authorMartínez Huertas, José Ángel
dc.contributor.authorMartínez Huertas, José Ángel
dc.contributor.authorMartínez Huertas, José Ángel
dc.date.accessioned2024-05-20T11:50:08Z
dc.date.available2024-05-20T11:50:08Z
dc.date.issued2021-02-26
dc.description.abstractA good deal of experimental research is characterized by the presence of random effects on subjects and items. A standard modeling approach that includes such sources of variability is the mixed-effects models (MEMs) with crossed random effects. However, under-parameterizing or over-parameterizing the random structure of MEMs bias the estimations of the Standard Errors (SEs) of fixed effects. In this simulation study, we examined two different but complementary perspectives: model selection with likelihood-ratio tests, AIC, and BIC; and model averaging with Akaike weights. Results showed that true model selection was constant across the different strategies examined (including ML and REML estimators). However, sample size and variance of random slopes were found to explain true model selection and SE bias of fixed effects. No relevant differences in SE bias were found for model selection and model averaging. Sample size and variance of random slopes interacted with the estimator to explain SE bias. Only the within-subjects effect showed significant underestimation of SEs with smaller number of items and larger item random slopes. SE bias was higher for ML than REML, but the variability of SE bias was the opposite. Such variability can be translated into high rates of unacceptable bias in many replications.en
dc.description.versionversión final
dc.identifier.doihttps://doi.org/10.1080/00273171.2021.1889946
dc.identifier.issn0027-3171; eISSN 1532-7906
dc.identifier.urihttps://hdl.handle.net/20.500.14468/12613
dc.journal.issue4
dc.journal.titleMultivariate Behavioral Research
dc.journal.volume57
dc.language.isoen
dc.publisher['Taylor and Francis Group', 'Routledge']
dc.relation.centerFacultad de Psicología
dc.relation.departmentMetodología de las Ciencias del Comportamiento
dc.rightsinfo:eu-repo/semantics/openAccess
dc.rights.urihttps://creativecommons.org/licenses/by-nc-nd/4.0/deed.es
dc.subject.keywordsmixed-effects models
dc.subject.keywordscrossed random effects
dc.subject.keywordsrandom slopes
dc.subject.keywordsmodel selection
dc.subject.keywordsmodel averaging
dc.subject.keywordsML
dc.subject.keywordsREML
dc.titleModel Selection and Model Averaging for Mixed-Effects Models with Crossed Random Effects for Subjects and Itemses
dc.typejournal articleen
dc.typeartículoes
dspace.entity.typePublication
relation.isAuthorOfPublicationca510876-0be8-438a-a565-ac5f8953fb78
relation.isAuthorOfPublicationca510876-0be8-438a-a565-ac5f8953fb78
relation.isAuthorOfPublicationca510876-0be8-438a-a565-ac5f8953fb78
relation.isAuthorOfPublicationca510876-0be8-438a-a565-ac5f8953fb78
relation.isAuthorOfPublication.latestForDiscoveryca510876-0be8-438a-a565-ac5f8953fb78
Archivos
Bloque original
Mostrando 1 - 1 de 1
Miniatura
Nombre:
Martinez-Huertas_JA_MEMsCRmodel.pdf
Tamaño:
619.9 KB
Formato:
Adobe Portable Document Format
Descargar
Colecciones
Artículos y papers