在金融风险管理理论与实践中,VaR和CVaR已成为主流方法之一。为分散金融风险的动态影响,一方面,通过时变波动模型将静态VaR和CVaR扩展到动态情形,进一步基于多元GARCH模型给出动态VaR和CVaR的计算方法;另一方面,在动态风险度量的基础上,建立了动态组合投资选择模型。最后,利用国际股市的数据进行了实证研究,将动态组合投资与静态组合投资的效果进行了比较。
In current financial risk management practice, value at risk (VaR) and conditional value at risk (CVaR) are the most popular risk measures. This paper extends the static VaR and CVaR to the dynamic ones through timevarying volatility modeled by general autoregressive conditional hetemscedasticity (GARCH) model. Under nomlal distribution assumption, the authors discuss the calculation of dynamic VaR and CVaR through multivariate GARCH model. Based on the dynamic measure of risk, the dynamic framework for optimal portfolio selection is proposed and solved by the dynamic programming methods. In particular, the authors focus on the portfolio which yields a portfolio of the minimum variance, VaR or CVaR at every day. Finally, empirical applications are applied into international stock markets.