View : 650 Download: 0

Full metadata record

DC Field Value Language
dc.contributor.advisor이외숙-
dc.contributor.author이정화-
dc.creator이정화-
dc.date.accessioned2016-08-26T04:08:55Z-
dc.date.available2016-08-26T04:08:55Z-
dc.date.issued2014-
dc.identifier.otherOAK-000000083616-
dc.identifier.urihttps://dspace.ewha.ac.kr/handle/2015.oak/210794-
dc.identifier.urihttp://dcollection.ewha.ac.kr/jsp/common/DcLoOrgPer.jsp?sItemId=000000083616-
dc.description.abstractThe Functional central limit theorem (FCLT) has played an important role in both statistical theory and practical application. In this paper, we consider the condition for the FCLT in the specific nonlinear time series model. Especially, Markov-swtiching ARMA-GARCH model is considered. We will establish the condition on the coefficients of model and one step transition probability of Markov chain. Stationarity and the FCLT will be proved under the condition. Several examples are given to compare the our condition to the existing condition for the FCLT for the model.;본 논문에서는 마코브 스위칭을 가지는 비선형모형인 Markov-switching ARMA-GARCH (MS-ARMA-GARCH) 모형을 대상으로 Fucntional Central Limit Theorem (FCLT) 이 성립하는 조건을 찾는다. 이를 위해 모형의 계수행렬과 마코브 체인의 1단계 전이확률에 조건을 부과하며 이 조건에서 모형의 정상성과 FCLT 가 성립하는 지를 확인한다. 이 조건을 만족하는 MS-ARMA-GARCH 모형을 실제로 구해보고, 기존의 다른 조건과 이를 비교해 본다.-
dc.description.tableofcontents1. Introduction 1 2. Preliminary and Assumptions 4 3. Sufficient Condition for Stationarity 9 4. Sufficient Condition for The Functional Central Limit Theorem 14 5. Examples 23 References 28 논문초록 29 감사의 글 30-
dc.formatapplication/pdf-
dc.format.extent887051 bytes-
dc.languageeng-
dc.publisher이화여자대학교 대학원-
dc.subject.ddc500-
dc.titleThe Functional Central Limit Theorem in Markov-switching ARMA-GARCH model-
dc.typeMaster's Thesis-
dc.format.pagev, 30 p.-
dc.identifier.thesisdegreeMaster-
dc.identifier.major대학원 통계학과-
dc.date.awarded2014. 2-
Appears in Collections:
일반대학원 > 통계학과 > Theses_Master
Files in This Item:
There are no files associated with this item.
Export
RIS (EndNote)
XLS (Excel)
XML


qrcode

BROWSE