Bayesian MAP model selection of chain event graphs

DOI10.1016/J.JMVA.2011.03.008zbMATH Open1216.62039arXiv0904.0977OpenAlexW2121589081MaRDI QIDQ548650FDOQ548650

Jim Q. Smith, Guy Freeman

Publication date: 29 June 2011

Published in: Journal of Multivariate Analysis (Search for Journal in Brave)

Abstract: The class of chain event graph models is a generalisation of the class of discrete Bayesian networks, retaining most of the structural advantages of the Bayesian network for model interrogation, propagation and learning, while more naturally encoding asymmetric state spaces and the order in which events happen. In this paper we demonstrate how with complete sampling, conjugate closed form model selection based on product Dirichlet priors is possible, and prove that suitable homogeneity assumptions characterise the product Dirichlet prior on this class of models. We demonstrate our techniques using two educational examples.

Full work available at URL: https://arxiv.org/abs/0904.0977

Recommendations

• Chain event graphs
• A new family of non-local priors for chain event graph model selection
• Conditional independence and chain event graphs
• The dynamic chain event graph
• Refining a Bayesian network using a chain event graph

zbMATH Keywords

Dirichlet distributionBayesian model selection

Mathematics Subject Classification ID

Bayesian inference (62F15) Applications of graph theory (05C90) Theory of languages and software systems (knowledge-based systems, expert systems, etc.) for artificial intelligence (68T35)

Cites Work

• Conditional independence and chain event graphs
• Title not available (Why is that?)
• Title not available (Why is that?)
• A characterization of the Dirichlet distribution through global and local parameter independence
• Sequential updating of conditional probabilities on directed graphical structures
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Causal analysis with chain event graphs
• Title not available (Why is that?)
• An invariant form for the prior probability in estimation problems
• Probabilistic Networks and Expert Systems
• A Quantitative Study of Gene Regulation Involved in the Immune Response of Anopheline Mosquitoes
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)

Cited In (16)

• Chain event graphs for informed missingness
• Sensitivity analysis beyond linearity
• Equivalence classes of staged trees
• Context-specific graphical models for discrete longitudinal data
• Refining a Bayesian network using a chain event graph
• Beyond conjugacy for chain event graph model selection
• Causal discovery through MAP selection of stratified chain event graphs
• The curved exponential family of a staged tree
• Discovery of statistical equivalence classes using computer algebra
• The dynamic chain event graph
• Distributional Kalman filters for Bayesian forecasting and closed form recurrences
• A modeling method and application of emergent event chain based on Bayesian network
• Coherent combination of probabilistic outputs for group decision making: an algebraic approach
• The role of local partial independence in learning of Bayesian networks
• Causal analysis with chain event graphs
• Towards a Bayesian Analysis of Migration Pathways Using Chain Event Graphs of Agent Based Models

This page was built for publication: Bayesian MAP model selection of chain event graphs

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q548650)