資源描述:
《Asymptotic Theory for ARCH Models .pdf》由會(huì)員上傳分享,免費(fèi)在線閱讀,更多相關(guān)內(nèi)容在學(xué)術(shù)論文-天天文庫(kù)。
1、AsymptoticTheoryforARCHModels:EstimationandTestingAuthor(s):AndrewA.WeissReviewedwork(s):Source:EconometricTheory,Vol.2,No.1(Apr.,1986),pp.107-131Publishedby:CambridgeUniversityPressStableURL:http://www.jstor.org/stable/3532216.Accessed:19/12/201215:03YouruseoftheJSTORarchiveindica
2、tesyouracceptanceoftheTerms&ConditionsofUse,availableat.http://www.jstor.org/page/info/about/policies/terms.jsp.JSTORisanot-for-profitservicethathelpsscholars,researchers,andstudentsdiscover,use,andbuilduponawiderangeofcontentinatrusteddigitalarchive.Weuseinformationtechnologyandto
3、olstoincreaseproductivityandfacilitatenewformsofscholarship.FormoreinformationaboutJSTOR,pleasecontactsupport@jstor.org..CambridgeUniversityPressiscollaboratingwithJSTORtodigitize,preserveandextendaccesstoEconometricTheory.http://www.jstor.orgThiscontentdownloadedonWed,19Dec201215:
4、03:51PMAllusesubjecttoJSTORTermsandConditionsEconometiricTheoryS,2,107-131.PrintedintheUnitedStatesofAmerica.ASYMPTOTICTHEORYFORARCHMODELS:ESTIMATIONANDTESTINGANDREWA.WEISSUniversityofSouthernCaliforniaatLosAngelesInthecontextofalineardynamicmodelwithmovingaverageerrors,wecon-sider
5、aheteroscedasticmodelwhichrepresentsanextensionoftheARCHmodelintroducedbyEngle[4].Wediscussthepropertiesofmaximumlikeli-hoodandleastsquaresestimatesoftheparametersofboththeregressionandARCHequations,andalsothepropertiesofvarioustestsofthemodelthatareavailable.Wedonotassumethattheer
6、rorsarenormallydistributed.1.INTRODUCTIONWebeginwiththesituationinwhicharesearcherwishestomodelthehet-eroscedasticityinatimeseriesregression.Forthis,Engle[4]hasintroducedtheconceptofautoregressiveconditionalheteroscedasticity(ARCH).Thisisseenasanextensionoftimeseriesbehaviorintheme
7、an,allowingthevarianceoftheerrorstochangeiftheprocesstakesintoaccountpastex-periencebutassumesitconstantifthisexperienceisnotknown.Inaprocesswithstochasticregressors,whichisthecaseinmosttimeseriesprocesses,thiscorrespondstotheusualpropertiesofthemeanoftheoutputfromtheregressionmode
8、l.Henceitismoreappealingth