中国商业银行操作风险损失分布的拟合与诊断被引量：3

Fitting and Diagnosing Operational Risk Loss Distribution of China’s Commercial Banks

导出

摘要基于中国商业银行1994-2008年的操作风险损失数据,本文通过对操作风险损失分布的检验及利用贝叶斯MCMC频率进行分析,结果证实了中国商业银行操作风险损失分布近似服从广义极值分布(GEV)。从理论上看,在某种情况下广义帕雷托分布(GPD)可转化为GEV分布。因此,本文检验了中国商业银行操作风险损失分布是否也服从于GPD。为了检验中国商业银行操作风险损失分布是否可用GEV或GPD,本文采用极大似然估计法对GEV和GPD分布的位置参数、尺度参数、形态参数进行了估计并对中国商业银行操作风险的GEV和GPD分布模型进行了诊断。研究表明中国商业银行操作风险损失的概率图、分位数图、重现水平曲线、密度曲线的四个诊断图都支持操作风险损失分布可用GEV和GPD分布表示。 Based on China commercial banks＇ 1994-2008 operational risk loss data, the article tests China＇ s commercial bank operational risk loss distribution and analyzes with the Bayesian MCMC frequency method. It confirms China commercial bank operational risk obeys Generalized Extreme Distribution （GEV）. In theory, Generalized Pareto Distribution （GPD） can transfer to GEV under certain conditions. Therefore, we exanimate whether China commercial bank operational risk loss can obey GPD. To exanimate whether China commercial bank operational risk loss obeys GEV or GPD, this paper uses MLE meth- od to obtain the location parameter, scale parameter and shape parameter of GEV and GPD, and diagnoses the GEV and GPD model. The results indicate that Probability Plot, Quantile Plot, Return Level Plot and Density Plot support China commercial bank operational risk loss is subject to GEV and GPD.

作者宾建成吴俊

机构地区上海对外贸易学院恒泰证券股份有限公司研发部

出处《投资研究》北大核心 2013年第3期20-32,共13页 Review of Investment Studies

基金上海市085工程建设项目(Z08511018)的阶段性成果

关键词 GEV GPD 极大似然估计贝叶斯蒙特卡洛模拟 GEV GPD MLE Bayesian MCMC simulation

分类号 F224 [经济管理—国民经济] F832.33 [经济管理—金融学]

引文网络
相关文献

参考文献12

1刘睿,詹原瑞,刘家鹏.基于贝叶斯MCMC的POT模型——低频高损的操作风险度量[J].管理科学,2007,20(3):76-83. 被引量：21
2梁世栋.巴塞尔Ⅲ若干议题讨论[J].投资研究,2011,30(8):149-154. 被引量：4
3Alexander J. McNeil, 1999, Extreme Value Theory for Risk Managers,pp.283-358 .
4Bortkiewicz Lvon, 1922,Variationsbreite und mittlerer Fehler, Sitzungsber. Berli Math Ges, pp.21:3-11.
5Chernobai,Svetlozar and Fabozzi,2007,Operational risk: A Guide to Basel II Capital Requirements, Models, and Analysis., John Wiley & Sons, Inc,pp.1-175.
6Elise Gourier, Walter Farkas and Donato Abbate, 2009,Operational Risk Quantification using Extreme Value Theory and Copulas: From Theory to Practice,The Jorunal of Operational Risk, Vol.4 Number3,pp. 1-24.
7Embrechts, Kliippelberg and Mikosch, 1997,Modelling Extreme Events for Insurance and Finance. Springer-Verlag Berlin Heidelberg,pp. 1-275.
8Fisher R A and Tippett L H C,1928, Limiting forms of the frequency distribution of the largest or smallest member of a sample. Cambridge Philos.Soc,pp. 180-190.
9Mises R von,1923.,Uber die Variationsbreite einer Beobachtungsreihe, Sitzungsber,Berlin, Math, Ges, pp.3-8.
10Samuel Kotz, Saralees Nadarajah,2000, Extreme Value Distributions, Imperial College Press, pp. 1-93.

二级参考文献26

1樊欣,杨晓光.我国银行业操作风险的蒙特卡罗模拟估计[J].系统工程理论与实践,2005,25(5):12-19. 被引量：49
2IBIS, 2010a, "Basel Ill: A global regulatory framework for more resilient banks and banking systems", http://www.bis.org/.
3BIS, 2010b, "Basel III: International framework for liquidity risk measurement, standards and monitoring" , http://www. bis.org/.
4BIS, 2009a, "Enhancements to the Basel II framework", http://www.bis.org/.
5BIS, 2009b, "Guidelines for computing capital for incremental risk in the trading book", http://www.bis.org/.
6BIS, 2009c, "Revisions to the Basel II market risk framework", http://www.bis.org/.
7BIS, 2009d, "Principles for sound stress testing practices and supervision", http://www.bis.org/.
8Basel Ⅱ.International Convergence of Capital Measurement and Capital Standards[R].Switzerland:Basel Committee on Banking Supervision,2004.
9Klugman Stuart A,Harry H Panjer,Gordon E Willmot.Loss Models:From Data to Decisions (second ed.)[M].New York:John Wiley & Sons,Inc.,2004.
10Reiss R,Thomas M.Statistical Analysis of Extreme Values from Insurance,Finance,Hydrology and Other Fields (second ed.)[M].Basel:Birkhauser Verlag,2001.