操作风险损失的广义帕累托分布参数估计及其应用  

Research on the Parameters Estimation and Application of Generalized Pareto Distribution: Based on Operational Risk Loss

作　　者：谭德俊[1] 邹敏烨[1] 

机构地区：[1]湖南大学金融与统计学院,湖南长沙410079

出　　处：《财经理论与实践》2010年第6期22-25,共4页The Theory and Practice of Finance and Economics

基　　金：教育部博士点基金项目(2006053211);湖南省研究生科研创新项目(CX2009B062)

摘　　要：极值理论表明大于某一阀值的样本服从广义帕累托分布,该结论在金融风险计量和保险精算中有着广泛的应用。然而,由于其参数没有可接受的估计方法,致使其应用受到限制。论文在推导出广义帕累托分布的条件矩的基础上,研究了基于操作风险损失的广义帕累托分布的参数估计问题。并且基于我国商业银行1994~2008年的操作风险损失数据对经济资本配置进行了算例分析。Extreme value theory（EVT） shows that the limiting distributions for the maximum of a very large collection of random observations which peak over threshold（POT） and from the same arbitrary distribution are distributed generalized Pareto distribution（GPD）.The POT approach has been developed largely in financial risk measurement and actuarial insurance.But its application subjects to the parameters estimation.In this paper,after inferring the condition moments,the parameters estimation of GPD have been researched based on operational risk loss.With the operational risk loss data of Chinese commercial banks from 1994 to 2008,empirical research into economic capital allocation have been carried out.

关 键 词：极值定理 广义帕累托分布 参数估计 操作风险损失 经济资本 

分 类 号：F830[经济管理—金融学]