On the Choice of Alternative Measures in Importance Sampling with Markov Chains

DOI10.1287/OPRE.43.3.509MaRDI QIDQ4861366zbMATH OpenOpenAlexFDO

Authors Sigrún Andradóttir, Daniel P. Heyman, Teunis J. Ott

Publication date 1 August 1996

Published in Operations Research (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1287/opre.43.3.509

zbMATH Keywords

distribution of the logarithm of the likelihood ratiolikelihood ratiosample path lengthsimulation of Markov chains

Mathematics Subject Classification ID

Applications of Markov chains and discrete-time Markov processes on general state spaces (social mobility, learning theory, industrial processes, etc.) (60J20) Sampling theory, sample surveys (62D05)

Recommendations

• Potentially unlimited variance reduction in importance sampling of Markov chains
• Importance sampling for markov chains: asymptotics for the variance
• Monte Carlo simulation and large deviations theory for uniformly recurrent Markov chains
• Examples comparing importance sampling and the Metropolis algorithm
• Importance Sampling for Stochastic Simulations

Cited in

(6)

• Alternative proof and interpretations for a recent state-dependent importance sampling scheme
• Examples comparing importance sampling and the Metropolis algorithm
• On the simulation of Markov chain steady-state distribution using CFTP algorithm
• Importance sampling for markov chains: asymptotics for the variance
• Potentially unlimited variance reduction in importance sampling of Markov chains
• The cross-entropy method with patching for rare-event simulation of large Markov chains

This page was built for publication: On the Choice of Alternative Measures in Importance Sampling with Markov Chains

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4861366)