On wishart and noncentral wishart distributions on symmetric cones

Research output: Contribution to journalArticlepeer-review

Abstract

Necessary conditions for the existence of noncentral Wishart distributions are given. Our method relies on positivity properties of spherical polynomials on Euclidean Jordan algebras and advances an approach by Peddada and Richards [Ann. Probab. 19 (1991), pp. 868–874] where only a special case (positive semidefinite matrices, rank 1 noncentrality parameter) is treated. Not only do the shape parameters need to be in the Wallach set—as is the case for Riesz measures—but also the rank of the noncentrality parameter is constrained by the size of the shape parameter. This rank condition has recently been proved with different methods for the special case of symmetric, positive semidefinite matrices (Letac and Massam; Graczyk, Malecki, and Mayerhofer).

Original languageEnglish
Pages (from-to)7093-7109
Number of pages17
JournalTransactions of the American Mathematical Society
Volume371
Issue number10
DOIs
Publication statusPublished - 2019

Keywords

  • Generalized binomial coefficients
  • Jack polynomials
  • Symmetric cones
  • Wishart distribution

Fingerprint

Dive into the research topics of 'On wishart and noncentral wishart distributions on symmetric cones'. Together they form a unique fingerprint.

Cite this