English

Faithfulness in Chain Graphs: The Gaussian Case

Machine Learning 2012-06-27 v1 Artificial Intelligence Statistics Theory Statistics Theory

Abstract

This paper deals with chain graphs under the classic Lauritzen-Wermuth-Frydenberg interpretation. We prove that the regular Gaussian distributions that factorize with respect to a chain graph GG with dd parameters have positive Lebesgue measure with respect to Rd\mathbb{R}^d, whereas those that factorize with respect to GG but are not faithful to it have zero Lebesgue measure with respect to Rd\mathbb{R}^d. This means that, in the measure-theoretic sense described, almost all the regular Gaussian distributions that factorize with respect to GG are faithful to it.

Cite

@article{arxiv.1008.2277,
  title  = {Faithfulness in Chain Graphs: The Gaussian Case},
  author = {Jose M. Peña},
  journal= {arXiv preprint arXiv:1008.2277},
  year   = {2012}
}
R2 v1 2026-06-21T16:00:23.044Z