Copula Theory And Its Applications Of Dependence Between The Stock And Insurance Industry

Copula theory is summarized systemically and comprehensively in this dissertation. On the basis of an overview of the introduction of Copula, two empirical researches are done in the Chinese stock market and the Chinese insurance industry. One is the dependence research between the Shanghai stock market and Shenzhen stock market, the other is the dependence between the Shanghai stock market and an investment-based insurance. The empirical research shows that the positive dependence is existed between the two stock markets, and the same result between the stock market and the insurance industry.The key points and main achievements of this work are listed as follows;1. We present an overview introduction of the Copula theory. The definition, its main mathematical properties, its classification are all included. In this thesis, fitting Copula to data is focused on, including three parametric estimation methods: Maximum likelihood estimation , the IFM method and the MBP method, and the chi-square goodness of fitting test to decide the prefect Copula.2. The empirical research about the conditional dependence between the Shanghai and Shenzhen stock market is carried out using different Copula functions. The EGARCH model with t error distribution is used to fit the marginal distribution, and it fit the financial time series better. The research indicates that the normal mixed copula function is better than the single copula to describe the dependence the two stock indexes and the two indexes have a strongly positively dependence.3. The dependence between the stock market and the insurance industry is carried out using copula function. The insurance industry is a main industry of the financial field. With the development of the economy marketization, the dependence between the insurance and stock industry will be more strongly. In this thesis, an investment-based insurance product is choice to use in the empirical research. The standard GARCH model with normal error distribution is used to fit the marginal distribution. The result shows that the BB4 copula of Archimax Copula is the best copula to describe the dependence structure between the two industries. Further, the account of growing blue chips has stronger dependence with the stock market than the account of equilibrium.