A Characterization of Interventional Distributions in Semi-Markovian Causal Models

Jin Tian, Changsung Kang, Judea Pearl

Abstract

A Characterization of Interventional Distributions in Semi-Markovian Causal Models Jin Tian, Changsung Kang, Judea Pearl We offer a complete characterization of the set of distributions that could be induced by local interventions on variables governed by a causal Bayesian network of unknown structure, in which some of the variables remain unmeasured. We show that such distributions are constrained by a simply formulated set of inequalities, from which bounds can be derived on causal effects that are not directly measured in randomized experiments. Subjects: 9.1 Causality; 3.4 Probabilistic Reasoning This page is copyrighted by AAAI. All rights reserved. Your use of this site constitutes acceptance of all of AAAI's terms and conditions and privacy policy.
BibTeX
@inproceedings{tian2006characterization,
  author = {Jin Tian and Changsung Kang and Judea Pearl},
  title = {{A Characterization of Interventional Distributions in Semi-Markovian Causal Models}},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year = {2006},
}

Loading related content...

Figure