Forecasting Markov-switching dynamic, conditionally heteroscedastic processes
Cardiff Business School (now at University of Exeter)
Statistics & Probability Letters
Recursive formulae are derived for the multi-step point forecasts and forecast standard errors of Markov switching models with ARMA(∞,q) dynamics (including the fractionally integrated case) and conditional heteroscedasticity in ARCH(∞) form. Hamilton's dynamic models of switching mean and variance are also treated, in a slightly modified version of the analysis.
Statistics and Probability Letters (2004) 68(2) 137-147