EconStor >
Stockholm School of Economics >
EFI - The Economic Research Institute, Stockholm School of Economics >
SSE/EFI Working Paper Series in Economics and Finance, EFI - The Economic Research Institute, Stockholm School of Economics >

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

http://hdl.handle.net/10419/56369
  
Title:Metropolis-Hastings prefetching algorithms PDF Logo
Authors:Strid, Ingvar
Issue Date:2008
Series/Report no.:SSE/EFI Working Paper Series in Economics and Finance 706
Abstract:Prefetching is a simple and general method for single-chain parallelisation of the Metropolis-Hastings algorithm based on the idea of evaluating the posterior in parallel and ahead of time. Improved Metropolis-Hastings prefetching algorithms are presented and evaluated. It is shown how to use available information to make better predictions of the future states of the chain and increase the efficiency of prefetching considerably. The optimal acceptance rate for the prefetching random walk Metropolis-Hastings algorithm is obtained for a special case and it is shown to decrease in the number of processors employed. The performance of the algorithms is illustrated using a well-known macroeconomic model. Bayesian estimation of DSGE models, linearly or nonlinearly approximated, is identi…ed as a potential area of application for prefetching methods. The generality of the proposed method, however, suggests that it could be applied in other contexts as well.
Subjects:Prefetching
Metropolis-Hastings
Parallel Computing
DSGE models
Optimal acceptance rate
Markov Chain Monte Carlo (MCMC)
JEL:C11
C13
C63
Document Type:Working Paper
Appears in Collections:SSE/EFI Working Paper Series in Economics and Finance, EFI - The Economic Research Institute, Stockholm School of Economics

Files in This Item:
File Description SizeFormat
587124989.pdf312.25 kBAdobe PDF
No. of Downloads: Counter Stats
Download bibliographical data as: BibTeX
Share on:http://hdl.handle.net/10419/56369

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