欢迎访问中国科学院大学学报,今天是

中国科学院大学学报 ›› 2008, Vol. 25 ›› Issue (5): 682-686.DOI: 10.7523/j.issn.2095-6134.2008.5.017

• 论文 • 上一篇    下一篇

基于Copula-VaR方法对上证和深证的研究

郝礼祥, 程希骏   

  1. 中国科技大学统计与金融系,合肥 230026
  • 收稿日期:1900-01-01 修回日期:1900-01-01 发布日期:2008-09-15

Analysis of Shanghai and Shenzhen stock market using Copula-VaR method

Hao Li-Xiang, Cheng Xi-Jun   

  1. University of Scienceand Technology of China, Hefei 230026, China
  • Received:1900-01-01 Revised:1900-01-01 Published:2008-09-15

摘要: 基于Copula函数对金融市场风险价值(VaR)的研究,构造出一种新的混合Copula,并于传统的方法进行了比较,通过事后检验(Backtesting),实证研究得出,混合Copula函数方法的确能够改善VaR模型,降低时失效天数。

关键词: Copula函数, Monte Carlo模拟, 事后检验

Abstract: Risk analysis of Portfolio is studied ,by comparing Copula functions and the traditional VaR methods,mixing copula is made. By backtesting ,the empirical research shows that mixing Copula method makes better VaR model .