Compatible Prior Distributions for Directed Acyclic Graph Models

DOI10.1111/j.1467-9868.2004.00431.xzbMath1062.62050OpenAlexW2147795518MaRDI QIDQ4665830

Guido Consonni, Alberto Roverato

Publication date: 11 April 2005

Published in: Journal of the Royal Statistical Society Series B: Statistical Methodology (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1111/j.1467-9868.2004.00431.x

zbMATH Keywords

invarianceBayes factordirected acyclic graphFisher information matrixgraphical modelreparameterizationJeffreys conditioninggroup reference priorreference conditioning

Mathematics Subject Classification ID

Bayesian inference (62F15) Applications of mathematical programming (90C90) Directed graphs (digraphs), tournaments (05C20)

Related Items

Sparse graphical models for exploring gene expression data, Compatibility of prior specifications across linear models, Multiple testing and error control in Gaussian graphical model selection, An encompassing prior generalization of the Savage-Dickey density ratio, Bayesian variable selection in linear regression, Conjugate and conditional conjugate Bayesian analysis of discrete graphical models of marginal independence, Optimal compromise between incompatible conditional probability distributions, with application to Objective Bayesian Kriging, Compatible priors for Bayesian model comparison with an application to the Hardy-Weinberg equilibrium model, The Bayes factor for inequality and about equality constrained models

Cites Work

• Parameter priors for directed acyclic graphical models and the characterization of several probability distributions
• Reference priors for exponential families
• On the invariance of noninformative priors
• Probabilistic Networks and Expert Systems
• Hyper Inverse Wishart Distribution for Non-decomposable Graphs and its Application to Bayesian Inference for Gaussian Graphical Models
• Chain Graph Models and their Causal Interpretations
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item