The author would like to thank Editor, Akira Okada, anonymous referees, Yasuhiro Omori, Mike West, Siddhartha Chib, Herman van Dijk, Sylvia Frühwirth-Schnatter, Alan Gelfand, James LeSage, Teruo Nakatsuma and Wolfgang Polasek for their helpful comments and suggestions. The author received an Honorable Mention for the earlier version of this paper in 2009 BEST Award for Student Research, Department of Statistical Science, Duke University. The computational results are generated using Ox version 4.02 (Doornik, 2006).
BAYESIAN ANALYSIS OF GENERALIZED AUTOREGRESSIVE CONDITIONAL HETEROSKEDASTICITY AND STOCHASTIC VOLATILITY: MODELING LEVERAGE, JUMPS AND HEAVY-TAILS FOR FINANCIAL TIME SERIES*
Article first published online: 25 MAY 2011
© 2011 Japanese Economic Association
Japanese Economic Review
Volume 63, Issue 1, pages 81–103, March 2012
How to Cite
NAKAJIMA, J. (2012), BAYESIAN ANALYSIS OF GENERALIZED AUTOREGRESSIVE CONDITIONAL HETEROSKEDASTICITY AND STOCHASTIC VOLATILITY: MODELING LEVERAGE, JUMPS AND HEAVY-TAILS FOR FINANCIAL TIME SERIES. Japanese Economic Review, 63: 81–103. doi: 10.1111/j.1468-5876.2011.00537.x
- Issue published online: 9 FEB 2012
- Article first published online: 25 MAY 2011
- Final version accepted 2 April 2011.
This paper develops a Bayesian model comparison of two broad major classes of varying volatility model, the generalized autoregressive conditional heteroskedasticity and stochastic volatility models, on financial time series. The leverage effect, jumps and heavy-tailed errors are incorporated into the two models. For estimation, the efficient Markov chain Monte Carlo methods are developed and the model comparisons are examined based on the marginal likelihood. The empirical analyses are illustrated using the daily return data of US stock indices, individual securities and exchange rates of UK sterling and Japanese yen against the US dollar. The estimation results indicate that the stochastic volatility model with leverage and Student-t errors yield the best performance among the competing models.