1499--1999: Five Centuries of the Universitat de València

INTERNATIONAL WORKSHOP ON OBJECTIVE BAYESIAN METHODOLOGY

Valencia, Spain, June 11th -- June 13th, 1999


The Universitat de València, Spain, celebrates this year its 500 anniversary. Within the Centenary Programme, the University of Valencia is sponsoring an International Workshop on Objective Bayesian Methodology.

Objective Bayesian Methodology

Objective Bayesian methodology is of increasing importance today for at least two reasons. First, application of Bayesian analysis is rapidly growing among nonspecialists, most of whom seek automatic or objective Bayesian procedures. Second, computational advances have allowed Bayesian methodology to be employed in problems of such complexity that determination of serious subjective priors is essentially impossible. The corresponding explosion of research on objective Bayesian methods makes a workshop in this area particularly timely.

Objective Bayesian methodology is, for the most part, oriented towards the development of prior distributions that can be used automatically, i.e. that do not require subjective input. There are three quite distinct statistical domains in which this development has taken place: parametric estimation, parametric testing, and nonparametric analysis. Specific topics in these areas considered within the Workshop programme include:

1. Objective Priors and Frequentist Statistics. Bayesian analysis with objective priors is being increasingly used to obtain `optimal' frequentist procedures (in both small sample size and asymptotic senses) for confidence sets, conditional testing, and decision-theoretic problems. Conversely, frequentist performance is currently the most common tool used to evaluate the quality of objective priors.

2. Determination of Objective Priors in Important Problems. Problems will be discussed in which there have been exciting recent developments involving objective priors, including mixture models, spatial models, hierarchical models, and latent variable models. An important component of many of these results is ensuring that the objective priors will yield proper posteriors.

3. Priors for Objective Bayesian Testing and Model Selection. Included here are such recent promising techniques as `matched' conventional priors, orthogonalized priors, fractional priors, intrinsic priors, reference testing priors, projection priors, encompassing priors, and expected posterior priors.

4. Objective Priors in Nonparametric Analysis. Defining objective priors here is particularly challenging, and ensuring basic properties such as consistency of resulting inferences is difficult.

5. The Roles of Objective Bayesian Analysis. `Objective' could mean `we agree on the answer', or it could mean `we agree to use this as the default answer, in the absence of specific subjective information.' The first definition relates to robust Bayesian analysis, the second to various philosophical issues about `reference points' for comparison.


Workshop organization

Conference Center:

The three day workshop will take place at the Peset Conference Center, a reconverted XVIII century palace in the heart of the medieval old town of the city of Valencia.

  • Conference Center "Rector Peset"
  • Palau dels Marquesos Martinez de Vallejo
  • Pl. Horno de San Nicolás 4, 46001-València, Spain
  • Tel (+34) 96.3166000, Fax (+34) 96.3922729
  • e-mail: crmpeset@uv.es

    For further information and a map, please look at their web page: Peset Center

    Programme Committee:

    Local Organizer:

  • José M. Bernardo (Universitat de València, Spain) jose.m.bernardo@uv.es

    Programme:


    Thursday, June 10

    Friday, June 11

    Saturday, June 12

    Sunday, June 13