基于重要抽样的信用风险度量VaR与CVaR计算
发布时间：2018-10-29 12:07
【摘要】：为度量和计算信用组合风险,美国J.P.MOrgan集团推出了信用风险的量化度量模型CreditMetrics。CreditMetrics是基于VaR方法的信用风险度量模型,对组合风险中各资产收益的假设基于Gauss_Copula模型。本文介绍了针对CreditMetrics模型的普通蒙特卡洛方法、两步重要抽样方法对其尾部概率进行估计。鉴于VaR与CVaR在风险管理中的重要作用,本文在指定概率水平下,给出了一种快速准确计算VaR与CVaR的方法,并结合两步重要抽样方法做了具体说明。数值模拟方面,本文分别使用普通蒙特卡洛方法及文章提出的方法对信用风险组合VaR与CVaR值进行模拟计算,并对标准差进行比较。结果表明,本文提出的方法可更好地减小方差,提高计算准确度。
[Abstract]:In order to measure and calculate the credit portfolio risk, J.P.MOrgan Group of the United States developed a quantitative credit risk measurement model CreditMetrics.CreditMetrics is a credit risk measurement model based on the VaR method, and the assumption of each asset return in the portfolio risk is based on the Gauss_Copula model. In this paper, the general Monte Carlo method for CreditMetrics model and the two-step important sampling method are introduced to estimate the tail probability. In view of the important role of VaR and CVaR in risk management, this paper presents a fast and accurate method for calculating VaR and CVaR at the specified probability level, and gives a detailed explanation with the two-step important sampling method. In the aspect of numerical simulation, the common Monte Carlo method and the method proposed in this paper are used to simulate and calculate the credit risk combination VaR and CVaR, and the standard deviation is compared. The results show that the proposed method can better reduce the variance and improve the accuracy of calculation.
【学位授予单位】：南京大学
【学位级别】：硕士
【学位授予年份】：2017
【分类号】：F830.91;O211.67
，
本文编号：2297653
[Abstract]:In order to measure and calculate the credit portfolio risk, J.P.MOrgan Group of the United States developed a quantitative credit risk measurement model CreditMetrics.CreditMetrics is a credit risk measurement model based on the VaR method, and the assumption of each asset return in the portfolio risk is based on the Gauss_Copula model. In this paper, the general Monte Carlo method for CreditMetrics model and the two-step important sampling method are introduced to estimate the tail probability. In view of the important role of VaR and CVaR in risk management, this paper presents a fast and accurate method for calculating VaR and CVaR at the specified probability level, and gives a detailed explanation with the two-step important sampling method. In the aspect of numerical simulation, the common Monte Carlo method and the method proposed in this paper are used to simulate and calculate the credit risk combination VaR and CVaR, and the standard deviation is compared. The results show that the proposed method can better reduce the variance and improve the accuracy of calculation.
【学位授予单位】：南京大学
【学位级别】：硕士
【学位授予年份】：2017
【分类号】：F830.91;O211.67
，
本文编号：2297653
本文链接：https://www.wllwen.com/kejilunwen/yysx/2297653.html
