Accuracy and validity of posterior distributions using the Cressie-Read empirical likelihoods

2017/08/02 by Laura Turbatu, Turbatu, Laura
Mathematics · #62G99 #62J12 #FOS: Mathematics #Statistical Distribution Estimation and Applications #Statistical Methods and Bayesian Inference #Statistical Methods and Inference #Statistics Theory (math.ST) #math.ST #msc:62G99 #msc:62J12 #stat.TH

paper · pdf · doi:10.48550/arxiv.1708.00711

33 pages, 1 figure

openalex publication_date 2017/08/02 · openalex created_date 2017/08/17 · arxiv created 2017/11/02 · arxiv updated 2017/11/03 · openalex updated_date 2026/07/28

Abstract

The class of Cressie-Read empirical likelihoods are constructed with weights derived at a minimum distance from the empirical distribution in the Cressie-Read family of divergences indexed by γ under the constraint of an unbiased set of M-estimating equations. At first order, they provide valid posterior probability statements for any given prior, but the bias in coverage of the resulting empirical quantile is inversely proportional to the asymptotic efficiency of the corresponding M-estimator. The Cressie-Read empirical likelihoods based on the maximum likelihood estimating equations bring about quantiles covering with O(n^-1) accuracy at the underlying posterior distribution. The choice of γ has an impact on the variance in small samples of the posterior quantile function. Examples are given for the M-type estimating equations of location and for the quasi-likelihood functions in the generalized linear models.

Citations

• Robust Estimation of a Location Parameter
• Empirical likelihood ratio confidence intervals for a single functional

Related

• Asymptotic normality, concentration, and coverage of generalized posteriors
• On the computation of the marginal likelihood
• The empirical likelihood prior applied to bias reduction of general\n estimating equations
• On approximate robust confidence distributions
• Empirical likelihood for linear models with spatial errors