摘要
VaR是金融风险度量方面研究的热点.CAViaR模型可以用来直接计算单个资产的VaR,DCC模型可以用于刻画资产间的相关性.结合这两个模型,通过分位数估计方差的方法,提出了基于CAViaR的DCC模型来计算投资组合的VaR.对中国股市的实证研究表明其具有更好的效果.
Value at risk （VaR） has been widely used in the measure of finance risk. Conditional Autoregressive Value At Risk （CAViaR） model can measure the VaR of individual asset directly. Dynamic Conditional Correlation （DCC） model can be applied to describe the correlation between assets. In current paper, utilizing the technique of estimating variance by quantiles, we establish a DCC model based on CAViaR that can be applied to estimate the VaR of portfolios through combining these two models. Empirical study results are in favor of the new model.
出处
《数学的实践与认识》
CSCD
北大核心
2009年第4期75-81,共7页
Mathematics in Practice and Theory
基金
中国科学院知识创新工程重要方向项目(KJCX3-SYW-S02)
