Universität zu Köln

Grothe, Oliver, Kleppe, Tore Selland and Liesenfeld, Roman ORCID: 0000-0001-6996-6215 (2019). The Gibbs sampler with particle efficient importance sampling for state-space models*. Econometric Reviews, 38 (10). 1152 -1176. PHILADELPHIA: TAYLOR & FRANCIS. ISSN 1532-4168

Full text not available from this repository.

Abstract

We consider Particle Gibbs (PG) for Bayesian analysis of non-linear non-Gaussian state-space models. As a Monte Carlo (MC) approximation of the Gibbs procedure, PG uses sequential MC (SMC) importance sampling inside the Gibbs to update the latent states. We propose to combine PG with the Particle Efficient Importance Sampling (PEIS). By using SMC sampling densities which are approximately globally fully adapted to the targeted density of the states, PEIS can substantially improve the simulation efficiency of the PG relative to existing PG implementations. The efficiency gains are illustrated in PG applications to a non-linear local-level model and stochastic volatility models.

Item Type:	Journal Article
Creators:	Creators Email ORCID ORCID Put Code Grothe, Oliver UNSPECIFIED UNSPECIFIED UNSPECIFIED Kleppe, Tore Selland UNSPECIFIED UNSPECIFIED UNSPECIFIED Liesenfeld, Roman UNSPECIFIED orcid.org/0000-0001-6996-6215 UNSPECIFIED
URN:	urn:nbn:de:hbz:38-127152
DOI:	10.1080/07474938.2018.1536098
Journal or Publication Title:	Econometric Reviews
Volume:	38
Number:	10
Page Range:	1152 -1176
Date:	2019
Publisher:	TAYLOR & FRANCIS
Place of Publication:	PHILADELPHIA
ISSN:	1532-4168
Language:	English
Faculty:	Faculty of Management, Economy and Social Sciences
Divisions:	Center of Excellence C-SEB
Subjects:	Economics
Uncontrolled Keywords:	Keywords Language INTEREST-RATES; SIMULATION; INFERENCE Multiple languages Economics; Mathematics, Interdisciplinary Applications; Social Sciences, Mathematical Methods; Statistics & Probability Multiple languages
Refereed:	Yes
URI:	http://kups.ub.uni-koeln.de/id/eprint/12715