The study of properties of mean functionals of random probability measures is an important area of research in the theory of Bayesian nonparametric statistics. Many results are known by now for random Dirichlet means but little is known, especially in terms of posterior distributions, for classes of priors beyond the Dirichlet process. In this paper we consider normalized random measures with independent increments (NRMI) and mixtures of NRMI: for both cases we are able to provide exact expressions for the posterior distribution of their means. These general results are then specialized leading to distributional results for means of two important particular cases of NRMI and also of the two parameter Poisson-Dirichlet process.

On the posterior distribution of classes of random means

PRUENSTER, Igor
2010-01-01

Abstract

The study of properties of mean functionals of random probability measures is an important area of research in the theory of Bayesian nonparametric statistics. Many results are known by now for random Dirichlet means but little is known, especially in terms of posterior distributions, for classes of priors beyond the Dirichlet process. In this paper we consider normalized random measures with independent increments (NRMI) and mixtures of NRMI: for both cases we are able to provide exact expressions for the posterior distribution of their means. These general results are then specialized leading to distributional results for means of two important particular cases of NRMI and also of the two parameter Poisson-Dirichlet process.
2010
16
155
180
http://isi.cbs.nl/bernoulli/
Bayesian Nonparametrics; Completely random measures; Means of random probability measures; Normalized random measures; Poisson-Dirichlet process; Posterior distribution; Species sampling models.
L.F. JAMES; A. LIJOI; I. PRUENSTER
File in questo prodotto:
File Dimensione Formato  
bernoulli2010_published.pdf

Accesso aperto

Tipo di file: PDF EDITORIALE
Dimensione 282.46 kB
Formato Adobe PDF
282.46 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2318/57297
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 7
  • ???jsp.display-item.citation.isi??? 8
social impact