一种估计风险价值的新模型

上海大学学报(自然科学版)

一种估计风险价值的新模型

唐林俊1,2,王汉兴1,3

1.上海大学理学院，上海 200444； 2.嘉兴学院统计系，嘉兴 314001;
3.中国立信风险管理研究院，上海 201620

收稿日期:2007-01-09 修回日期:1900-01-01 出版日期:2007-12-20 发布日期:2007-12-20
通讯作者: 唐林俊1,2

A New Approach of Estimating Value at Risk

TANG Lin-jun1,2,WANG Han-xing1,3

1. School of Sciences, Shanghai University, Shanghai 200444, China;
2. Department of Statistics, Jiaxing College, Jiaxing 314001, China;
3. China Lixin Risk Management Research Institute, Shanghai 201620, China

Received:2007-01-09 Revised:1900-01-01 Online:2007-12-20 Published:2007-12-20
Contact: TANG Lin-jun1,2

摘要/Abstract

摘要：

根据极值-Ⅱ型分布的厚尾性质，结合当今金融市场收益分布的尖峰厚尾特征，提出一种具有尖峰厚尾的Laplace极值-Ⅱ型混合分布，并在此基础上建立了一种新的估计风险价值VaR(Value at Risk)的Laplace极值混合模型，通过对上证B股的实证模拟分析，发现该模型对收益表现异常的金融序列的VaR估计具有较高的应用价值.

关键词:

风险价值（VaR）, Laplace极值-Ⅱ型混合分布, Laplace极值混合模型

Abstract:

As for the sharp-kurtosis and fat-tail characteristics of the money-market yield, a mixed distribution — Laplace and extreme value-II distribution is proposed, which is applied to establish a new model for estimating value at risk (VaR).By demonstrating in the financial market, this new method shows a very high practical value in which return rate has extreme.

Key words: Laplace-extreme value mixing model

, mixing distribution of Laplace and EVD-Ⅱ,

risk-at-value

唐林俊;王汉兴;. 一种估计风险价值的新模型[J]. 上海大学学报(自然科学版).

TANG Lin-jun;WANG Han-xing;. A New Approach of Estimating Value at Risk[J]. Journal of Shanghai University（Natural Science Edition）.