CPL - Chalmers Publication Library
| Utbildning | Forskning | Styrkeområden | Om Chalmers | In English In English Ej inloggad.

Total Positivity In Markov Structures

S. Fallat ; S. Lauritzen ; K. Sadeghi ; C. Uhler ; Nanny Wermuth (Institutionen för matematiska vetenskaper) ; P. Zwiernik
Annals of Statistics (0090-5364). Vol. 45 (2017), 3, p. 1152-1184.
[Artikel, refereegranskad vetenskaplig]

We discuss properties of distributions that are multivariate totally positive of order two (MTP2) related to conditional independence. In particular, we show that any independence model generated by an MTP2 distribution is a compositional semi-graphoid which is upward-stable and singletontransitive. In addition, we prove that any MTP2 distribution satisfying an appropriate support condition is faithful to its concentration graph. Finally, we analyze factorization properties of MTP2 distributions and discuss ways of constructing MTP2 distributions; in particular, we give conditions on the log-linear parameters of a discrete distribution which ensure MTP2 and characterize conditional Gaussian distributions which satisfy MTP2.

Nyckelord: Association, concentration graph, conditional Gaussian distribution, faithfulness, graphical models, Conditional-Independence, Correlation Inequalities, Binary Variables, Graphical Models, Association, Dependence, Distributions, Matrices



Denna post skapades 2017-08-10.
CPL Pubid: 251020

 

Läs direkt!


Länk till annan sajt (kan kräva inloggning)


Institutioner (Chalmers)

Institutionen för matematiska vetenskaperInstitutionen för matematiska vetenskaper (GU)

Ämnesområden

Matematik

Chalmers infrastruktur