摘要
在金融全球化的背景下,金融市场的各个组成部分存在密切的关联性,一个市场的价格变化会引起另一个市场的联动性反应,多个市场间的相依性分析由此成为金融学中的一个中心问题。相依性分析方法中,传统的线性相关系数只能描述变量间的线性相依关系。因此,能较好地捕获变量间非线性相依关系的Copula技术成为当前流行的分析方法。
本文对以Copula为核心技术的相依性模型进行了比较深入的研究。在理论上,本文将结构系统的可靠度理论融入金融系统,提出了破产风险计算的两类模型,给出了银行系统相关性可靠度的Copula计算模型,并通过抽样样本银行系统的实例计算说明了该理论方法的可行性。
在方法上,本文对时变Copula的演化方程进行改进。本文基于Patton的条件t-Copula时变参数的演化方程,结合Bartram,Taylor和Wang的时变高斯Copula演化方程,提出了三个同时包含自相关历史项和两个变量累积概率历史项之差的绝对值的演化方程作为时变t-Copula参数的演化方程,通过实证分析说明了该演化方程的适当性。本文采用基于Monte Carlo数值模拟技术的Copula-CVaR风险评估模型讨论Copula函数的选择对投资决策的影响,实证检验说明根据该模型进行资产选择可以使投资者的资产选择更加稳健。
最后在应用上,本文采用了以Copula为核心的多种相依性研究方法对金融市场主要是股票市场、外汇市场的相依性问题进行了比较全面的实证,取得了一些有价值的研究结论。一方面,本文依次从信息传导、波动溢出和相关模式的角度对我国股票市场的相依性进行了实证研究,结果发现我国沪、港股票市场之间的收益信息传导不明显,同时两地的波动溢出也不显著,两地股市联动性程度小,上海股市的波动具有相对的独立性。这说明我国股市的开放程度尚低,不过在世界金融危机的时候这种谨慎的开放步伐对于我国的股票市场是一种保护。另一方面,本文采用相依性研究的计量模型、分别从宏观和中观的角度实证检验了我国外汇市场和股票市场联动性。本文主要研究了人民币升值以来汇率与中国沪深两市主要股票指数之间的相互关系。结果表明长期运行关系来说,汇率与各主要股指有稳定的均衡关系。短期波动来说,汇率仅对A股指数有单向的Granger因果传递关系。这一系列结果基本符合金融学理论的解释和预期。同时也说明,汇率制度改革之后,汇率市场的变化对股票市场的波动有一定的引导作用,股票市场的投资者应该关注人民币汇率的短期波动对股票市场的影响。本文的研究对金融风险管理和投资决策具有一定的参考价值。
On the background of financial globalization, the correlation among various components of financial markets become closer, price fluction in one market will cause another market's linkage response, dependency analysis between different markets men become a central issue of Finance. Among dependency analysis methods, the traditional linear correlation coefficient can only describe the linear dependencies between variables. Therefore, Copula techinique which can better capture the nonlinear dependencies between the variables become a popular method.
Dependency models which used Copula as a core technology are deeply studied. In theory, reliability theory of the structural systems is transferred into the financial systems, then two types of bankruptcy risk calculation model are proposed, then Copula calculation model of the relevance reliability of the banking system is given, finally, example calculation of sample banking system shows that the approach is feasible.
In the method, the evolution equation of time-varying Copula is improved. Based on Patton's conditional t-Copula evolution equation with time-varying parameters, combined with Bartram, Taylor & Wang's time-varying Gaussian Copula evolution equation, three new evolution equations that contain both lagged autocorrelation items and the absolute difference between the lagged cumulative probabilities of the two variables are proposed. The empirical analysis shows that the evolution equations are appropriate. Copula-CVaR risk assessment model based on Monte Carlo simulation techniques is used to discuss the impact of the choice of Copula function on investment decisions. Empirical test shows that a choice of assets under the model allows investors to choose more stable assets.
Finally, used Copula as a core technique , supplemented by other dependency research methods , comprehensive empirical research on the financial market, mainly on stock markets and the foreign exchange markets are conducted and some valuable results are found. On the one hand, the dependence degree of china's stock market is analyzed from the sight of information transmission, volatility spillover and dependence seperately. The empirical results show that return information transmission between Hu、Gang stock market is not significant, the spillover between these two stock markets is also not significant and the correlation between them is small, the volatility of mainland's stock market has its relative independence. This tests that the openness degree of china's stock market is low, however, this openness speed is a kind of protection for china's stock market. On the other hand, Connection degree between exchange rate market and stock market is also analyzed. Mainly, long-term and short-term correlation between exchange rate market and stock market after the exchange rate regime transformation are studied. It is showed that there is long-term equilibrium correlation between exchange rate and the main stock index, however, there is only one directional short-term Granger causality relation from RMB exchange rate to the A-shares index. These results are consistent with the explanation based on the financial theory, at the same time, this tests that the short term change of exchange rate market has some conductive meaning to fluction of stock market, which deserves the investor's attention. This study has some important reference value to financial risk management and investment decisions.
引文
[1]Aggarwal.R.Exchange Rate and Stock Prices:A Study of the US Capital Markets Under Floating Exchange Rate.Akron Business and Economic Review,1981,3:13-35
[2]Ajayi,R.A.,Mougoue,M.On the dynamic relation between stock prices and exchange rates.Journal of Financial Research,1996(19):93-207.
[3]Baek E,Brock W.A Nonparametric Test for Independence of a Multivariate Time Series.Statistica Sinica,1992,2:137-156
[4]Bahmani,Oskooee,M.,Sohrabian,A.Stock prices and the effective exchange rate of the dollar.Applied Economics,1992,24:459-464.
[5]Banwens,L.,S.Laurent and J.Rombouts.Multivariate GARCH Models:A Survey,Journal of Applied Econometrics,2006,21:79-109
[6]Bartram,S.M.,Taylor,S.J.,Wang,Y.-H.The Euro and European financial market dependence.Journal of Banking & Finance,2007,31:1461-1481
[7]Becker,K.G.,Finnerty,J.E.,Gupta,M.The intertemporal relation between the U.S.and Japanese stock markets.Journal of Finance,1990,45:1297-1306.
[8]Bodart,V.,Redding,P.Exchange Rate Regime,Volatility and International Correlations on Bond and Stock Markets.Journal of International Money and Finance,1999,18:133-151.
[9]Bouye,E.,Ganssel,N.and Salmon,M.Investigating Dynamic Dependence Using Copula.Manuscript,Financial Econometrics Research Center.2002
[10]Calvo,Sarah,and Carmen M.Reinhart.Capital flows to Latin America:Is there evidence of contagion effects? in Guillermo A.Calvo,Morris Goldstein,and Eduard Hochreiter,eds.:Private Capital Flows to Emerging Markets After the Mexican Crisis(Institute for International Economics,Washington,DC) 1996
[11]Chen,X.,Fan,Y.Estimation of Copula-based Semiparametric Time Series Models.Journal of Econometrics.2006a,130:307-335
[12]Chen,X.,Fan,Y.Estimation and Model Selection of Semiparametric Copula-based Multivariate Dynamic Models under Copula Misspecification. Journal of Econometrics.2006b,135:125-154
[13]Chen,Lee and Rui.Foreign Ownership Restrictions and Market Segmentation in China's Stock Markets.Journal of Financial Research,2001,24(1):133-155.
[14]Cherubini,U.and E.Luciano,Value at Risk trade-off and capital allocation with Copulas,Economic Notes.2004,30:235-256
[15]Chollete,L.Frequent extreme events? A dynamic Copula approach,mimeo,Norwegian School of Economics and Business,2005
[16]Chow G.C.China's Economic Reform and Policies at the Beginning of the Twenty-first Century.China Economic Review,2000,11(4):427-431
[17]Chui and Kwok.Cross-autocorrelation between A shares and B Shares in the Chinese Stock Market.Journal of Financial Research,1998,21:333-53
[18]Darrat,A.F.,Rahman,S.,Zhong,M.Intraday Trading Volume and Return Volatility of the DJIA Stocks:A note.Journal of Banking & Finance,2003,27:2035-2043.
[19]De Santis,G.,Gerard,B.,Hillion,P.The Relevance of Currency Risk in the EMU.Unpublished Norwegian School of Management Working Paper.2002.
[20]Desislava Dimitrova.The Relationship between Stock Price and Exchange Rates:Studied in Multivariate Model.Polital economy,2005(14):139-162
[21]Diebold F.X.,Hahn J.,Tay A.S.Multivariate Density Forecast Evaluation and Calibration in Financial Risk Management:High-frequency Returns on Foreign Exchange.The Review of Economics and Statistics,1999,81(4):661-673.
[22]Dimakos,X.and Aas,K.Integrated Risk Modeling.Statistical Modeling,2004,4:265-277.
[23]Ditlevsen O.Narrow reliability bounds for structural system.Mechanics Based Design of Structures and Machines,1979,7(4):453-472
[24]Dorey M,Joubert P.Modelling Copulas:An Overview.Working Paper,2005
[25]Dombusch,R.,Fischer,S.Exchange Rates and Current Account.American Economic Review,1980,70:960-971.
[26]Embrechts,P.and A.H(o|¨)ing.Extreme VaR scenarios in higher dimensions,mimeo,ETH Z(u|¨)rich,2006
[27]Embrechts,P.,Lindskog,F.,McNeil,A.Modeling Dependence with Copulas and Applications to Risk Management.Handbook of Heavy Tailed Distributions in Finance,Elsevier,Rotterdam,2003.329-384.
[28]Embrechts,P.,McNeil,A.Straumann,D.Correlation:Pitfalls and Alternatives.Risk,1999,12:69-71.
[29]Engle,R.F.Dynamic conditional correlation——A Simple Class of Multivariate GARCH Models.Journal of Business and Economic Statistics,2002,3:339-350.
[30]Eun,C.,Shim,S.International Transmission of Stock Market Movements.Journal of Financial and Quantitative Analysis,1989,24:241-256.
[31]Fantazzini,D.Dynamic Copula modelling for Value at Risk,working paper,2006
[32]Flood,R.P.,Rose,A.K.Fixing Exchange Rates:A Virtual Quest for Fundamentals.Journal of Monetary Economics.1995,36:3-37.
[33]Fung,Lee and leung.Segmentation of the A- and B- Share Chinese equity Market.Journal of Financial Research,2000,23:179-195
[34]Fratianni,M.,von Hagen,J.The European Monetary System Ten Years after Carnegie-Rochester Conference Series on Public Policy.1990,32:173-242.
[35]Frey,R.,McNeil,A.Modeling Dependent Defaults.Journal of Risk,2003,6(1):59-92.
[36]Genest C.,Rivest,L.P.Statistical Inference Procedures for Bivariate Archimedean Copulas.J.Amer.Statist.Assoc.1993,88:1034-1043
[37]Granger,C.Investigating Causal Relations by Econometric Models and Crossspectral Methods.Econometric,a,1969,37:424-438.
[38]Granger,C.W.Testing for Causality:A Personal View.Journal of Economic Dynamics and Control,1980,2:329-352.
[39]Gumbel.E.J.Multivariate extreme distributions.Bulletin of the International Statistical Institute,1960,39(2):471-475.
[40]Hansen,B.E.Autoregressive Conditional Density Estimation.International Economic Review,1994,35:5-30.
[41]Hamao,Y.,Masulis,R.W.,and Ng,V.Correlation in Price Changes and Volatility across International Stock Markets.Review of Financial Studies,1990,3:5-33.
[42]Hardouvelis,G.,Malliaropulos,D.,Priestley,R.EMU and European Stock Market Integration.Unpublished National Bank of Greece Working Paper.1999
[43]Hasbrouck.Measuring the Information Content of Stock Trades.Journal of Finance,1991,46:179-207.
[44]Hiemsta C,Jones J D.Testing for Linear and Nonlinear Granger Causality in the Stock Price-volume Relation.Journal of Finance,1994,54(5):1639-1664
[45]Hong Yongmaio.A Test for Volatility Spillover with Application to Exchange Rates.Journal of Econometrics,2001,103:183-224.
[46]Huard D,Evin G,Favre A.C.Bayesian Copula Selection.Computational Statistics & Data Analysis 2006,51:809-822
[47]Hyuk Choe,Bong-Chan Kho,and Rene M.Stulz.Do Foreign Investors Destabilize Stock Markets? The Korean Experience in 1997,NBER Working Papers 6661,1998,National Bureau of Economic Research,Inc.
[48]Jain.D.,Singh.V.P.A comparison of transformation methods for flood frequency analysis.Water Resource Bulletin,1986,22(6):903-912.
[49]Jondeau,E.,Rockinger,M.The Copula-GARCH model of conditional dependencies:An international stock market application,Journal of International Money and Finance,2006,25:827-853
[50]Joe,H.Multivariate Models and Dependence Concepts.Chapman & Hall.1997
[51]Jose,E.R.,David,W.C.A Monte-Carlo simulation approach for approximating multi-terminal reliability.Reliability Engineering and System Safety,2005,87:253-264
[52]Junker,M.,May,A.Measurement of Aggregate Risk with Copulas.Econometrics Journal,2005,8:428-454
[53]Kandel and Stambaugh.A Mean-Variance Framework for Tests of Asset Pricing Models.Review of Financial Studies,1989,2:125-156
[54]Kim,G,Silvapulle,M.J.,Silvapulle,P.Comparison of Semiparametric and Parametric Methods for Estimating Copulas.Computational Statistics & Data Analysis,2007,51:2836-2850
[55]Kole,E.,Koedijk,K.,Verbeek,M.Selecting Copulas for Risk Management,Journal of Banking & Finance,2007,31(8):2405-2423
[56]Kolev,Anjos,Mendes.Copulas:A Review and Recent Developments.Stochastic Models,2006,22:617-660
[57]Krueger,A.Protectionism,Exchange Rate Distortions,and Agricultural Trading Patterns.American Journal of Agricultural Economics,1983,65(5):864-871
[58]Lee,T.-H,.Long,X.Copula-based multivariate GARCH model with uncorrelated dependent standardized returns,mimeo,University of California,Riverside,2005
[59]Lin,W.,Engle,R.,Ito,T.Do Bulls and Bears Move across Borders? International Transmission of Stock Returns and Volatility.Review of Financial Studies,1994,7:507-538.
[60]Morton,R.C.On the Pricing of Corporate Debt:The Risk Structure of Interest Rates[J].Journal of Finance,1974,29(2):449-470.
[61]Morley,B.,Pentecost E.J.Common Trends and Cycles in G-7 Countries Exchange Rates and Stock Prices.Applied Economics Letters,2000,7,(1):7-10.
[62]Murinde,V.,Poshakwale,S.Exchange Rate and Stock Price Interactions in European Emerging Financial Markets before and after the Euro.2004,Paper presented in the 2004 FEMA annual meeting held in Basel,Switzerland on June 30-July3.
[63]Nelsen,R.An Introduction to Copulas.Springer,New York.1999
[64]Okimoto,T.New Evidence of Asymmetric Dependence Structure in International Equity Markets:Further Asymmetry in Bear Markets,mimeo,Yokohama National University,2006
[65]Padhan,P.C.The Dynamic Relationship between Stock Price and Exchange Rate In India.Journal of Monetary Economics,Icfai press,2006(3):26-36
[66]Paradlwrter H J,PellissettiM F.Realistic and efficient reliability estimation for aerospace structures.Computer Methods in Applied Mechanics and Engineering,2005,194:1597-1617
[67]Patton,A.J.Modeling Time-varying Exchange Rate Dependence using the Conditional Copula.Working Paper,San Diego:Department of Economics,University of California,2001.
[68]Patton,A.J.Applications of Copula Theory in Financial Econometrics,Unpublished Ph.D.dissertation,University of California,San Diego,2002.
[69]Patton,AJ.On the Out-of-Sample Importance of Skewness and Asymmetric Dependence for Asset Allocation.Journal of Financial Econometrics,2004,20):130-168.
[70]Patton,A.J.Modelling Asymmetric Exchange Rate Dependence.International Economic Review,2006a,47(2):527-556.
[71]Patton,A.J.Estimation of Multivariate Models for Time Series of Possibly Different Lengths,Journal of Applied Econometrics,2006b,21(2):147-173.
[72]Rigobon,Roberto.Informational speculative attacks:good news is no news,1998,MIT Mimeo
[73]Rodriguez,J.C.Measuring financial contagion:A Copula approach.Journal of Empirical Finance,2007,14:401-423
[74]Rosenberg,J.,Schuermann,T.A General Approach to Integrated Risk Management with Skewed,Fat-tailed Risk.2005,FRB of New York Staff Report No.185
[75]Schwettzer B,Wolff E.On nonparametric measures of dependence for random variables[J].Annals of Statistics.1981,9:879-885.
[76]Shanken.Statistical Methods in Tests of Beta-Pricing Models:a Synthesis.Handbook of Statistics:Statistical Methods in Finance,North-Holland,Amsterdam,1996,14:693-711.
[77]Sjoo,Zhang.Market Segmentation and Information Diffusion in China's Stock Markets.Journal of Multinational Financial Management,2000,10:421-438.
[78]Sklar,A.Fonctions de Repartition a n Dimensions et Leurs Marges.Publications de 1' Institut de Statistique de 1' Universite de Paris,1959,8:229-231.
[79]Stuart,C.An Introduction to Statistical Modeling of Extreme Values.Springer,2001
[80]Tabak,B.M.The Dynamic Relationship between Stock Price and Exchange Rate:evidence for Brazil.The Banco Central do Brazil working paper,novmember,2006
[81]冯鹏熙.我国商业银行资产负债管理的实证研究[D].华中科技大学,2006
[82]龚朴,黄荣兵.外汇资产的时变相关性分析[J].系统工程理论与实践,2008(8):26-37
[83]谷耀、陆丽娜.沪、深、港股市信息溢出效应与动态相关性[J].数量经济技术经济研究,2006(8):142-151
[84]何旭彪.VaR风险耦合理论模型、数值模拟技术及应用研究[D].华中科技大学,2005
[85]李秀敏,史道济.金融市场组合风险的相关性研究[J].系统工程理论与实践,2007(2):112-117
[86]李悦,程希骏.上证指数和恒生指数的Copula尾部相关性分析[J].系统工程,2006(5):88-92
[87]刘志东.基于Copula-GARCH-EVT的资产组合选择模型及其混合遗传算法[J].系统工程理论方法应用.2006(2):149-157
[88]刘金全,崔畅.中国沪深股市收益率和波动性的实证分析[J].经济学(季刊),2002(7):885-898
[89]罗付岩,邓光明.基于时变Copula的VaR估计[J].系统工程,2007(8):28-33
[90]吕江林,李明生,石劲.人民币升值对中国股市影响的实证分析[J].金融研究,2007(6):23-34
[91]芮延年,傅戈雁.现代可靠性设计[M].北京:国防工业出版社,2007
[92]史道济,邸男.关于外汇组合风险相关性的分析[J].系统工程,2005(6):90-94
[93]史道济,姚庆祝.改进Copula对数据拟合的方法[J].系统工程理论与实践,2004(4):49-55.
[94]司继文,蒙坚玲,龚朴.国内外期货市场相关性研究[J].华中科技大学学报,2004(12):16-19
[95]唐家银等.机械系统相关性可靠度计算的Copula新理论[J].机械科学与技术,2009(4):532-535.
[96]唐齐鸣,刘亚清.市场分割下A、B股成交量、收益率与波动率之间关系的SVAR 分析[J].金融研究,2008(2):113-126.
[97]韦艳华.Copula理论及其在多变量金融时间序列分析上的应用研究[D].天津大学,2004
[98]韦艳华,张世英,郭焱.金融市场相关程度与相关模式的研究[J].系统工程学报,2004(8):18-25
[99]韦艳华,张世英.金融市场动态相关结构的研究[J].系统工程学报,2006(6):313-317
[100]吴振翔,陈敏,叶五一,缪柏其.基于Copula-GARCH的投资组合风险分析[J].系统工程理论与实践,2006(3):45-52
[101]邢毓静.证券市场与外汇市场的互动关系及宏观政策选择——从B股向境内居民开放谈起[J].当代财经,2001(5):36-53
[102]战雪丽,张世英.基于Copula-SV模型的金融投资组合风险分析,系统管理学报,2007(3):302-306
[103]张明恒.多金融资产风险价值的Copula计量方法研究.数量经济技术经济研究,2004(4):67-70
[104]张永东,黎荣舟.上海股市日内波动性与成交量之间引导关系的实证分析[J].系统工程理论与实践,2003(2):19-23
[105]赵留彦,王一鸣.沪深股市交易量与收益率及其波动的相关性:来自实证分析的证据[J].经济科学,2003(1):57-67.
[106]张碧琼.中国股票市场信息国际化:基于EGARCH模型的检验[J].国际金融研究,2005(5):68-73
[107]张碧琼,李越.汇率对中国股票市场的影响是否存在:从自回归分布滞后模型得到的证明[J].金融研究,2002(7):26-35
[108]张金清,李徐.资产组合的集成风险度量及其应用——基于最优拟合Copula函数的VaR方法[J].系统工程理论与实践,2008(6):14-21.
[109]张尧庭.我们应该选取怎样的相关性指标[J].统计研究,2002(9):41-44.
[110]邹功达,陈浪南.中国A股与B股的市场分割性检验[J].经济研究,2002(4):15-23
[111]朱世武.基于Copula函数度量违约相关性,统计研究,2005(4):61-64