View : 521 Download: 0

Full metadata record

DC Field Value Language
dc.contributor.author강채련-
dc.creator강채련-
dc.date.accessioned2016-08-26T03:08:43Z-
dc.date.available2016-08-26T03:08:43Z-
dc.date.issued2001-
dc.identifier.otherOAK-000000002900-
dc.identifier.urihttps://dspace.ewha.ac.kr/handle/2015.oak/194338-
dc.identifier.urihttp://dcollection.ewha.ac.kr/jsp/common/DcLoOrgPer.jsp?sItemId=000000002900-
dc.description.abstract비정상 혹은 비선형 확률과정 미분방정식에서 정의된 이분산 dif-fusion process의 관심모수를 추정함에 있어 새로운 Instrumental Variable estimator를 생각한다. 제시된 IV estimator의 povotal quantity가 finite sam-ple에서도 exact Gaussian 분포를 갖기 때문에, IV estimator를 사용하여 관심 모수에 대한 exact confidence interval과 exact test를 수행할 수 있다. 본 논문에서는 이분산 diffusion prcoess에 대한 Monte-Carlo sim-ulation을 통해, 비정상 혹은 비선형 모형에서는 제안된 sign-type IV estimator가 기존의 최우추정법(maximum likeihood estimator)보다 유용함을 확인하고 있다. ; We consider a new instrumental variable (IV) estimator of the parameter of a class of heteroscedastic diffusion processes defined by the possibly non-stationary and/or nonlinear stochastic differential equations. Because the pivotal statistic of proposed estimator has an exact finite sample Gaussian distribution, we can construct the exact confidence intervals and the exact tests for the parameter θ. Monte-Carlo simulation for two heteroscedastic diffusion process shows that the proposed IV estimator seems to provide a useful alternative to the maximum likelihood estimator(MLE) for non-stationary and/or nonlinear processes.-
dc.description.tableofcontentsABSTRACT = v 1. Introduction = 1 2. Sign-type IV Estimator for the diffusion Model = 4 3. Finite Sample properties of Cauchy estimator = 7 4. Monte-Carlo simulation for general heteroscedastic non-linear diffusion model = 12 4.1 model 1 = 13 4.2 model 2: Log-Normal model = 20 5. Discussion = 28 APPENDIX A. = 29 1.1 Brownian Motion(Wiener) Process = 29 1.2 Properties = 30 1.3 Proof of Equivalence Lemma = 30 1.4 Girsanov Theorem = 31 APPENDIX B. C++ PROGRAM CODE = 32 REFERENCES = 39 국문초록 = 40-
dc.formatapplication/pdf-
dc.format.extent868233 bytes-
dc.languageeng-
dc.publisher이화여자대학교 대학원-
dc.titleA simulation study for heteroscedastic diffusion model-
dc.typeMaster's Thesis-
dc.identifier.thesisdegreeMaster-
dc.identifier.major대학원 통계학과-
dc.date.awarded2001. 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