In this paper we study the effects of infinitesimal perturbations to a fixed sampling distribution function, known up to a finite-dimensional parameter, on the Bayes factor comparing the given parametric model against a nonparametric alternative. We consider the Bayes factor as a non ratio-linear functional defined on a set of sampling distributions functions and maximize its first von Mises derivative over this set. In particular mixture and density bounded sets are considered.

Local robustness and Bayes factors for nonparametric alternatives

CAROTA, Cinzia
1996-01-01

Abstract

In this paper we study the effects of infinitesimal perturbations to a fixed sampling distribution function, known up to a finite-dimensional parameter, on the Bayes factor comparing the given parametric model against a nonparametric alternative. We consider the Bayes factor as a non ratio-linear functional defined on a set of sampling distributions functions and maximize its first von Mises derivative over this set. In particular mixture and density bounded sets are considered.
1996
Workshop on Bayesian Robustness
Rimini
May 22-25
Lecture Notes Monograph Series - Bayesian Robustness
Institute of Mathematical Statistics
29
283
291
9780940600416
http://imstat.org/cup/default.htm
von Mises derivatives; robustness to sampling distribution; Bayes factors
Cinzia Carota
File in questo prodotto:
Non ci sono file associati a questo prodotto.

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/2318/114518
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact