2936 articles  [version française]
HAL: hal-00450010, version 1

Detailed view  Export this paper
On matrix variate Dirichlet vectors
Konstencia Bobecka 1, Richard Emilion 2, Jacek Wesolowski 1
For the MAPMO; POLYTECHNIKA Varsovie collaboration(s)
(2009-12-01)

A matrix variate Dirichlet vector is a random vector of independent Wishart matrices 'divided' by their sum. Many properties of Dirichlet vectors are usually established through integral computations assuming existence of density for the Wishart's. We propose a method to deal with the general case where densities need not exist. On the other hand, in dimension larger than 2, Dirichlet processes reduce to Dirichlet vectors and posterior of Dirichlet need not be Dirichlet.
1:  Polytechnika (PW)
Polytechnika Warsawska
2:  Mathématiques - Analyse, Probabilités, Modélisation - Orléans (MAPMO)
Université d'Orléans – CNRS : UMR7349
Mathematics/Statistics

Statistics/Statistics Theory
Bayesian statistics – Dirichlet vectors – Positive definite matrix – Random matrices – Wishart distribution
Attached file list to this document: 
PDF
MatDir00.pdf(205 KB)