Marginal likelihood for Markov-switching and change-point GARCH models

Bauwens, Luc [UCL] Dufays, Arnaud [UCL] Rombouts, Jeroen [ESSEC Business School, Cergy-Pontoise]

GARCH volatility models with fixed parameters are too restrictive for long time series due to breaks in the volatility process. Flexible alternatives are Markov-switching GARCH and change-point GARCH models. They require estimation by MCMC methods due to the path dependence problem. An unsolved issue is the computation of their marginal likelihood, which is essential for determining the number of regimes or change-points. We solve the problem by using particle MCMC, a technique proposed by Andrieu et al. (2010). We examine the performance of this new method on simulated data, and we illustrate its use on several return series.

• metadata
• relations

Document type	Article de périodique (Journal article) – Article de recherche
Access type	Accès interdit
Publication date	2014
Language	Anglais
Journal information	"Journal of Econometrics" - Vol. 178, Part 3, p. 508-522 (2014)
Peer reviewed	yes
Publisher	Elsevier BV * North-Holland ((Netherlands) Amsterdam)
issn	0304-4076
e-issn	1872-6895
Publication status	Publié
Affiliation	UCL - SSH/LIDAM/CORE - Center for operations research and econometrics
Keywords	Bayesian inference ; Simulation ; GARCH Markov-switching model ; Change-point model ; Marginal likelihood ; Particle MCMC
Links	http://hdl.handle.net/2078.1/136057[Handle] https://doi.org/10.1016/j.jeconom.2013.08.017[DOI]

See also
	[boreal:95704]	Marginal likelihood for Markov-switching and change-point GARCH models