Please use this identifier to cite or link to this item: http://hdl.handle.net/10419/19022
Full metadata record
DC FieldValueLanguage
dc.contributor.authorEgger, Peteren_US
dc.contributor.authorLarch, Marioen_US
dc.contributor.authorPfaffermayr, Michaelen_US
dc.contributor.authorWalde, Janette F.en_US
dc.date.accessioned2009-01-28T15:54:31Z-
dc.date.available2009-01-28T15:54:31Z-
dc.date.issued2005en_US
dc.identifier.urihttp://hdl.handle.net/10419/19022-
dc.description.abstractThis paper undertakes a Monte Carlo study to compare MLE-based and GMM-based testsregarding the spatial autocorrelation coefficient of the error term in a Cliff and Ord typemodel. The main finding is that a Wald-test based on GMM estimation as derived by Kelejianand Prucha (2005a) performs surprisingly well. Our Monte Carlo study indicates that theGMM Wald-test is correctly sized even in small samples and exhibits the same power as theirMLE-based counterparts. Since GMM estimates are much easier to calculate, the GMMWald-test is recommended for applied researches.en_US
dc.language.isoengen_US
dc.publisher|aCenter for Economic Studies and Ifo Institute (CESifo) |cMunichen_US
dc.relation.ispartofseries|aCESifo working papers |x1558en_US
dc.subject.jelC12en_US
dc.subject.jelR10en_US
dc.subject.jelC21en_US
dc.subject.ddc330en_US
dc.subject.keywordspatial autocorrelationen_US
dc.subject.keywordhypothesis testsen_US
dc.subject.keywordMonte Carlo studiesen_US
dc.subject.keywordmaximum likelihood estimationen_US
dc.subject.keywordgeneralized method of momentsen_US
dc.subject.stwMaximum-Likelihood-Methodeen_US
dc.subject.stwMomentenmethodeen_US
dc.subject.stwAutokorrelationen_US
dc.subject.stwStatistischer Testen_US
dc.subject.stwTheorieen_US
dc.titleSmall sample properties of maximum likelihood versus generalized method of moments based tests for spatially autocorrelated errorsen_US
dc.typeWorking Paperen_US
dc.identifier.ppn503677639en_US
dc.rightshttp://www.econstor.eu/dspace/Nutzungsbedingungen-

Files in This Item:
File
Size
376.87 kB





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