Easily Computed Marginal Likelihoods from Posterior Simulation Using the THAMES Estimator
Open Access
- 1 September 2025
- journal article
- research article
- Published by Institute of Mathematical Statistics in Bayesian Analysis
- Vol. 20 (3) , 1-28
Abstract
We propose an easily computed estimator of the marginal likelihood from posterior simulation output, via reciprocal importance sampling, combining earlier proposals of DiCiccio et al (1997) and Robert and Wraith (2009). This involves only the unnormalized posterior densities from the sampled parameter values, and does not involve additional simulations beyond the main posterior simulation, or additional complicated calculations, provided that the parameter space is unconstrained. Even if this is not the case, the estimator is easily adjusted by a simple Monte Carlo approximation. It is unbiased for the reciprocal of the marginal likelihood, consistent, has finite variance, and is asymptotically normal. It involves one user-specified control parameter, and we derive an optimal way of specifying this. We illustrate it with several numerical examples.Keywords
All Related Versions
This publication has 25 references indexed in Scilit:
- Comparing methods for statistical inference with model uncertaintyProceedings of the National Academy of Sciences, 2022
- A First Course in Bayesian Statistical Methods2009
- The Elements of Statistical Learning2009
- Computational methods for Bayesian model choiceAIP Conference Proceedings, 2009
- Methods for inference in large multiple-equation Markov-switching modelsJournal of Econometrics, 2008
- Benchmark priors for Bayesian model averagingJournal of Econometrics, 2001
- Asymptotic Normality of Posterior Distributions for Exponential Families when the Number of Parameters Tends to InfinityJournal of Multivariate Analysis, 2000
- Bayes FactorsJournal of the American Statistical Association, 1995
- Prostate Specific Antigen in the Diagnosis and Treatment of Adenocarcinoma of the Prostate. II. Radical Prostatectomy Treated PatientsJournal of Urology, 1989
- Bayesian Estimation and Prediction Using Asymmetric Loss FunctionsJournal of the American Statistical Association, 1986