Bayesian inference for Gibbs random fields using composite likelihoods

Gibbs random fields play an important role in statistics, for example the autologistic model is commonly used to model the spatial distribution of binary variables defined on a lattice. However they are complicated to work with due to an intractability of the likelihood function. It is therefore natural to consider tractable approximations to the likelihood function. Composite likelihoods offer a principled approach to constructing such approximation. The contribution of this paper is to examine the performance of a collection of composite likelihood approximations in the context of Bayesian inference.

• Publication year

  2012

• Venue

  Online World Conference on Soft Computing in Industrial Applications

• Publication date

  2012-07-24

• Fields of study

  Mathematics, Computer Science

• Identifiers
  DOI 10.1109/WSC.2012.6465236arXiv 1207.5758
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Author Biography

  2018cited by this paper
• Bayesian composite marginal likelihoods

  2011cited by this paper
• Statistical Inference for Stochastic Processes

  2011cited by this paper
• EXTENDING PSEUDO-LIKELIHOOD FOR POTTS MODELS

  2011cited by this paper
• Learning with Blocks: Composite Likelihood and Contrastive Divergence

  2010cited by this paper
• Bayesian Inference in Hidden Markov Random Fields for Binary Data Defined on Large Lattices

  2009cited by this paper
• An introduction to exponential random graph (p*) models for social networks

  2007cited by this paper
• Recursive computing and simulation-free inference for general factorizable models

  2007cited by this paper
• MCMC for Doubly-intractable Distributions

  2006cited by this paper
• An efficient Markov chain Monte Carlo method for distributions with intractable normalising constants

  2006cited by this paper
• Efficient recursions for general factorisable models

  2004cited by this paper
• A note on pseudolikelihood constructed from marginal densities

  2004cited by this paper
• Bayesian Methods for Hidden Markov Models

  2002cited by this paper
• Pairwise likelihood methods for inference in image models

  1999cited by this paper
• Computational Bayesian Analysis of Hidden Markov Models

  1998cited by this paper
• A Composite Likelihood Approach to Binary Spatial Data

  1998cited by this paper
• Consistent and Asymptotically Normal Parameter Estimates for Hidden Markov Models

  1994cited by this paper
• Constrained Monte Carlo Maximum Likelihood for Dependent Data

  1992cited by this paper
• A Hidden Markov Model for Space‐Time Precipitation

  1991cited by this paper
• Statistical Inference in Stochastic Processes

  1982cited by this paper
• Statistical Analysis of Non-Lattice Data

  1975influential reference
• Spatial Interaction and the Statistical Analysis of Lattice Systems

  1974cited by this paper
• Nearest‐Neighbour Systems and the Auto‐Logistic Model for Binary Data

  1972influential reference

• Enabling Inference for Context-Dependent Models of Mutation by Bounding the Propagation of Dependency

  2021cites this paper
• Bayesian Computation with Intractable Likelihoods

  2020cites this paper
• Asymptotic Normality, Concentration, and Coverage of Generalized Posteriors

  2019influential citation
• Coevolution Regression and Composite Likelihood Estimation for Social Networks

  2018cites this paper
• Noisy Hamiltonian Monte Carlo for Doubly Intractable Distributions

  2017cites this paper
• R Package bayesImageS : Bayesian Methods for Image Segmentation using a Hidden Potts Model

  2017cites this paper
• Hidden Gibbs random fields model selection using Block Likelihood Information Criterion

  2016influential citation
• Conditional Random Fields for Pattern Recognition Applied to Structured Data

  2015cites this paper
• Calibration of conditional composite likelihood for Bayesian inference on Gibbs random fields

  2015cites this paper
• Conditional Random Fields for Modeling Structured Data

  2015cites this paper
• Scalable Bayesian Inference for the Inverse Temperature of a Hidden Potts Model

  2015influential citation
• Bayesian analysis for time series of count data

  2014cites this paper
• Adaptive ABC model choice and geometric summary statistics for hidden Gibbs random fields

  2014cites this paper
• Report of President 2011/2012 - School of Mathematical Sciences

  2012cites this paper