Number of the records: 1
On conditional independence and log-convexity
- 1.0386229 - ÚTIA 2013 RIV FR eng J - Journal Article
Matúš, František
On conditional independence and log-convexity.
Annales de L Institut Henri Poincare-Probabilites Et Statistiques. Roč. 48, č. 4 (2012), s. 1137-1147. ISSN 0246-0203
R&D Projects: GA AV ČR IAA100750603; GA ČR GA201/08/0539
Institutional support: RVO:67985556
Keywords : Conditional independence * Markov properties * factorizable distributions * graphical Markov models * log-convexity * Gibbs-Markov equivalence * Markov fields * Gaussian distributions * positive definite matrices * covariance selection model
Subject RIV: BA - General Mathematics
Impact factor: 0.933, year: 2012
http://library.utia.cas.cz/separaty/2013/MTR/matus-0386229.pdf
If conditional independence constraints define a family of positive distributions that is log-convex then this family turns out to be a Markov model over an undirected graph. This is proved for the distributions on products of finite sets and for the regular Gaussian ones. As a consequence, the assertion known as Brook factorization theorem, Hammersley-Clifford theorem or Gibbs-Markov equivalence is obtained.
Permanent Link: http://hdl.handle.net/11104/0216169
Number of the records: 1