基于时变Copula-CoVaR商业银行系统性金融风险溢出分析
|
摘要
为了更加准确捕捉商业银行系统性金融风险溢出过程的动态非线性相依特征,以科学分析商业银行风险负外部性与风险溢出强度,通过时变Copula模型计算VaR,CoVaR和△CoVaR,研究了浦发、华夏、民生、招商、兴业、中信6个商业银行个股指数和中证800银行业指数间的商业银行系统性金融风险溢出问题.结果表明:时变模型对于△CoVaR的刻画相较于静态模型更为准确、灵敏,且计算得出的CoVaR均为负值,分析比较△CoVaR,得出风险溢出强度从强到弱依次为:中信银行、兴业银行、华夏银行、民生银行、浦发银行、招商银行.研究为风险监管资源分配、监管对象确定提供了一定依据.
In order to seize the characteristic of dynamic-nonlinearly dependence of the process of systematic financial risks' spillovers of commercial banks more accurately, and to make a scientific analysis of the negative externality and risk spillover intensity of commercial banks' risks, VaR, CoVaR and △CoVaR have been computed in this paper by means of time-varying Copula models and the problem been studied of systematic financial risks' spillovers between six commercial banks individual index, CITIC Bank, CIB, HXB, CMBC, SPDB and CMB included, and China Securities 800 Banking Index. The results show that for the description of △CoVaR, dynamic models are more accurate and sensitive, all the values of CoVaRs are negative, the risk spillover intensity ranks as CITIC Bank>CIB>HXB>CMBC>SPDB>CMB. As can be seen, the research in this paper can provide basis for risks supervision resources allocation and supervision objects determination.
In order to seize the characteristic of dynamic-nonlinearly dependence of the process of systematic financial risks' spillovers of commercial banks more accurately, and to make a scientific analysis of the negative externality and risk spillover intensity of commercial banks' risks, VaR, CoVaR and △CoVaR have been computed in this paper by means of time-varying Copula models and the problem been studied of systematic financial risks' spillovers between six commercial banks individual index, CITIC Bank, CIB, HXB, CMBC, SPDB and CMB included, and China Securities 800 Banking Index. The results show that for the description of △CoVaR, dynamic models are more accurate and sensitive, all the values of CoVaRs are negative, the risk spillover intensity ranks as CITIC Bank>CIB>HXB>CMBC>SPDB>CMB. As can be seen, the research in this paper can provide basis for risks supervision resources allocation and supervision objects determination.
引文
[1] LAIY,CHEN C W S,GERLACH R.Optimal Dynamic Hedging Via Copula-Threshold-GARCH Models [J].Mathematics and Computers in Simulation,2009,79(8):2609-2624.
[2] LEE H T.A Copula-Based Regime-Switching GARCH Model for Optimal Futures Hedging [J].Journal of Futures Markets,2009,29(10):946-972.
[3] 吴振翔,陈敏.基于Copula-GARCH的投资组合风险分析 [J].系统工程理论与实践,2006,26(3):45-52.
[4] 柏满迎,孙禄杰.三种Copula-VaR计算方法与传统VaR方法的比较 [J].数量经济技术经济研究,2007,24 (2):154-160.
[5] GOODHART C A E,SEGOVIANO BASURTO M A.Banking Stability Measures [J].IMF Working Papers,2009,9(4):1.
[6] REBOREDO J C,UGOLINI A.Downside/upside Price Spillovers between Precious Metals:A Vine Copula Approach [J].The North American Journal of Economics and Finance,2015,34:84-102.
[7] 苟红军,陈迅,花拥军.基于GARCH-EVT-COPULA模型的外汇投资组合风险度量研究 [J].管理工程学报,2015,29(1):83-193.
[8] 马锋,魏宇,黄登仕.基于vine copula方法的股市组合动态 VaR测度及预测模型研究 [J].系统工程理论与实践,2015,35(1):26-36.
[9] 高国华,潘英丽.银行系统性风险度量—基于动态CoVaR方法的分析 [J].上海交通大学学报,2011,45(12):1753-1759.
[10] 陈守东,章秀.基于时变CoVaR模型的我国商业银行风险溢出效应研究 [J].数量经济研究,2013(2):34-48.
[11] 欧阳资生,莫廷程.基于广义CoVaR模型的系统重要性银行的风险溢出效应研究 [J].统计研究,2017,34(9):36-43.
[12] KARIMALIS E N,NOMIKOS N K.Measuring Systemic Risk in the European Banking Sector:A Copula CoVaR Approach [J].The European Journal of Finance,2018,24(11):944-975.
[13] 王锦阳,刘锡良,杜在超.相依结构、 动态系统性风险测度与后验分析 [J].统计研究,2018,35(3):3-13.
[14] SKLAR A.Fonctions de Répartition àn Dimentions et Leursmarges [J].Publication de I'Institut de Statistique de L'Universit-é de Paris,1959,8:229-231.
[2] LEE H T.A Copula-Based Regime-Switching GARCH Model for Optimal Futures Hedging [J].Journal of Futures Markets,2009,29(10):946-972.
[3] 吴振翔,陈敏.基于Copula-GARCH的投资组合风险分析 [J].系统工程理论与实践,2006,26(3):45-52.
[4] 柏满迎,孙禄杰.三种Copula-VaR计算方法与传统VaR方法的比较 [J].数量经济技术经济研究,2007,24 (2):154-160.
[5] GOODHART C A E,SEGOVIANO BASURTO M A.Banking Stability Measures [J].IMF Working Papers,2009,9(4):1.
[6] REBOREDO J C,UGOLINI A.Downside/upside Price Spillovers between Precious Metals:A Vine Copula Approach [J].The North American Journal of Economics and Finance,2015,34:84-102.
[7] 苟红军,陈迅,花拥军.基于GARCH-EVT-COPULA模型的外汇投资组合风险度量研究 [J].管理工程学报,2015,29(1):83-193.
[8] 马锋,魏宇,黄登仕.基于vine copula方法的股市组合动态 VaR测度及预测模型研究 [J].系统工程理论与实践,2015,35(1):26-36.
[9] 高国华,潘英丽.银行系统性风险度量—基于动态CoVaR方法的分析 [J].上海交通大学学报,2011,45(12):1753-1759.
[10] 陈守东,章秀.基于时变CoVaR模型的我国商业银行风险溢出效应研究 [J].数量经济研究,2013(2):34-48.
[11] 欧阳资生,莫廷程.基于广义CoVaR模型的系统重要性银行的风险溢出效应研究 [J].统计研究,2017,34(9):36-43.
[12] KARIMALIS E N,NOMIKOS N K.Measuring Systemic Risk in the European Banking Sector:A Copula CoVaR Approach [J].The European Journal of Finance,2018,24(11):944-975.
[13] 王锦阳,刘锡良,杜在超.相依结构、 动态系统性风险测度与后验分析 [J].统计研究,2018,35(3):3-13.
[14] SKLAR A.Fonctions de Répartition àn Dimentions et Leursmarges [J].Publication de I'Institut de Statistique de L'Universit-é de Paris,1959,8:229-231.