Posterior consistency for partially observed Markov models

DOI10.1016/J.SPA.2019.03.012zbMATH Open1471.60107arXiv1608.06851OpenAlexW2964101981WikidataQ128154109 ScholiaQ128154109MaRDI QIDQ2289808FDOQ2289808

Authors: Randal Douc, Jimmy Olsson, François Roueff 

Publication date: 24 January 2020

Published in: Stochastic Processes and their Applications (Search for Journal in Brave)

Abstract: In this work we establish the posterior consistency for a parametrized family of partially observed, fully dominated Markov models. As a main assumption, we suppose that the prior distribution assigns positive probability to all neighborhoods of the true parameter, for a distance induced by the expected Kullback-Leibler divergence between the family members' Markov transition densities. This assumption is easily checked in general. In addition, under some additional, mild assumptions we show that the posterior consistency is implied by the consistency of the maximum likelihood estimator. The latter has recently been established also for models with non-compact state space. The result is then extended to possibly non-compact parameter spaces and non-stationary observations. Finally, we check our assumptions on examples including the partially observed Gaussian linear model with correlated noise and a widely used stochastic volatility model.

Full work available at URL: https://arxiv.org/abs/1608.06851

Recommendations

• Bayesian consistency for Markov models
• scientific article; zbMATH DE number 5770656
• Posterior consistency in conditional distribution estimation
• Posterior consistency for some semi-parametric problems
• Posterior consistency for nonparametric hidden Markov models with finite state space
• Bayesian consistency for a nonparametric stationary Markov model
• Perfect posterior simulation for mixture and hidden Markov models
• Estimation for partially observed Markov processes
• On the consistency of posterior mixtures and its applications

zbMATH Keywords

Kullback-Leibler divergencedominated Markov models

Mathematics Subject Classification ID

Bayesian inference (62F15) Markov processes: estimation; hidden Markov models (62M05) Discrete-time Markov processes on general state spaces (60J05)

Cites Work

• Title not available (Why is that?)
• Inference in hidden Markov models.
• Ergodicity of observation-driven time series models and consistency of the maximum likelihood estimator
• Particle Markov Chain Monte Carlo Methods
• Markov chains and stochastic stability
• On some properties of Markov chain Monte Carlo simulation methods based on the particle filter
• Statistical Inference for Probabilistic Functions of Finite State Markov Chains
• Stochastic volatility models as hidden Markov models and statistical applications
• Maximum-likelihood estimation for hidden Markov models
• The consistency of posterior distributions in nonparametric problems
• Hidden Markov Models for Speech Recognition
• Hidden Markov models in finance
• Probability essentials
• About the posterior distribution in hidden Markov models with unknown number of states
• Probabilistic Functions of Finite State Markov Chains
• Subadditive ergodic theory
• Hidden Markov Models for Time Series
• Consistency of the maximum likelihood estimator for general hidden Markov models
• The strong ergodic theorem for densities: Generalized Shannon-McMillan- Breiman theorem
• Parameter estimation and asymptotic stability in stochastic filtering
• Asymptotic properties of the maximum likelihood estimator in autoregressive models with Markov regime
• Asymptotics of the maximum likelihood estimator for general hidden Markov models
• Asymptotic behavior of Bayes estimators for hidden Markov models with application to ion channels
• Hidden Markov chains and the analysis of genome structure
• Leroux's method for general hidden Markov models
• Correlation functions of a function of a finite-state Markov process with application to channel kinetics
• Asymptotic properties of the maximum likelihood estimation in misspecified hidden Markov models
• Posterior consistency for nonparametric hidden Markov models with finite state space

Cited In (9)

• Asymptotic analysis of model selection criteria for general hidden Markov models
• Bayes posterior convergence for loss functions via almost additive thermodynamic formalism
• Convergence in Markovian models with implications for efficiency of inference
• Bayesian consistency for Markov models
• Posterior consistency for nonparametric hidden Markov models with finite state space
• Title not available (Why is that?)
• Nonasymptotic control of the MLE for misspecified nonparametric hidden Markov models
• Bayesian consistency for a nonparametric stationary Markov model
• Gibbs posterior convergence and the thermodynamic formalism

This page was built for publication: Posterior consistency for partially observed Markov models

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2289808)