Modeling Market Volatility with Mixed Exponential Power Asymmetric Conditional Heteroskedasticity: An Application to Shanghai Stock Exchange Composite Index Daily Returns

We utilize the mixed exponential power asymmetric GARCH model where each component exhibits asymmetric conditional heteroskedasticity to model Shanghai Stock Exchange Composite Index daily returns. Thanks to extra component-specific shape parameters, it can better capture the tail behavior and match the stylized facts of high frequency financial time series precisely and parsimoniously. The application to SSE Composite Index returns illustrates all the conditional variance processes become stationary. Good nature of the performance both in-sample and out-of-sample as well as the flexibility of the maximum likelihood estimation makes it more attractive in the applications of risk management of portfolio and VaR calculation.