Abstract
In this article, we derive an alternative estimation algorithm for the innovation regime-switching model, which avoids the potential divergence problem that may arise from the algorithm proposed by Kuan et al. (Citation2005, JBES). Our simulation demonstrates that the proposed algorithm compares favourably with that of Kuan et al. (Citation2005), in terms of both numerical accuracy and computing time.
Acknowledgements
I thank C.-M. Kuan for valuable suggestions on early drafts of this article. I am also indebted to the editor and two anonymous referees whose comments lead to a much improved version of the article. All remaining errors are mine. The research supports from the National Science Council of the Republic of China (NSC95-2415-H-007-004) is gratefully acknowledged.