The performance of the switching forecast model of value-at-risk in the Asian stock markets

This paper examines a comparative risk forecast experiment for Asian stock markets. Apart from the literature, this work extends previous methods to propose a Switching forecast model to increase forecast effectiveness. The Switching forecast model is explicitly designed to estimate the forecasting problem faced by the risk manager who does not rely on a specific Value-at-Risk (VaR) model and allows for the VaR model to change over time. It is found that the Switching forecast model is not only capable of capturing the characteristics of Asian stock markets but also provides a satisfactorily accurate measurement based on coverage tests. Additionally, the superiority test indicates statistically that the Switching forecast model is more effective than alternative models based on quadratic loss function.