Based Copula Approach Binary Combination Of Risk Models And Application Of Research

Along with the finance research area developing, the study based on unitary asset or market is not always reaching the need. The relevant analysis becomes more and more important in the financial application, especially in the area of portfolio risk management. But the former research based on liner correlation usually all concentrates in to the degree of relativity, and neglected to related structure or the tail dependence in the money market. In fact, the same relativity of two pair random variables possibly can have the different related pattern and the special part characteristic. Therefore using the degree of relativity or the linear correlation describe dependence of correlation during the random variable is not comprehensive. So we need a new tool to measure the portfolio risk better.Then Copula theory is introduced into financial analysis to avoid those defects. Using the Copula function technology, may take the relativity and the correlation pattern organically into together, and get more accurate on financial risk measurement. As so far, the research always suppose that the correlation, includes correlation pattern and relativity, will be invariant on all the period under study. Though the correlation has been time-dependence, this assumption is made most of the time in practice.In order to catch the dynamic changes of correlation for good measuring of portfolio risk, the key points and main content of this work are listed as follows:1. First, this paper gives a simple introduction on the development of financial risk management theory and methods, which points out that it is important and necessary to introduce Copula theory into financial risk measurement area. Then Copula theory is detailed presented. We come to the conclusion that the goodness-of-fit of Copula model is largely affected by the peripheral distribution through establishing Copula-GARCH model and doing empirical analysis in the Chinese futures market.2. This paper supposed that correlation will be time-dependence. Based on this assumption, it is focused on the application of time-varying Copula function in the research to describe the dynamic changes of correlation. Parameters evolution equations of the time-varying Copula model was been improved and empirical analysis also has been done in China stock markets. Research found that the modified time-varying Copula model not only increased the prediction accuracy of assets portfolio's value at risk but also made prediction value closer to the actual loss value, which helping to raise the efficiency of capital use.