Parameter priors for directed acyclic graphical models and the characterization of several probability distributions

DOI10.1214/AOS/1035844981zbMATH Open1016.62064arXiv2105.03248OpenAlexW2950017290MaRDI QIDQ79791

David Heckerman, Dan Geiger, Dan Geiger, David Heckerman

Publication date: 1 October 2002

Published in: The Annals of Statistics (Search for Journal in Brave)

Abstract: We develop simple methods for constructing parameter priors for model choice among Directed Acyclic Graphical (DAG) models. In particular, we introduce several assumptions that permit the construction of parameter priors for a large number of DAG models from a small set of assessments. We then present a method for directly computing the marginal likelihood of every DAG model given a random sample with no missing observations. We apply this methodology to Gaussian DAG models which consist of a recursive set of linear regression models. We show that the only parameter prior for complete Gaussian DAG models that satisfies our assumptions is the normal-Wishart distribution. Our analysis is based on the following new characterization of the Wishart distribution: let $W$ be an $nimesn$, $nge3$, positive-definite symmetric matrix of random variables and $f(W)$ be a pdf of $W$. Then, f$(W)$ is a Wishart distribution if and only if $W_{11}-W_{12}{W}_{22}^{-1}W{\text{'}}_{12}$ is independent of $W_{12},W_{22}$ for every block partitioning $W_{11},W_{12},W{\text{'}}_{12},W_{22}$ of $W$. Similar characterizations of the normal and normal-Wishart distributions are provided as well.

Full work available at URL: https://arxiv.org/abs/2105.03248

zbMATH Keywords

Bayesian networkdirected acyclic graphical modelDirichlet distributionGaussian DAG modellearninglinear regression modelnormal distributionWishart distribution

Mathematics Subject Classification ID

Probability distributions: general theory (60E05) Applications of graph theory (05C90) Characterization and structure theory for multivariate probability distributions; copulas (62H05) Directed graphs (digraphs), tournaments (05C20) Functional equations and inequalities (39B99) Bayesian problems; characterization of Bayes procedures (62C10)

Cites Work

• 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?)
• Title not available (Why is that?)
• Parameter priors for directed acyclic graphical models and the characterization of several probability distributions
• On regular solutions of functional equations
• A Bayesian method for the induction of probabilistic networks from data
• Regularity property of the functional equation of the Dirichlet distribution
• Hyper Markov laws in the statistical analysis of decomposable graphical models
• A characterization of Markov equivalence classes for acyclic digraphs
• A characterization of the Dirichlet distribution through global and local parameter independence
• Bayesian analysis in expert systems. With comments and a rejoinder by the authors
• Learning Bayesian networks: The combination of knowledge and statistical data
• A characterization of the bivariate Wishart distribution
• Bayesian model averaging and model selection for markov equivalence classes of acyclic digraphs
• Sequential updating of conditional probabilities on directed graphical structures

Cited In (52)

• On the exact and approximate distributions of the product of a Wishart matrix with a normal vector
• Sensitivity to hyperprior parameters in Gaussian Bayesian networks
• Bayesian learning of multiple directed networks from observational data
• The Matsumoto\,-\,Yor property and the structure of the Wishart distribution
• Title not available (Why is that?)
• Distribution of the product of a singular Wishart matrix and a normal vector
• Complexity analysis of Bayesian learning of high-dimensional DAG models and their equivalence classes
• Compatible priors for model selection of high-dimensional Gaussian DAGs
• Objective Bayes Factors for Gaussian Directed Acyclic Graphical Models
• Objective Bayes model selection of Gaussian interventional essential graphs for the identification of signaling pathways
• Discovering causal graphs with cycles and latent confounders: an exact branch-and-bound approach
• Comparing Score-Based Methods for Estimating Bayesian Networks Using the Kullback–Leibler Divergence
• Being Bayesian about learning Bayesian networks from ordinal data
• Bayesian sample size determination for causal discovery
• NetVIX -- a network volatility index of financial markets
• Posterior graph selection and estimation consistency for high-dimensional Bayesian DAG models
• On the robustness of Bayesian networks to learning from non-conjugate sampling
• Compatible Prior Distributions for Directed Acyclic Graph Models
• Learning Markov equivalence classes of directed acyclic graphs: an objective Bayes approach
• Equivalence class selection of categorical graphical models
• Bayesian graphical models for modern biological applications
• High-dimensional covariance estimation for Gaussian directed acyclic graph models with given order
• Parametrizations and reference priors for multinomial decomposable graphical models
• Model averaging for sparse seemingly unrelated regression using Bayesian networks among the errors
• Bayesian Approaches for Large Biological Networks
• More on connections between Wishart and matrix GIG distributions
• Addendum on the scoring of Gaussian directed acyclic graphical models
• Estimating Bayesian networks for high-dimensional data with complex mean structure and random effects
• Kummer and gamma laws through independences on trees -- another parallel with the Matsumoto-Yor property
• Objective Bayesian search of Gaussian directed acyclic graphical models for ordered variables with non-local priors
• Bayesian causal inference in probit graphical models
• Bayesian Model Selection of Gaussian Directed Acyclic Graph Structures
• Being Bayesian about learning Gaussian Bayesian networks from incomplete data
• BiDAG
• Parameter priors for directed acyclic graphical models and the characterization of several probability distributions
• Parameter Estimation for Undirected Graphical Models With Hard Constraints
• A Gibbs sampler for learning DAG: a unification for discrete and Gaussian domains
• Kshirsagar-Tan independence property of beta matrices and related characterizations
• Causal structure learning: a combinatorial perspective
• The use of unlabeled data in predictive modeling
• Structural learning and estimation of joint causal effects among network-dependent variables
• A review of Gaussian Markov models for conditional independence
• Modeling risk contagion in the Italian zonal electricity market
• Efficient Sampling and Structure Learning of Bayesian Networks
• Learning Gaussian graphical models with fractional marginal pseudo-likelihood
• Bayesian inference of causal effects from observational data in Gaussian graphical models
• Sparse graphical models for exploring gene expression data
• A loss‐based prior for Gaussian graphical models
• Hyper Inverse Wishart Distribution for Non-decomposable Graphs and its Application to Bayesian Inference for Gaussian Graphical Models
• Efficient local updates for undirected graphical models
• Bayesian graphical modeling for heterogeneous causal effects
• Continuity approximation in hybrid Bayesian networks structure learning

Uses Software

• elicit-normlin

This page was built for publication: Parameter priors for directed acyclic graphical models and the characterization of several probability distributions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q79791)