The application Copula-GARCH-EVT models in analyzing financial markets tail dependence of China

Abstract

Dependence plays a central role in financial theory. Linear correlation is the appropriate measure of dependence if financial asset returns follow an elliptical distribution. However, experiences show that the volatility of a single asset return possesses the heteroscedasticity and clustering. Meanwhile, a distribution of financial asset return has fat-tails, skewness and other non-normal features. It is well known that the EGARCH-EVT method could either show the character of the return volatility or depict the feature of the fat-tail distribution. And, the theory of copula provides a flexible methodology for the general modeling of multivariate dependence. In this study, we combine the EGARCH-EVT model with a Copula function and construct Copula-EGARCH-EVT model to analyze the tail correlation of financial asset returns. We present inference procedure which is based on the parameter estimation for the copula parameter. Some numerical techniques are used for selecting an appropriate Copula-EGARCH-EVT model. Finally, we do empirical study on the tail correlation analysis on Shanghai composite index and Shenzhen compositional Index of China financial market.