On Monte Carlo methods for estimating ratios of normalizing constants
Open Access
- 1 August 1997
- journal article
- Published by Institute of Mathematical Statistics in The Annals of Statistics
- Vol. 25 (4) , 1563-1594
- https://doi.org/10.1214/aos/1031594732
Abstract
Recently, estimating ratios of normalizing constants has played an important role in Bayesian computations. Applications of estimating ratios of normalizing constants arise in many aspects of Bayesian statistical inference. In this article, we present an overview and discuss the current Monte Carlo methods for estimating ratios of normalizing constants. Then we propose a new ratio importance sampling method and establish its theoretical framework. We find that the ratio importance sampling method can be better than the current methods, for example, the bridge sampling method (Meng and Wong) and the path sampling method (Gelman and Meng), in the sense of minimizing asymptotic relative mean-square errors of estimators. An example is given for illustrative purposes. Finally, we present two special applications and the general implementation issues for estimating ratios of normalizing constants.Keywords
This publication has 17 references indexed in Scilit:
- A general Bahadur representation of M-estimators and its application to linear regression with nonstochastic designsThe Annals of Statistics, 1996
- The Intrinsic Bayes Factor for Model Selection and PredictionJournal of the American Statistical Association, 1996
- Marginal Likelihood from the Gibbs OutputJournal of the American Statistical Association, 1995
- Markov Chains for Exploring Posterior DistributionsThe Annals of Statistics, 1994
- Importance-Weighted Marginal Bayesian Posterior Density EstimationJournal of the American Statistical Association, 1994
- Performance of the Gibbs, Hit-and-Run, and Metropolis SamplersJournal of Computational and Graphical Statistics, 1993
- Bayesian Analysis of Constrained Parameter and Truncated Data Problems Using Gibbs SamplingJournal of the American Statistical Association, 1992
- Sampling-Based Approaches to Calculating Marginal DensitiesJournal of the American Statistical Association, 1990
- Bayesian Inference in Econometric Models Using Monte Carlo IntegrationEconometrica, 1989
- Rate of Convergence of One- and Two-Step $M$-Estimators with Applications to Maximum Likelihood and Pitman EstimatorsThe Annals of Statistics, 1985