针对传统风险分析模型的不足,结合Copula技术和GARCH模型,提出了多元Copula-GARCH模型。指出该模型不仅可以捕捉金融市场间的非线性相关性,还可以得到更灵活的多元分布进而用于资产投资组合VaR分析。在详细探讨了基于Copula技术的资产投资组合的Monte Carlo仿真技术的基础上,运用具有不同边缘分布的多元Copula-GARCH模型,对上海股市进行了研究,结果证实了所提模型和方法的可行性和有效性。
Combined copula techniques with GARCH model, multivariate Copula - GARCH model is provided to avoid defects of classical risk analysis models. Not only is non - linear dependence between financial markets able to be caught, but also flexible multivariate distribution which can be use to analyze portfolio Value - at - Risk is able to receive from this model. Monte Carlo techniques of portfolio based on copula techniques are fully discussed in this paper. The empirical results getting from Shanghai stock markets indicate that Copula - GARCH model with different marginal distributions and Monte Carlo techniques given in this paper is feasible and effective.