資源描述：
《on the asymptotic properties of some seasonal unit root tests》由會(huì)員上傳分享，免費(fèi)在線閱讀，更多相關(guān)內(nèi)容在工程資料-天天文庫(kù)。
1、BootstrappingUnitRootTestsforAutoregressiveTimeSeriesAuthor(s):EfstathiosPaparoditisandDimitrisN.PolitisReviewedwork(s):Source:JournaloftheAmericanStatisticalAssociation,Vol.100,No.470(Jun.,2005),pp.545-553Publishedby:AmericanStatisticalAssociationStableURL:http:/
2、/www.jstor.org/stable/27590576.Accessed:01/12/201208:59YouruseoftheJSTORarchiveindicatesyouracceptanceoftheTerms&ConditionsofUse,availableat.http://www.jstor.org/page/info/about/policies/terms.jsp.JSTORisanot-for-profitservicethathelpsscholars,researchers,andstude
3、ntsdiscover,use,andbuilduponawiderangeofcontentinatrusteddigitalarchive.Weuseinformationtechnologyandtoolstoincreaseproductivityandfacilitatenewformsofscholarship.FormoreinformationaboutJSTOR,pleasecontactsupport@jstor.org..AmericanStatisticalAssociationiscollabor
4、atingwithJSTORtodigitize,preserveandextendaccesstoJournaloftheAmericanStatisticalAssociation.http://www.jstor.orgThiscontentdownloadedbytheauthorizeduserfrom192.168.52.78onSat,1Dec201208:59:51AMAllusesubjecttoJSTORTermsandConditionsBootstrappingUnitRootTestsforAut
5、oregressiveTimeSeriesEfstathiosPaparoditisandDimitrisN.PolitisThetheorydevelopedforbootstrappingunitroottestsinanautoregressive(AR)contexthasbeenconcernedmainlywiththelarge-samplebehaviorofthemethodsproposedundertheassumptionthatthenullhypothesisistrue.Noresultsex
6、istfortherelativeperformanceandthepowerbehaviorofthebootstrapmethodsunderthealternative.ThisarticlestudiesthepropertiesofdifferentARbootstrapschemesoftheunitroothypothesis,includinganewproposalbasedonunrestrictedresiduals.Itshowsthatbootstrapproceduresbasedondiffe
7、rencingtheobservedseriessufferfrompowerproblemsascomparedwithbootstrapproceduresbasedonunrestrictedresiduals.WhereasforfiniteorderARprocessesdifferencingleadstojustalossofpower,forinfinite-orderautoregressionssuchadifferencingmakestheapplicationofsieveARbootstraps
8、chemesinappropriateifthealternativeistrue.Thesuperiorityofthenewbootstrapproposalisshown,andsomenumericalexamplesillustrateourtheoreticalfindings.KEYWOR
