Markov equivalence of marginalized local independence graphs

DOI10.1214/19-AOS1821zbMATH Open1441.62221arXiv1802.10163OpenAlexW2788264713MaRDI QIDQ2176633FDOQ2176633

Authors: Søren Wengel Mogensen, Niels Richard Hansen 

Publication date: 5 May 2020

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

Abstract: Symmetric independence relations are often studied using graphical representations. Ancestral graphs or acyclic directed mixed graphs with $m$-separation provide classes of symmetric graphical independence models that are closed under marginalization. Asymmetric independence relations appear naturally for multivariate stochastic processes, for instance in terms of local independence. However, no class of graphs representing such asymmetric independence relations, which is also closed under marginalization, has been developed. We develop the theory of directed mixed graphs with $mu$-separation and show that this provides a graphical independence model class which is closed under marginalization and which generalizes previously considered graphical representations of local independence. For statistical applications, it is pivotal to characterize graphs that induce the same independence relations as such a Markov equivalence class of graphs is the object that is ultimately identifiable from observational data. Our main result is that for directed mixed graphs with $mu$-separation each Markov equivalence class contains a maximal element which can be constructed from the independence relations alone. Moreover, we introduce the directed mixed equivalence graph as the maximal graph with edge markings. This graph encodes all the information about the edges that is identifiable from the independence relations, and furthermore it can be computed efficiently from the maximal graph.

Full work available at URL: https://arxiv.org/abs/1802.10163

Recommendations

• On the Markov Equivalence of Chain Graphs, Undirected Graphs, and Acyclic Digraphs
• Graphical Models and Message-Passing Algorithms: Some Introductory Lectures
• Graphical models for event history analysis based on local independence
• Markov properties for mixed graphs
• scientific article; zbMATH DE number 922429
• Marginals of DAG-Isomorphic Independence Models
• Markov equivalence in Bayesian networks

zbMATH Keywords

independence model\(\mu\)-separationMarkov equivalencelocal independencedirected mixed graphslocal independence graph

Mathematics Subject Classification ID

Markov processes: estimation; hidden Markov models (62M05) Applications of statistics to biology and medical sciences; meta analysis (62P10) Foundations and philosophical topics in statistics (62A01) Probabilistic graphical models (62H22)

Cites Work

• Causality. Models, reasoning, and inference
• Extended conditional independence and applications in causal inference
• Ancestral graph Markov models.
• Graphical Models for Marked Point Processes Based on Local Independence
• Markov Properties for Acyclic Directed Mixed Graphs
• A general dynamical statistical model with causal interpretation
• Dynamic modelling and causality
• Title not available (Why is that?)
• On the Validity of the Markov Interpretation of Path Diagrams of Gaussian Structural Equations Systems with Correlated Errors
• Composable Markov processes
• On Granger causality and the effect of interventions in time series
• A general definition of influence between stochastic processes
• Markov equivalence for ancestral graphs
• Graphical modelling of multivariate time series
• Title not available (Why is that?)
• Stable mixed graphs
• Title not available (Why is that?)
• Markovian acyclic directed mixed graphs for discrete data
• Separoids: a mathematical framework for conditional independence and irrelevance
• Graphical Models for Composable Finite Markov Processes
• A graphical characterization of the largest chain graphs
• Graphical models for event history analysis based on local independence
• On the Markov equivalence of maximal ancestral graphs
• A constraint optimization approach to causal discovery from subsampled time series data
• Unifying Markov properties for graphical models
• Nested Markov properties for acyclic directed mixed graphs
• Counterfactual analyses with graphical models based on local independence
• Graphs for margins of Bayesian networks
• Markov equivalence of marginalized local independence graphs
• Causal interpretation of stochastic differential equations
• Causal inference with multiple time series: principles and problems

Cited In (8)

• Marginals of DAG-Isomorphic Independence Models
• Ancestral graph Markov models.
• Nonparametric conditional local independence testing
• Characterization of causal ancestral graphs for time series with latent confounders
• Foundations of structural causal models with cycles and latent variables
• Markov equivalence of marginalized local independence graphs
• Graphical modeling of stochastic processes driven by correlated noise
• Mixed orthogonality graphs for continuous-time stationary processes

Uses Software

• Separoids

This page was built for publication: Markov equivalence of marginalized local independence graphs

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2176633)