[논문]Dependence Structure of Korean Financial Markets Using Copula-GARCH Model

Kim, Woohwan

doi:10.5351/csam.2014.21.5.445

Dependence Structure of Korean Financial Markets Using Copula-GARCH Model 원문보기

Communications for statistical applications and methods = 한국통계학회논문집, v.21 no.5, 2014년, pp.445 - 459

Kim, Woohwan (Financial Research & Implementation)

Abstract ▼ AI-Helper

This paper investigates the dependence structure of Korean financial markets (stock, foreign exchange (FX) rates and bond) using copula-GARCH and dynamic conditional correlation (DCC) models. We examine GJR-GARCH with skewed elliptical distributions and four copulas (Gaussian, Student's t, Clayton and Gumbel) to model dependence among returns, and then employ DCC model to describe system-wide correlation dynamics. We analyze the daily returns of KOSPI, FX (WON/USD) and KRX bond index (Gross Price Index) from $2^{nd}$ May 2006 to $30^{th}$ June 2014 with 2,063 observations. Empirical result shows that there is significant asymmetry and fat-tail of individual return, and strong tail-dependence among returns, especially between KOSPI and FX returns, during the 2008 Global Financial Crisis period. Focused only on recent 30 months, we find that the correlation between stock and bond markets shows dramatic increase, and system-wide correlation wanders around zero, which possibly indicates market tranquility from a systemic perspective.

주제어

AI 본문요약
AI-Helper

* AI 자동 식별 결과로 적합하지 않은 문장이 있을 수 있으니, 이용에 유의하시기 바랍니다.

문제 정의

This paper investigates the dependence structure of Korean financial markets using copula-GARCH and dynamic conditional correlation models. We examine GJR-GARCH with skewed elliptical distributions and four copulas (Gaussian, Student’s t, Clayton and Gumbel) to model dependence among returns incorporating marginal specific characteristics, and then employ DCC model for describing correlation dynamics.

제안 방법

This paper considers four candidates to model innovations: normal, Student’s t, skew-normal and skew-t distributions.
kr. To better understand the impact of GFC to Korean markets, we construct two sub-samples, named as GFC and Recent. The GFC is ranged from 2^nd January 2008 to 30^thDecember 2009 (500 observations) and Recent is from 2^nd January 2012 to 30^th June 2014 (616 observations).
To decide the best model for describing heteroskedasticity, we mainly examine GARCH and GJRGARCH with normal, t, skew-normal and skew-t distributions. The following results are obtained using R package rugarch.
To improve our understanding of dependence structure over time and find out why the parameter estimates of Clayton and Gumbel copulas are unable to obtain in previous sub-section, we conduct rolling window analysis and exponentially weighted moving average (EWMA) correlation. We use 252-day (approximately one year) moving windows rolling analysis based on Pearson’s correlation coefficient.
We examine GJR-GARCH with skewed elliptical distributions and four copulas (Gaussian, Student’s t, Clayton and Gumbel) to model dependence among returns incorporating marginal specific characteristics, and then employ DCC model for describing correlation dynamics.

데이터처리

We use 252-day (approximately one year) moving windows rolling analysis based on Pearson’s correlation coefficient.

이론/모형

Under the standard regularity condition, it is well-known that two-stage method yields the consistent and asymptotically normal estimator. The copula selection is based on Bayesian information criterion (BIC). For more details on parameter estimation and copula selection, see Joe (1997) and Nelsen (2006).
For practical application, we need to estimate copula parameters and select a best copula based on given data. This paper applies two-stage approach to obtain the parameter estimates in copula GARCH models. We decide each marginal distribution using GARCH models and then apply PIT to each return, in the first stage.
(2013). This paper employs copula-GARCH model to investigate the dependence structure of Korean financial markets, stock, foreign exchange (FX) rates and bond. We employ standard GARCH of Bollerslev (1986) and GJR-GARCH of Glosten et al.

참고문헌 (15)

Alouia, R., Aissa, M. S. B. and Nguyen, D. K. (2013). Conditional dependence structure between oil prices and exchange rates: A copula-GARCH approach, Journal of International Money and Finance, 32, 719-738.

상세보기
Bollerslev, T. (1986). Generalized autoregressive conditional heteroskedasticity, Journal of Econometrics, 31, 300-328.
Dobric, J. and Schmid, F. (2005). Nonparametric estimation of the lower tail dependence in bivariate copulas, Journal of Applied Statistics, 32, 387-407.

상세보기
Engle, R. F. (2002). Dynamic conditional correlation: A simple class of multivariate GARCH models, Journal of Business and Economic Statistics, 20, 339-350.

상세보기
Glosten, L. R., Jagannathan, R. and Runkle, D. (1993). On the relation between the expected value and the volatility of the nominal excess return on stocks, Journal of Finance, 48, 1779-1801.

상세보기
Hillebrand, E. (2005). Neglecting parameter changes in GARCH models, Journal of Econometrics, 129, 121-138.

상세보기
Huang, J. J., Lee, K. J., Liang, H. and Lina, W. F. (2009). Estimating value at risk of portfolio by conditional copula-GARCH method, Insurance: Mathematics and Economics, 45, 315-324

상세보기
Joe, H. (1997). Multivariate models and dependence concepts, Monographs in Statistics and Probability 73, Chapman and Hall, London.
Jondeau, E. and Rockinge, M. (2006). The Copula-GARCH model of conditional dependencies: An international stock market application, Journal of International Money and Finance, 25, 827-853.

상세보기
Liu, Y. and Luger, R. (2009). Efficient estimation of copula-GARCH models, Computational Statistics & Data Analysis, 53, 2284-2297.

상세보기
Marshal, R. and Zeevi, A. (2002). Beyond correlation: Extreme comovements between financial assets, Working Paper, Columbia Business.
Mikosch, T. and Starica, C. (2004). Nonstationarities in financial times series, the long range dependence and the IGARCH effects, The Review of Economics and Statistics, 86, 378-390.

상세보기
Nelsen, R. B. (2006). An Introduction to Copulas, Springer, Second edition, New York.
Pesaran, B. and Pesaran, M. H. (2007). Modelling volatilities and conditional correlations in futures markets with a multivariate t distribution, Cambridge Working Papers in Economics 0734.
RiskMetrics. (1996). RiskMetrics TM Technical Document, Fourth edition, J.P. Morgan/Reuters.

LOADING...

내보내기 구분	파일저장 인쇄 메일전송
구성항목	기본정보 상세정보 관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관 관리번호, 논문명, 대등논문명, 저자 , 저널/프로시딩명, 발행기관, 발행년, 발행언어, 권, 호, 시작페이지, 끝페이지, ISBN, ISSN, 주제분야, 키워드, 초록(한글), 초록(영문), 저자(소속기관)
저장형식	Text(ASCII format) Excel format RefWorks Direct Export RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley
메일정보	받는사람 (필수) @ 보내는사람 (선택) @ 제목 내용 KISTI 검색결과 이메일 서비스
안내	총 건의 자료가 검색되었습니다. 다운받으실 자료의 인덱스를 입력하세요. (1-10,000) 검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다. 데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요) 다운로드 파일은 UTF-8 형태로 저장됩니다. 파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오. ~ Text(ASCII format) Excel format

연합인증