EconStor >
Christian-Albrechts-Universität Kiel (CAU) >
Department of Economics, Universität Kiel  >
Economics Working Papers, Department of Economics, CAU Kiel >

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10419/53125
  
Title:Efficient high-dimensional importance sampling in mixture frameworks PDF Logo
Authors:Kleppe, Tore Selland
Liesenfeld, Roman
Issue Date:2011
Series/Report no.:Economics working paper / Christian-Albrechts-Universität Kiel, Department of Economics 2011,11
Abstract:This paper provides high-dimensional and flexible importance sampling procedures for the likelihood evaluation of dynamic latent variable models involving finite or infinite mixtures leading to possibly heavy tailed and/or multi-modal target densities. Our approach is based upon the efficient importance sampling (EIS) approach of Richard and Zhang (2007) and exploits the mixture structure of the model when constructing importance sampling distributions as mixture of distributions. The proposed mixture EIS procedures are illustrated with ML estimation of a student-t state space model for realized volatilities and a stochastic volatility model with leverage effects and jumps for asset returns.
Subjects:dynamic latent variable model
importance sampling
marginalized likelihood
mixture
Monte Carlo
realized volatility
stochastic volatility
JEL:C15
Document Type:Working Paper
Appears in Collections:Economics Working Papers, Department of Economics, CAU Kiel

Files in This Item:
File Description SizeFormat
679408649.pdf1.83 MBAdobe PDF
No. of Downloads: Counter Stats
Download bibliographical data as: BibTeX
Share on:http://hdl.handle.net/10419/53125

Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.