A review of Gaussian Markov models for conditional independence

Abstract

Markov models lie at the interface between statistical independence in a probability distribution and graph separation properties. We review model selection and estimation in directed and undirected Markov models with Gaussian parametrization, emphasizing the main similarities and differences. These two model classes are similar but not equivalent, although they share a common intersection. We present the existing results from a historical perspective, taking into account the amount of literature existing from both the artificial intelligence and statistics research communities, where these models were originated. We cover classical topics such as maximum likelihood estimation and model selection via hypothesis testing, but also more modern approaches like regularization and Bayesian methods. We also discuss how the Markov models reviewed fit in the rich hierarchy of other, higher level Markov model classes. Finally, we close the paper overviewing relaxations of the Gaussian assumption and pointing out the main areas of application where these Markov models are nowadays used.

Fix author signature

References in corpus (14)

• Sparse permutation invariant covariance estimation
• Lasso-type recovery of sparse representations for high-dimensional data
• Strong Completeness and Faithfulness in Bayesian Networks
• Regularized rank-based estimation of high-dimensional nonparanormal graphical models
• Geometry of the faithfulness assumption in causal inference
• Directed Cyclic Graphical Representations of Feedback Models
• Wishart distributions for decomposable graphs
• Parameter Priors for Directed Acyclic Graphical Models and the Characterization of Several Probability Distributions
• Discrete chain graph models
• Flexible covariance estimation in graphical Gaussian models
• Nested Markov Properties for Acyclic Directed Mixed Graphs
• Elliptical graphical modelling
• Probability distributions with summary graph structure
• Learning Local Dependence In Ordered Data

Cited by in corpus (1)

• Sparse Cholesky covariance parametrization for recovering latent structure in ordered data