基于Asymmetric Laplace分布的金融风险度量

摘要/Abstract

摘要： 金融资产的损益分布具有明显尖峰肥尾和不对称等特征,本文采用非对称拉普拉斯分布来刻画这些风险特征,给出了市场风险VaR和CVaR度量的AL参数法和AL-MC法。选取上证指数、日经225指数及S&P500指数为研究对象,结合各股市的风险特征,给出了VaR和CVaR度量及其返回检验和准确性评价。结果表明,基于AL分布的风险度量模型具有其合理性和适用性,能很好地度量市场风险。

关键词: VaR, CVaR, 非对称拉普拉斯分布, 风险管理

Abstract: The actual distribution of asset returns possesses the characters of steep peaks, heavy tails and asymmetry, in this paper, asymmetric laplace distribution is used to fit the data of asset returns and described these features. Then, AL parametric method and AL-MC method are employed to measure VaR and CVaR. The Shanghai Composite Index, Nikkei225 Stock Index and S&P500 Index are selected in the calculation of VaR and CVaR considering actual stocks risk features. Also, the back testing and accuracy assessment of risk are given. The results show that the risk measurement model based on Asymmetric Laplace distribution is reasonable and applicable and can effectively estimated the market risk.

Key words: value at risk, conditional value at risk, asymmetric laplace distribution, risk management

中图分类号:

F830.9

杜红军, 王宗军. 基于Asymmetric Laplace分布的金融风险度量[J]. 中国管理科学, 2013, 21(4): 1-7.

DU Hong-jun, WANG Zong-jun. Financial Risk Measurement Based on Asymmetric Laplace Distribution[J]. Chinese Journal of Management Science, 2013, 21(4): 1-7.

参考文献

[1] Jorion P. Value at Risk[M]. 2nd ed. McGraw-Hill, 2001.
[2] Artzner P, Delbaen F, Eber J M, et al. Coherent measure of risk[J]. Mathematical Finance, 1999, 9(3): 203-228.
[3] Rockfeller T, Urvasev S. Conditional value-at-risk for general loss distribution[J]. Journal of Banking & Finance, 2002, 26(7): 1443-1471.
[4] Nolan J P. Fitting date and assessing goodness-of-fit with stable distributions[D]. Washington: American University, 1999.
[5] 朱国庆, 张维. 关于上海股市极值收益渐近分布的实证研究[J]. 系统工程学报, 2000, 15(4): 338-343.
[6] 詹原瑞, 田宏伟. 极值理论(EVT)在汇率受险价值(VaR)计算中的应用[J]. 系统工程学报, 2000, 15(1): 44-53.
[7] 陈守东, 俞世典. 基于GARCH模型的VaR方法对中国股市的分析[J]. 吉林大学社会科学学报, 2002, 4: 11-17.
[8] 田新时, 刘汉中, 李耀. 沪深股市一般误差分布(GED)下的VaR计算[J]. 管理工程学报, 2003, 1: 25-28.
[9] 朱海霞, 潘志斌. 基于g-h分布的投资组合VaR方法研究[J]. 中国管理科学, 2005, 13(4): 7-12.
[10] 肖智,傅肖肖,钟波. 基于EVT-BM-FIGARCH的动态VaR风险测度[J]. 中国管理科学, 2008, 16(4): 18-23.
[11] 林宇,卫贵武,魏宇,等. 基于Skew-t-FIAPARCH的金融市场动态风险VaR测度研究[J]. 中国管理科学, 2009, 17(6): 17-24.
[12] 花拥军, 张宗益. 基于峰度法的POT模型对沪深股市极端风险的度量[J]. 系统工程理论与实践,2010, 30(5): 786-796.
[13] 叶五一, 陈杰成, 缪柏其. 基于虚拟变量分位点回归模型的条件VaR估计以及杠杆效应分析[J]. 中国管理科学, 2010, 18(4): 1-7.
[14] Kozubowski T J, Podgorski K. Asymmetric Laplace distributions[J]. Math Sci, 2000, 25: 37-46.
[15] Kozubowski T J, Podgorski K. Asymmetric Laplace laws and modeling financial data[J]. Math Comput Modelling, 2001, 34: 1003-1021.
[16] Kotz S, Kozabowski T J, Podgórski K. The laplace distribution and generalizations: a revisit with applications to communications, economics, engineering, and finance[M]. Boston: Birkhauser, 2001.
[17] Jayakumar K, Kuttykrishnan A P. A time-series model using asymmetric Laplace distribution[J]. Statist Probab Lett, 2007, 77: 1636-1640.
[18] Trindade A A, Zhu Yun. Approximating the distributions of estimators of financial risk under an asymmetric Laplace law[J]. Computational Statistics and Data Analysis, 2007, 51: 3433-3447.
[19] 黄海. 风险管理中的建模与预测:基于非对称Laplace分布的新方法[D]. 北京:中科院数学与系统科学研究院硕士毕业论文,2003.
[20] Kotz S, Kozabowski T J, Podgórski K. Maximum likelihood estimation of asymmetric Laplace parameters[J]. Ann Inst Statist Math, 2002, 54(2): 816-826.
[21] Kupiec P H. Techniques for verifying the accuracy of risk measurement models[J]. Journal of Derivatives. 1995, 3(2): 73-84.