Full metadata record
DC FieldValueLanguage
dc.contributor.authorAlhorn, Kira-
dc.contributor.authorDette, Holger-
dc.contributor.authorSchorning, Kirsten-
dc.date.accessioned2019-04-03T15:30:14Z-
dc.date.available2019-04-03T15:30:14Z-
dc.date.issued2019-
dc.identifier.urihttp://hdl.handle.net/2003/37979-
dc.identifier.urihttp://dx.doi.org/10.17877/DE290R-19964-
dc.description.abstractIn this paper we construct optimal designs for frequentist model averaging estimation. We derive the asymptotic distribution of the model averaging estimate with fixed weights in the case where the competing models are non-nested and none of these models is correctly specified. A Bayesian optimal design minimizes an expectation of the asymptotic mean squared error of the model averaging estimate calculated with respect to a suitable prior distribution. We demonstrate that Bayesian optimal designs can improve the accuracy of model averaging substantially. Moreover, the derived designs also improve the accuracy of estimation in a model selected by model selection and model averaging estimates with random weights.en
dc.language.isoende
dc.relation.ispartofseriesDiscussion Paper / SFB823;7/2019-
dc.subjectmodel selectionen
dc.subjectBayesian optimal designsen
dc.subjectoptimal designen
dc.subjectmodel uncertaintyen
dc.subjectmodel averagingen
dc.subject.ddc310-
dc.subject.ddc330-
dc.subject.ddc620-
dc.titleOptimal designs for model averaging in non-nested modelsen
dc.typeTextde
dc.type.publicationtypeworkingPaperde
dcterms.accessRightsopen access-
eldorado.secondarypublicationfalsede
Appears in Collections:Sonderforschungsbereich (SFB) 823

Files in This Item:
File Description SizeFormat 
DP_0719_SFB823_Alhorn_Dette_Schorning.pdfDNB368.7 kBAdobe PDFView/Open


This item is protected by original copyright



This item is protected by original copyright rightsstatements.org