ABSTRACT BOOTSTRAP CONFIDENCE INTERVALS IN LINEAR MODELS

dc.contributor.author	Holm, Sture
dc.date.accessioned	2011-02-10T10:22:55Z
dc.date.available	2011-02-10T10:22:55Z
dc.date.issued	1990-01-01
dc.identifier.issn	0349-8034
dc.identifier.uri	http://hdl.handle.net/2077/24407
dc.description.abstract	A bootstrap method for generating confidence intervals in linear models is suggested. The method is motivated by an abstract nonobservable bootstrap sample of true residuals leading to an observable final result. This means that the only error in the method is the pure bootstrap error obtained by replacing the true residual distribution by the empirical one. It is shown that the method is valid, having the same asymptotic conditional distribution as the ordinary bootstrap method. Simulations indicate clearly that the abstract bootstrap method works better than the ordinary bootstrap method for small samples.	sv
dc.format.extent	21	sv
dc.language.iso	eng	sv
dc.publisher	University of Gothenburg	sv
dc.relation.ispartofseries	Research Report	sv
dc.relation.ispartofseries	1990-1	sv
dc.title	ABSTRACT BOOTSTRAP CONFIDENCE INTERVALS IN LINEAR MODELS	sv
dc.type	Text	sv
dc.type.svep	report	sv