Computing Marginal Likelihoods via Posterior Sampling

DOI10.1080/03610918.2012.707721MaRDI QIDQ5415865zbMATH OpenOpenAlexFDO

Authors Stephen G. Walker

Publication date 19 May 2014

Published in Communications in Statistics. Simulation and Computation (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1080/03610918.2012.707721

zbMATH Keywords

MCMCmarginal likelihoodlatent variableposterior sampling

Mathematics Subject Classification ID

Bayesian inference (62F15) Numerical analysis or methods applied to Markov chains (65C40)

Recommendations

• Randomized maximum likelihood based posterior sampling
• On the use of marginal posteriors in marginal likelihood estimation via importance sampling
• Computing marginal likelihoods via the Fourier integral theorem and pointwise estimation of posterior densities
• Computing marginal likelihoods from a single MCMC output
• Approximate methods for calculating marginals and likelihoods
• Marginal Likelihood Estimation via Power Posteriors
• Estimating marginal likelihoods from the posterior draws through a geometric identity
• A comparison of marginal likelihood computation methods
• scientific article; zbMATH DE number 4211273

Cites work

• Computing the Bayes factor from a Markov chain Monte Carlo simulation of the posterior distribution
• Reversible jump Markov chain Monte Carlo computation and Bayesian model determination

Cited in

(16)

• Estimating marginal likelihoods from the posterior draws through a geometric identity
• On the use of marginal posteriors in marginal likelihood estimation via importance sampling
• Randomized maximum likelihood based posterior sampling
• Estimating the marginal likelihood using the arithmetic mean identity
• Marginal Likelihood Estimation with the Cross-Entropy Method
• Improving power posterior estimation of statistical evidence
• Accept–reject Metropolis–Hastings sampling and marginal likelihood estimation
• Computing marginal likelihoods from a single MCMC output
• A new Monte Carlo method for estimating marginal likelihoods
• Computing the Bayes factor from a Markov chain Monte Carlo simulation of the posterior distribution
• -stable limit laws for harmonic mean estimators of marginal likelihoods
• Computing marginal likelihoods via the Fourier integral theorem and pointwise estimation of posterior densities
• Marginal Likelihood from the Gibbs Output
• Marginal Likelihood From the Metropolis–Hastings Output
• Computation of marginal likelihoods with data-dependent support for latent variables
• Posterior simulation via the signed root log-likelihood ratio

This page was built for publication: Computing Marginal Likelihoods via Posterior Sampling

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5415865)