Identifying Independencies in Causal Graphs with Feedback

Abstract

We show that the d -separation criterion constitutes a valid test for conditional independence relationships that are induced by feedback systems involving discrete variables.

Appears in Proceedings of the Twelfth Conference on Uncertainty in Artificial Intelligence (UAI1996)

References in corpus (2)

• On the Testability of Causal Models with Latent and Instrumental Variables
• A Definition and Graphical Representation for Causality

Cited by in corpus (7)

• Bayes-Ball: The Rational Pastime (for Determining Irrelevance and Requisite Information in Belief Networks and Influence Diagrams)
• Discovering Cyclic Causal Models with Latent Variables: A General SAT-Based Procedure
• On Deducing Conditional Independence from d-Separation in Causal Graphs with Feedback (Research Note)
• From Ordinary Differential Equations to Structural Causal Models: the deterministic case
• Modeling Discrete Interventional Data using Directed Cyclic Graphical Models
• Asymmetric separation for local independence graphs
• On the Foundations of Cycles in Bayesian Networks