滬深股市之間的相關性分析－利用MMBP方法估計Copula-t-GARCH模型

Dependence Analysis of China Stock Markets-MMBP Algorithm to Estimate Copula-t-GARCH Models

10.6704/JMSSD.2009.6.1.25

劉金全(Jin-Quan Liu)；王雄威(Xiong-Wei Wang)；張營(Ying Zhang)

Copula ； t-GARCH ； MMBP ； 相關性 ； Copula ； t-GARCH ； MMBP ； dependence

管理科學與統計決策

6卷1期（2009 / 03 / 01）

25 - 34

繁體中文

在金融市場風險管理分析中，如何有效的估計金融市場間的相關性是重要的一個環節。中國滬深股市高度相關，且中國滬深股市收益率序列並不滿足人們常常假設的Normal-GARCH模型。本文嘗試使用殘差項滿足t分佈的Copula-t-GARCH模型，並結合使用MMBP估計方法對中國滬深股市相關關係進行估計。分析結果表明：Copula-t-GARCH模型能夠更好的捕捉金融市場間相關性變換規律，且MMBP方法較傳統的兩步估計方法(IFM)更加有效。

Estimating financial market dependence efficiently is very important in the finance market risk management. In China, Shanghai stock market and Shenzhen stock market are highly relevant, and the returns do not meet the hypothesis that it follows the Normal-GARCH model. In this paper, we used Modified Maximization by Parts (MMBP) algorithm and t-GARCH (1, 1) model to estimate the relationship between Shanghai stock market and Shenzhen stock market. The result shows that Copula-t-GARCH model could better capture the relationship in finance market, and MMBP algorithm is better than the traditional IFM method.

1. Bartram, S.M.,Taylor, S.J.,Wang, Y.-H.(2007).The euro and European financial market dependence.Journal of Banking and Finance,31,1461-1481.
2. Bollerslev, T.(1986).Generalized autoregressive conditional heteroskedasticity.Journal of Econometrics,31,307-327.
3. Colm, K.,Patton, A.J.(2000).Multivariate GARCH modeling of exchange rate volatility transmission in the european monetary system.The Financial Review,41,29-48.
4. Fan, Y.,Pastorello, S.,Renault, E.(2007).Maximization by parts in extremum estimation.
5. Hotta, L K,Helder Palaro.(2006).Using Conditional Copulas to Estimate Value at Risk.Journal of Data Science,4(1),93-115.
6. Joe, H.,Xu, J.J.(1996).Technical Report 166, Department of StatisticsTechnical Report 166, Department of Statistics,University of British Columbia.
7. Jondeau, E.,Rockinger, M(2002).Conditional Dependency of Financial Series: The Copula-GARCH Model.FAME Research Paper Series rp 69, International Center for Financial Asset Management and Engineering.
8. Jondeau, E.,Rockinger, M(2001).Gram-Charlier densities.Journal of Economic Dynamics and Control, Elsevier,25(10),1457-1483.
9. Jondeau, E.,Rockinger, M.(2006).The Copula-GARCH model of conditional dependencies: An international stock market application.Journal of International Money and Finance,25,827-853.
10. Lee, T.H.,X. Long.(2007).Copula-based Multivariate GARCH Models with Uncorrelated Dependent Errors.Journal of Econometrics
11. Liu, Y.,Luger, R.(2008).Efficient estimation of Copula-GARCH models.Computational Statistics and Data Analysis.
12. Nelsen R B.(2005).An introduction to Copulas.New York:Springer.
13. Patton, A.J.(2006).Estimation of multivariate models for time series of possibly different lengths.Journal of Applied Econometrics,21,147-173.
14. Song, P.X.-K.,Fan, Y.,Kalbfleisch, J.D.(2005).Maximization by parts in likelihood inference.Journal of the American Statistical Association,100,1145-1158.
15. Umberto Cherubini.,Elisa Luciano,Walter Vecchiato(2004).Copula Methods in Finance.New York:Wiley.
16. 韋豔華、張世英(2007)。多元Copula-GARCH模型及其在金融風險分析上的應用。數理統計與管理，3
17. 張堯庭(2002)。連接函數(Copula)技術與金融風險分析。統計研究，4