A0396
Title: Estimation under copula-based Markov mixture normal models for serially correlated data
Authors: Li-Hsien Sun - National Central University (Taiwan) [presenting]
Takeshi Emura - Kurume University (Japan)
Abstract: The estimation problem under a copula-based Markov model for serially correlated data is proposed. Owing to the fat tail feature in stock market, we select mixture normal distribution as the marginal distribution for the log return. Based on the mixture normal distribution as the marginal distribution and the Clayton copula, we obtain the corresponding likelihood function. In order to obtain the maximum likelihood estimators, we apply the Newton-Raphson method. In the empirical analysis, the stock price of Dow Jones Industrial Average is analyzed for illustration.
