A Mixture Multiplicative Error Model for Realized Volatility

Abstract

A multiplicative error model with time-varying parameters and an error term following a mixture of gamma distributions is intro- duced. The model is fitted to the daily realized volatility series of Deutschemark/Dollar and Yen/Dollar returns and is shown to capture the conditional distribution of these variables better than the com- monly used ARFIMA model. The forecasting performance of the new model is found to be, in general, superior to that of the set of volatil- ity models recently considered by Andersen et al. (2003) for the same data.