Study On Portfolio And VaR Based On Copula And GARCH Method

Traditional portfolio theory based on multivariate normal distribution assumes that investors can benefit from diversification by investing in assets with lower correlations in order to avoid risk. However, this is not what happens in reality, since it is quite easy to see financial markets with different correlations but almost the same numbers of market crashes. Correlation is not the useable in reality. This paper resorted to copula theory and its conditional dependence measures, Kendall's Tau, implemented it in the traditional mean-variance framework. By this method, not only have already kept having effectiveness of the traditional portfolio theory, but also consider the non-linear dependence among the related variables.Recent empirical studies show that in volatile periods financial markets tends to be characterized by different level of dependence than occurs in quiet periods. In order to take into account this reality ,we resort to Copula theory and its conditional dependence measures,like Kendall's Tau and Tail dependence. We implemented this idea to the traditional RiskMetrics model, and build multi-Copula VaR model. Finally , we make a empirical studies and confirmed the operability of these models.