The curved exponential family of a staged tree

DOI10.1214/22-EJS1984MaRDI QIDQ2137807zbMATH OpenOpenAlexWikidataFDO

Authors Christiane Görgen, Manuele Leonelli, Orlando Marigliano

Publication date 11 May 2022

Published in Electronic Journal of Statistics (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2010.15515, https://projecteuclid.org/journals/electronic-journal-of-statistics/volume-16/issue-1/The-curved-exponential-family-of-a-staged-tree/10.1214/22-EJS1984.full

zbMATH Keywords

chain event graphgraphical modelBayesian information criterioncurved exponential familystaged tree

Mathematics Subject Classification ID

Multivariate analysis (62H99) Artificial intelligence (68T99)

Abstract: Staged tree models are a discrete generalization of Bayesian networks. We show that these form curved exponential families and derive their natural parameters, sufficient statistic, and cumulant-generating function as functions of their graphical representation. We give necessary and sufficient graphical criteria for classifying regular subfamilies and discuss implications for model selection.

Recommendations

• Staged tree models with toric structure
• Equations defining probability tree models
• Gröbner bases for staged trees
• Equivalence classes of staged trees
• Tree cumulants and the geometry of binary tree models

Cites work

• scientific article; zbMATH DE number 1055955 (Why is no real title available?)
• scientific article; zbMATH DE number 1134987 (Why is no real title available?)
• scientific article; zbMATH DE number 918134 (Why is no real title available?)
• A new family of non-local priors for chain event graph model selection
• Algebraic statistical models
• Bayesian MAP model selection of chain event graphs
• Bayesian decision analysis. Principles and practice.
• CUMULANTS OF MULTIVARIATE MULTINOMIAL DISTRIBUTIONS
• Causal discovery through MAP selection of stratified chain event graphs
• Chain event graphs
• Equations defining probability tree models
• Equivalence classes of staged trees
• Estimating the dimension of a model
• Gröbner bases for staged trees
• On the choice of a model to fit data from an exponential family
• Probabilistic graphical models.
• Refining a Bayesian network using a chain event graph
• Stratified exponential families: Graphical models and model selection
• Structure estimation for discrete graphical models: generalized covariance matrices and their inverses
• The geometry of exponential families

Cited in

(2)

• Staged tree models with toric structure
• Equivalence classes of staged trees

Describes a project that uses

Uses Software

• stagedtrees

This page was built for publication: The curved exponential family of a staged tree

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2137807)