Analysis of correlation matrice, copula and Epps effect in stock market for various time intervals = 시간 간격에 따른 주식시장의 연관행렬 및 코플라, 엡스 효과 분석

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 358
  • Download : 0
Analysis of correlation matrice with Random matrix theory(RMT) is well known in daily stochastic data. We conduct making correlation matrice in various time intervals, different from the previous study. RMT is also available in most of cases using the various time intervals, but the components of $u^{largest}$ has different shapes of distributions as time intervals change. It is effective not in short time intervals but in long time intervals. Also, the shifts of pdf of coefficients support the same conjecture. The largest eigenvalues show Epps effect, but not enough to explain due to the change of $u^{largest}$ . The dependence structure of Cook-Johnson copula relies on a copula parameter, and the increase of a copula parameter makes sure the structure of correlation matrix stronger as time interval increases. They imply an anlysis for correlation matrix requires the time interval long enough with RMT, and multiasset Epps effect is also available.
Advisors
Kim, Soo-yongresearcher김수용researcher
Description
한국과학기술원 : 물리학과,
Publisher
한국과학기술원
Issue Date
2010
Identifier
418984/325007  / 020063024
Language
eng
Description

학위논문(석사) - 한국과학기술원 : 물리학과, 2010.2, [ v, 43 p. ]

Keywords

copula; Epps effect; 연관행렬; 코플라; 엡스 효과; correlation matrix

URI
http://hdl.handle.net/10203/48750
Link
http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=418984&flag=dissertation
Appears in Collection
PH-Theses_Master(석사논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0