Applications Of Copula On The Correlation Analysis Of Fund Market In China

Along with the finance research developing, the relevant analysis becomes more and more important in the financial application. Investment analysis, assets'diversification and pricing and financial risk measure all involve to relevant analysis. The term Copula is based on the notion of "coupling", the Copula couples the marginal distributions together to form a joint distribution. The dependence relationship is entirely determined by the Copula, while statistical descriptions are entirely determined by the marginal. Copulas have become a popular multivariate modeling tool in many fields where the multivariate dependence is of great interest and the usual multivariate normality is in question. Conventional methods like correlation summarize dependence, whereas a Copula gives a model for the dependence structure that reflects more detailed knowledge of the random variables. Copulas have become a popular multivariate modeling tool in many fields.1. Copula theory is summarized systemically and wholly in this thesis. We present an overview of introduction of Copula, such as the definition and it's main mathematical and modeling properties and the classification. In this thesis, fitting Copulas to data is focused on, including the parametric and nonparametric methods of estimating parameter, simulating random variables from certain Copula and different methods to decide which Copula is to be preferred.2. The Copula is a tool for understanding relationships among multivariate random variable. Our goal of the empirical research is to fit One-parameter families of Archimedean Copulas to bivariate data. The research indicates that the two indexes are strongly positively correlative and the correlation can be characterized by unsymmetrical tail dependence.3. The Copula describes the dependence structure of a multivariate random variable. In this thesis, it is used as a practical and flexible instrument to generate Monte Carlo scenarios of risk factor returns. The same Copula with different hypotheses of marginal produces almost the same result, while with the same hypotheses of marginal, the Copula can model such extreme events effectively.