seminario

[Pietro Muliere <pietro.muliere@uni-bocconi.it>]

Istituto Metodi Quantitativi - Università L. Bocconi
  Viale Isonzo, 25 - 20135 Milano
   Tel. 02-58365629  - Fax 02-58365630



                                                 SEMINARIO







    Statistical Decision Problems and Bayesian Nonparametric Methods



                                                Eduardo Gutierrez- Pena

                                 IIMAS-UNAM, Mexico, and University of Bath, UK




                                  giovedì, 20 novembre 2003 – ore 16.30
                                              Aula IMQ – stanza 137
______________________________________________________________
Abstract . The Bayesian approach to statistical inference finds a solid 
justification in decision theory, where considerable emphasis is
placed on coherent inferences and rational behaviour. Given a parametric 
model, the Bayesian solution to most inferential problems is
coherent. We argue, however, that parametric model selection is basically 
incoherent. We go on to suggest that one simple way to
eliminate this problem is by adopting a decision theoretical approach 
within a Bayesian nonparametric framework.

This is a joint work with Stephen G. Walker (University of Bath, UK)