Please use this identifier to cite or link to this item:
Full metadata record
DC FieldValueLanguage
dc.contributor.authorHolzmann, Hajoen_US
dc.contributor.authorMin, Alekseyen_US
dc.contributor.authorCzado, Claudiaen_US
dc.description.abstractA new method for testing linear restrictions in linear regression models is suggested. It allows to validate the linear restriction, up to a specified approximation error and with a specified error probability. The test relies on asymptotic normality of the test statistic, and therefore normality of the errors in the regression model is not required. In a simulation study the performance of the suggested method for model selection purposes, as compared to standard model selection criteria and the t-test, is examined. As an illustration we analyze the US college spending data from 1994.en_US
dc.publisher|aTechn. Univ.; Sonderforschungsbereich 386, Statistische Analyse Diskreter Strukturen|cMünchenen_US
dc.relation.ispartofseries|aDiscussion paper // Sonderforschungsbereich 386 der Ludwig-Maximilians-Universität München|x478en_US
dc.subject.keywordasymptotic normalityen_US
dc.subject.keywordlinear regressionen_US
dc.subject.keywordmodel selectionen_US
dc.subject.keywordmodel validationen_US
dc.titleValidating linear restrictions in linear regression models with general error structureen_US
dc.type|aWorking Paperen_US

Files in This Item:
309.12 kB

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