English

Latent-free equivalent mDAGs

Statistics Theory 2023-12-06 v3 Statistics Theory

Abstract

We show that the marginal model for a discrete directed acyclic graph (DAG) with hidden variables is distributionally equivalent to another fully observable DAG model if and only if it does not induce any non-trivial inequality constraints.

Cite

@article{arxiv.2209.06534,
  title  = {Latent-free equivalent mDAGs},
  author = {Robin J. Evans},
  journal= {arXiv preprint arXiv:2209.06534},
  year   = {2023}
}

Comments

13 pages, 6 figures

R2 v1 2026-06-28T01:16:24.206Z