Bayesian frequentist hybrid inference

DOI10.1214/08-AOS649zbMATH Open1173.62012arXiv0908.3413OpenAlexW3104216992MaRDI QIDQ834347FDOQ834347

Authors: Ao Yuan 

Publication date: 19 August 2009

Published in: The Annals of Statistics (Search for Journal in Brave)

Abstract: Bayesian and frequentist methods differ in many aspects, but share some basic optimality properties. In practice, there are situations in which one of the methods is more preferred by some criteria. We consider the case of inference about a set of multiple parameters, which can be divided into two disjoint subsets. On one set, a frequentist method may be favored and on the other, the Bayesian. This motivates a joint estimation procedure in which some of the parameters are estimated Bayesian, and the rest by the maximum-likelihood estimator in the same parametric model, and thus keep the strengths of both the methods and avoid their weaknesses. Such a hybrid procedure gives us more flexibility in achieving overall inference advantages. We study the consistency and high-order asymptotic behavior of the proposed estimator, and illustrate its application. Also, the results imply a new method for constructing objective prior.

Full work available at URL: https://arxiv.org/abs/0908.3413

Recommendations

• Frequentist-Bayesian Monte Carlo testing
• A comparison of the Bayesian and frequentist approaches to estimation
• Blending Bayesian and frequentist methods according to the precision of prior information with applications to hypothesis testing
• Bayes/frequentist compromise decision rules for Gaussian sampling.
• Toward a Reconciliation of the Bayesian and Frequentist Approaches to Point Estimation

zbMATH Keywords

Bayesian inferenceconsistencyfrequentist inferencehybrid inferencehigh-order expansion

Mathematics Subject Classification ID

Point estimation (62F10) Asymptotic properties of parametric estimators (62F12) Bayesian inference (62F15) Estimation in multivariate analysis (62H12)

Cites Work

• Title not available (Why is that?)
• Profile likelihood and conditionally parametric models
• Title not available (Why is that?)
• The Selection of Prior Distributions by Formal Rules
• Title not available (Why is that?)
• Asymptotics in statistics: some basic concepts
• The interplay of Bayesian and frequentist analysis
• Integrated likelihood methods for eliminating nuisance parameters. (With comments and a rejoinder).
• Title not available (Why is that?)
• Title not available (Why is that?)
• On Profile Likelihood
• Note on the Consistency of the Maximum Likelihood Estimate
• Title not available (Why is that?)
• Asymptotic Normality of Semiparametric and Nonparametric Posterior Distributions
• On Bayes procedures
• Title not available (Why is that?)
• General frequentist properties of the posterior profile distribution
• An Inconsistent Maximum Likelihood Estimate
• Higher order semiparametric frequentist inference with the profile sampler
• Asymptotic Expansions Associated with Posterior Distributions
• Two Formulas for Numerical Indefinite Integration
• Title not available (Why is that?)
• Asymptotic Expansions Associated with Some Statistical Estimators in the Smooth Case. 1. Expansions of Random Variables
• Pseudo maximum likelihood estimation: Theory and applications
• Miscellanea. Second-order probability matching priors
• An Asymptotic Expansion for a Class of Estimators Containing Maximum Likelihood Estimators
• Consistency of maximum likelihood and Bayes estimates
• The Profile Sampler
• The 1988 Wald Memorial Lectures: The present position in Bayesian statistics. With comments and a rejoinder by the author
• Some contributions to the asymptotic theory of Bayes solutions
• Prediction of U.S. Cancer Mortality Counts Using Semiparametric Bayesian Techniques
• Bayesians, Frequentists, and Scientists
• Coverage probability bias, objective Bayes and the likelihood principle
• Unbiasedness as the Dual of Being Bayes
• Title not available (Why is that?)
• A Note on Bayes Estimates

Cited In (16)

• Joining forces of Bayesian and frequentist methodology: a study for inference in the presence of non-identifiability
• Conditionally exponential prior in focal near- and far-field EEG source localization via randomized multiresolution scanning (RAMUS)
• Bayesian-Frequentist Hybrid Inference in Applications with Small Sample Sizes
• A hybrid approach for regression analysis with block missing data
• Bayes/frequentist compromise decision rules for Gaussian sampling.
• Fully Bayesian aggregation
• Hybrid Bayesian inference on HIV viral dynamic models
• Simple estimators of false discovery rates given as few as one or two \(p\)-values without strong parametric assumptions
• Longitudinal data analysis using Bayesian-frequentist hybrid random effects model
• Bayesian neural tree models for nonparametric regression
• Blending Bayesian and frequentist methods according to the precision of prior information with applications to hypothesis testing
• Bayesian, classical and hybrid methods of inference when one parameter value is special
• Bayesian–frequentist hybrid model with application to the analysis of gene copy number changes
• Evaluating the accuracy of small \(p\)-values in genetic association studies using Edgeworth expansions
• Empirical Bayesian analysis through the lens of a particular class of constrained Bayesian hierarchical models
• Can Bayesian, confidence distribution and frequentist inference agree?

This page was built for publication: Bayesian frequentist hybrid inference

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q834347)