| Abstract: | The use of Markov-switching models to capture the volatilitydynamics of financial time series has grown considerably duringpast years, in part because they give rise to a plausible interpretationof nonlinearities. Nevertheless, GARCH-type models remain ubiquitousin order to allow for nonlinearities associated with time-varyingvolatility. Existing methods of combining the two approachesare unsatisfactory, as they either suffer from severe estimationdifficulties or else their dynamic properties are not well understood.In this article we present a new Markov-switching GARCH modelthat overcomes both of these problems. Dynamic properties arederived and their implications for the volatility process discussed.We argue that the disaggregation of the variance process offeredby the new model is more plausible than in the existing variants.The approach is illustrated with several exchange rate returnseries. The results suggest that a promising volatility modelis an independent switching GARCH process with a possibly skewedconditional mixture density. |
