Consistent estimation of the basic neighborhood of Markov random fields

Abstract

For Markov random fields on ${\mathbb{Z}}^d$ with finite state space, we address the statistical estimation of the basic neighborhood, the smallest region that determines the conditional distribution at a site on the condition that the values at all other sites are given. A modification of the Bayesian Information Criterion, replacing likelihood by pseudo-likelihood, is proved to provide strongly consistent estimation from observing a realization of the field on increasing finite regions: the estimated basic neighborhood equals the true one eventually almost surely, not assuming any prior bound on the size of the latter. Stationarity of the Markov field is not required, and phase transition does not affect the results.

Published at http://dx.doi.org/10.1214/009053605000000912 in the Annals of Statistics (http://www.imstat.org/aos/) by the Institute of Mathematical Statistics (http://www.imstat.org)

Cited by in corpus (17)

• High-dimensional Ising model selection using ${\ell }_1$-regularized logistic regression
• On Learning Discrete Graphical Models Using Greedy Methods
• Marginal Pseudo-Likelihood Learning of Markov Network structures
• Neighborhood radius estimation in Variable-neighborhood Random Fields
• Goodness of fit tests for a class of Markov random field models
• Structure learning of antiferromagnetic Ising models
• Sparsistent Estimation of Time-Varying Discrete Markov Random Fields
• Estimating the interaction graph of stochastic neural dynamics
• High Dimensional Structure Learning of Ising Models on Sparse Random Graphs
• Mixture of hidden Markov models for accelerometer data
• Structure Learning of Contextual Markov Networks using Marginal Pseudo-likelihood
• Sharp oracle inequalities and slope heuristic for specification probabilities estimation in discrete random fields
• Privately Learning Markov Random Fields
• Covariate-Assisted Bayesian Graph Learning for Heterogeneous Data
• Hidden Gibbs random fields model selection using Block Likelihood Information Criterion
• Pseudo-likelihood-based $M$-estimation of random graphs with dependent edges and parameter vectors of increasing dimension
• Statistical Inference in the Differential Privacy Model