Conclusion
In this chapter we apply the Markov switching heteroskedasticity model to stock returns for Germany, Japan, the UK, and USA, and decompose these stock returns into permanent and transitory components. This modeling approach is superior to the GARCH model, as emphasized by Lamoureux and Lastrapes (1990). In particular, the Markov-switching model explicitly considers the possibility of regime shift, whereas the GARCH model does not.
According to our evaluation of the differences between the speeds of mean reversion of the temporary components, the high-variance state of the transitory component lasts for an average of only 3.42 months for the USA, versus 20.62 months for Germany. The time periods for the other two countries fall between these values.
Regarding the second objective of this study, to determine differences in the patterns of correlation between permanent and temporal components across international markets, we find that the US market correlates positively with the other markets for the permanent component, but negatively for the temporal component. This implies that the USA moves in the same direction as the other three countries in the long run, and in an opposite direction in the short run.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Rights and permissions
Copyright information
© 2004 Springer Science + Business Media, Inc.
About this chapter
Cite this chapter
(2004). Exploring Permanent and Transitory Components of Stock Return. In: Hidden Markov Models. Advanced Studies in Theoretical and Applied Econometrics, vol 40. Springer, Boston, MA. https://doi.org/10.1007/1-4020-7940-0_6
Download citation
DOI: https://doi.org/10.1007/1-4020-7940-0_6
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4020-7899-6
Online ISBN: 978-1-4020-7940-5
eBook Packages: Springer Book Archive