Identifying US turning points revisited: the panel model with the regime switching approach

Abstract

This article proposes a panel model with a regime switching mechanism to analyse the feature of US business cycles. This Markov Switching Panel model is simple and can easily be estimated using Hamilton's (1989) method. We test the ability of the Markov Switching Panel model to identify US turning points using the US coincident indicator data. The empirical evidence shows that this model is highly capable of identifying US recessionary dates. It also has a better forecast performance than the Markov Switching vector autoregressive model.

Acknowledgements

I would like to thank Professor Mark Taylor and anonymous referees of this journal for helpful comments and suggestions. Financial support from the National Science Council (NSC 95-2415-H-029-001) is gratefully acknowledged. The usual disclaimer applies.

Notes

¹ Many articles have adopted Hamilton's (1989) approach to identify business cycle turning points. See, for example, Layton and Smith (2000) and Cruz (2005) to name a few.

² The study by Asea and Blomberg (1998) was the first to use the Markov switching panel model, but is was not in a study of business cycle.

³ Readers are referred to Hansen (1992, 1996) and Garcia (1998) for details.

⁴ Two types of error signals could have occurred in our predictions. The first is a missed signal failure, i.e. when there is a recession, but the model fails to predict it. The other is a false signal failure, i.e. when the model predicts there is a recession, but one does not actually occur.

Fig. 1 Average filtered probabilities from the Markov switching panel model. The shaded areas are the NBER-defined reference recessionary dates

⁵ We do not report the parameter estimates from the MS–VAR model. The results are available from the author upon request.