AN EXAMINATION OF THE SIGN AND VOLATILITY SWITCHING ARCH MODELS UNDER ALTERNATIVE DISTRIBUTIONAL ASSUMPTIONS

This paper relaxes the assumption of conditional normal innovations used by Fornari and Mele (1997) in modelling the asymmetric reaction of the conditional volatility to the arrival of news. We compare the performance of the Sign and Volatility Switching ARCH model of Fornari and Mele (1997) and the GJR model of Glosten et al. (1993) under the assumption that the innovations follow the Generalized Student’s t distribution. Moreover, we hedge against the possibility of misspecification by basing the inferences on the robust variance-covariance matrix suggested by White (1982). The results suggest that using more flexible distributional assumptions on the financial data can have a significant impact on the inferences drawn.