Optimal designs for frequentist model averaging

dc.contributor.author	Alhorn, Kira
dc.contributor.author	Schorning, Kirsten
dc.contributor.author	Dette, Holger
dc.date.accessioned	2018-07-16T12:03:35Z
dc.date.available	2018-07-16T12:03:35Z
dc.date.issued	2018
dc.description.abstract	We consider the problem of designing experiments for the estimation of a target in regression analysis if there is uncertainty about the parametric form of the regression function. A new optimality criterion is proposed, which minimizes the asymptotic mean squared error of the frequentist model averaging estimate by the choice of an experimental design. Necessary conditions for the optimal solution of a locally and Bayesian optimal design problem are established. The results are illustrated in several examples and it is demonstrated that Bayesian optimal designs can yield a reduction of the mean squared error of the model averaging estimator up to 45%.	en
dc.identifier.uri	http://hdl.handle.net/2003/37014
dc.identifier.uri	http://dx.doi.org/10.17877/DE290R-19011
dc.language.iso	en	de
dc.relation.ispartofseries	Discussion Paper / SFB823;14/2018
dc.subject	model selection	en
dc.subject	Bayesian optimal designs	en
dc.subject	optimal design	en
dc.subject	model uncertainty	en
dc.subject	local misspecification	en
dc.subject	model averaging	en
dc.subject.ddc	310
dc.subject.ddc	330
dc.subject.ddc	620
dc.title	Optimal designs for frequentist model averaging	en
dc.type	Text	de
dc.type.publicationtype	workingPaper	de
dcterms.accessRights	open access
eldorado.secondarypublication	false	de

Files

Now showing 1 - 1 of 1

Now showing 1 - 1 of 1