• xmlui.mirage2.page-structure.header.title
    • français
    • English
  • Help
  • Login
  • Language 
    • Français
    • English
View Item 
  •   BIRD Home
  • CEREMADE (UMR CNRS 7534)
  • CEREMADE : Publications
  • View Item
  •   BIRD Home
  • CEREMADE (UMR CNRS 7534)
  • CEREMADE : Publications
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

Browse

BIRDResearch centres & CollectionsBy Issue DateAuthorsTitlesTypeThis CollectionBy Issue DateAuthorsTitlesType

My Account

LoginRegister

Statistics

Most Popular ItemsStatistics by CountryMost Popular Authors
Thumbnail - No thumbnail

Jeffreys’ Priors for Mixture Estimation

Grazian, Clara; Robert, Christian P. (2015), Jeffreys’ Priors for Mixture Estimation, in Sylvia Frühwirth-Schnatter, Angela Bitto, Gregor Kastner, Alexandra Posekany, Bayesian Statistics from Methods to Models and Applications / BAYSM 2014, Springer : Berlin Heidelberg, p. 37-48. 10.1007/978-3-319-16238-6_4

Type
Communication / Conférence
External document link
https://arxiv.org/abs/1511.03145v2
Date
2015
Book title
Bayesian Statistics from Methods to Models and Applications / BAYSM 2014
Book author
Sylvia Frühwirth-Schnatter, Angela Bitto, Gregor Kastner, Alexandra Posekany
Publisher
Springer
Published in
Berlin Heidelberg
ISBN
978-3-319-16237-9
Pages
37-48
Publication identifier
10.1007/978-3-319-16238-6_4
Metadata
Show full item record
Author(s)
Grazian, Clara

Robert, Christian P.
Abstract (EN)
Mixture models may be a useful and flexible tool to describe data with a complicated structure, for instance characterized by multimodality or asymmetry. The literature about Bayesian analysis of mixture models is huge, nevertheless an “objective” Bayesian approach for these models is not widespread, because it is a well-established fact that one needs to be careful in using improper prior distributions, since the posterior distribution may not be proper, yet noninformative priors are often improper. In this work, a preliminary analysis based on the use of a dependent Jeffreys’ prior in the setting of mixture models will be presented. The Jeffreys’ prior which assumes the parameters of a Gaussian mixture model is shown to be improper and the conditional Jeffreys’ prior for each group of parameters is studied. The Jeffreys’ prior for the complete set of parameters is then used to approximate the derived posterior distribution via a Metropolis–Hastings algorithm and the behavior of the simulated chains is investigated to reach evidence in favor of the properness of the posterior distribution.
Subjects / Keywords
Improper priors; Mixture of distributions; Monte Carlo methods; Noninformative priors

Related items

Showing items related by title and author.

  • Thumbnail
    Jeffreys priors for mixture estimation: properties and alternatives 
    Grazian, Clara; Robert, Christian P. (2018) Article accepté pour publication ou publié
  • Thumbnail
    Jeffreys Priors for Mixture Models 
    Robert, Christian P.; Grazian, Clara (2014) Communication / Conférence
  • Thumbnail
    Comment on Article by Dawid and Musio 
    Robert, Christian P.; Grazian, Clara; Masiani, Illaria (2015) Article accepté pour publication ou publié
  • Thumbnail
    Accelerating Metropolis-Hastings algorithms: Delayed acceptance with prefetching 
    Banterle, Marco; Grazian, Clara; Robert, Christian P. (2014) Document de travail / Working paper
  • Thumbnail
    Mixtures. Estimation and Applications 
    Titterington, Mike; Robert, Christian P.; Mengersen, Kerrie (2011) Ouvrage
Dauphine PSL Bibliothèque logo
Place du Maréchal de Lattre de Tassigny 75775 Paris Cedex 16
Phone: 01 44 05 40 94
Contact
Dauphine PSL logoEQUIS logoCreative Commons logo