When is Eaton's Markov chain irreducible?

DOI10.3150/07-BEJ6191zbMATH Open1131.60066arXiv0709.0448OpenAlexW3101609231MaRDI QIDQ2469645FDOQ2469645

Authors: James P. Hobert, Aixin Tan, Ruitao Liu 

Publication date: 6 February 2008

Published in: Bernoulli (Search for Journal in Brave)

Abstract: Consider a parametric statistical model $P(mathrmdx|heta)$ and an improper prior distribution $u(mathrmdheta)$ that together yield a (proper) formal posterior distribution $Q(mathrmdheta|x)$. The prior is called strongly admissible if the generalized Bayes estimator of every bounded function of $heta$ is admissible under squared error loss. Eaton [Ann. Statist. 20 (1992) 1147--1179] has shown that a sufficient condition for strong admissibility of $u$ is the local recurrence of the Markov chain whose transition function is $R(heta,mathrmdeta)=intQ(mathrmdeta|x)P(mathrmdx|heta)$. Applications of this result and its extensions are often greatly simplified when the Markov chain associated with $R$ is irreducible. However, establishing irreducibility can be difficult. In this paper, we provide a characterization of irreducibility for general state space Markov chains and use this characterization to develop an easily checked, necessary and sufficient condition for irreducibility of Eaton's Markov chain. All that is required to check this condition is a simple examination of $P$ and $u$. Application of the main result is illustrated using two examples.

Full work available at URL: https://arxiv.org/abs/0709.0448

Recommendations

• Eaton's Markov chain, its conjugate partner and \(\mathcal P\)-admissibility
• Evaluating improper priors and the recurrence of symmetric Markov chains: an overview
• Evaluating default priors with a generalization of Eaton's Markov chain
• Evaluation of formal posterior distributions via Markov chain arguments
• On perturbations of strongly admissible prior distributions

zbMATH Keywords

reversible Markov chainimproper prior distributionstrong admissibilitylocal recurrence

Mathematics Subject Classification ID

Discrete-time Markov processes on general state spaces (60J05)

Cites Work

• Title not available (Why is that?)
• Markov chains and stochastic stability
• A statistical diptych: Admissible inferences -- recurrence of symmetric Markov chains
• Admissibility in quadratically regular problems and recurrence of symmetric Markov chains: Why the connection?
• Eaton's Markov chain, its conjugate partner and \(\mathcal P\)-admissibility
• Conditions for recurrence and transience of a Markov chain on \(\mathbb Z^ +\) and estimation of a geometric success probability.
• On perturbations of strongly admissible prior distributions
• Title not available (Why is that?)
• Evaluating improper priors and the recurrence of symmetric Markov chains: an overview
• Markov chain conditions for admissibility in estimation problems with quadratic loss
• Stability of the tail Markov chain and the evaluation of improper priors for an exponential rate parameter

Cited In (8)

• Markov chain conditions for admissibility in estimation problems with quadratic loss
• Evaluating default priors with a generalization of Eaton's Markov chain
• Evaluation of formal posterior distributions via Markov chain arguments
• Admissibility in quadratically regular problems and recurrence of symmetric Markov chains: Why the connection?
• Conditions for recurrence and transience of a Markov chain on \(\mathbb Z^ +\) and estimation of a geometric success probability.
• The analysis of expected fitness and success ratio of two heuristic optimizations on two bimodal MaxSat problems
• On perturbations of strongly admissible prior distributions
• Recurrence and transience of a Markov chain on \(\mathbb{Z}^+\) and evaluation of prior distributions for a Poisson mean

This page was built for publication: When is Eaton's Markov chain irreducible?

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2469645)