Workshop of Bayesian Objective Methodology

Tue Feb 23 06:41:16 EST 1999

Apologies for cross-posting

INTERNATIONAL WORKSHOP ON OBJECTIVE BAYESIAN METHODOLOGY
SECOND INFORMATION BULLETIN

1499--1999: Five Centuries of the Universitat de València
Valencia, Spain, June 11th -- June 13th, 1999

The  Universitat of València, Spain, will celebrate
next 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, ie 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. The specific topics in these
areas that are currently being considered for the Workshop are
listed below. Note, however, that it is planned to maintain
considerable flexibility so as to be able to include late-breaking
developments.

1. Objective Priors and Frequentist Statistics
2. Determination of Objective Priors in Important Problems
3. Priors for Objective Bayesian Testing and Model Selection
4. Objective Priors in Nonparametric Analysis
5. The Roles of Objective Bayesian Analysis

Workshop Organization:

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

Workshop Web sites:

http://www.uv.es/~bernardo/workshop.html  (Spain)
http://www.stat.duke.edu/~bernardo/workshop.html  (USA mirror)

Programme Committee:

Professor James O. Berger ({ Duke University, USA})
Professor José M. Bernardo ({ Universitat de València, Spain})
Professor Jayanta K. Ghosh ({ Indian Statistical Institute, India and
Purdue University, USA})
Professor Malay  Ghosh ({ University of Florida, USA})
Professor Christian P. Robert  ({ Université de Rouen, France})

Scientific Programme:

The scientific programme will feature the following invited lectures

Berger, James, Duke University, USA
(Generalized) Reference Priors for Spatial Models
(with B. Sanso, and V. De Oliveira)

Bernardo, José, Universidad de Valencia, Spain
Bayesian Reference Multivariate Hypothesis Testing
(with  Rueda)

Datta, Gauri, University of Georgia, USA
Bayesian Prediction with Approximate Frequentist Validity

Dawid, a. Phil, University College London, UK
The Trouble with Bayes Factors

Fraser, Donald, University of Toronto, Canada
Objective priors and model dependence: the frequentist-Bayesian interface

Ghosh, Jayanta, Indian Statistical Institute, India
Prior Elicitation, Default Priors and Prediction Loss

Ghosh, Malay, University of Florida, USA
Noninformative Priors for Item Response Models

Ghosal, Subhashis, Vrije Universiteit Amsterdam, the Netherlands
Default Priors, Model Selection and Adaptation in Density Estimation

Liseo, Brunero, Università di Roma La Sapienza, Italy,
Semiparametric Inference for Long Memory Time Series: on
Bayesian-Frequentist Interface
(with D. Marinucci  and L. Petrella)

Mukerjee, Rahul, Indian Institute of Management, India
On Confidence Intervals Associated with the Usual and Adjusted  Likelihoods
(with  N. Reid)

Pérez, José M., Universidad Simon Bolivar, Venezuela
Expected Posterior Priors for Default Model Selection

Pericchi, Luis, Universidad Simón Bolívar,  Venezuela
The Intrinsic Bayes Factor as a Constructive Method to Develop Default or
Conventional Priors for Hypothesis Testing and Model Selection.

Robert, Christian, CREST-ENSAE, France
Nonidentifiable Models and Symmetric Priors: How to Teach MCMC Samplers to
Jump Farther
(with M.  Hurn)

Rousseau, Judith, CREST-ENSAE, France
Edgeworth expansion for a Gaussian long-memory process with
application to matching priors

Sun, Dongchu, University of Missouri-Columbia, USA
Random Effects in Generalized Linear Mixed Models

Sweeting, Trevor, University of Surrey, UK
Coverage Probability Bias, Objective Bayes and the Likelihood Principle

Wasserman, Larry, Carnegie Mellon University, USA
Priors for Infinite Dimensional Problems

Each lecture will be followed by invited discussions and by discussion
from the floor.

Invited discussants include:

Barbieri, Marilena, Università di Roma La Sapienza, Italy
Bayarri, Susie, Universitat de València, Spain
Clarke, Bertrand, University of British Columbia, Canada
Clyde,  Merlise, Duke University , USA
de Santis, Fulvio, Università di Roma La Sapienza, Italy
DiCiccio, Thomas, Stanford University, USA
Gelfand, Alan, University of Connecticut, USA
George, Edward, University of Texas, USA
Girón, Javier, Universidad de Málaga, Spain
Gutiérrez-Peña, Eduardo, UNAM, Mexico
Mendoza, Manuel, ITAM, Mexico
Moreno, Elías, Universidad de Granada, Spain
Mortera, Julia, Università di Roma 3, Italy
Petrone, Sonia, Università di Pavia, Italy
Ramamoorthi, R., Michigan State University, USA
Reid, Nancy, University of Toronto, Canada
Rueda, Raúl, UNAM, Mexico
Severini, Thomas, Northwestern University, USA
Sivaganesan, Siva, University of Cincinnati, USA
van der Linde, Angelika, University of Edinburgh, UK
Wells,  Martin, Cornell University, USA
Ye, Keying, Virginia Polytechnic Institute and State University, USA

Contributed papers are encouraged. These will be presented
in two plenary poster sessions, organized in the
tradition of the Valencia meetings.

The abstracts deadline is  April 30th . The abstract should be sent by
e-mail using the abstract format
http://www.uv.es/~bernardo/abstract.html (Spain)
http://www.stat.duke.edu/~bernardo/abstract.html  (USA mirror)
accessible at the workshop web sites.

There will not be  published proceedings, but a booklet of extended
abstracts will be  distributed at the Workshop.

Travel Information:

Delegates will be expected to arrive
on  Thursday June 10th evening,  and to depart on Monday 14th morning.

The opening ceremony will be on the morning of Friday 11th, and the
Conference Dinner  on the evening of Sunday 13th.

Valencia international airport, 7 km. from town, has direct connections to
many european cities, and frequent connexions to both Madrid and Barcelona.

Registration:

To register, please mail or fax the registration form
http://www.uv.es/~bernardo/registration.html (Spain)
http://www.stat.duke.edu/~bernardo/registration.html  (USA mirror)
accessible at the workshop web sites.

Those possibly interested in participating, but not ready to register,
should e-mail
the local organizer, José M. Bernardo  mailto:jose.m.bernardo at uv.es
Periodic electronic Information Bulletins,  will be sent to those who
who have declared their interest.

Additional information:

Further information on the workshop, including pointers to the first draft
of the talks as they become available is posted in the workshop web sites.

http://www.uv.es/~bernardo/workshop.html  (Spain)
http://www.stat.duke.edu/~bernardo/workshop.html  (USA mirror)

For tourist information on the area, please visit
he Web site of the Tourism Agency of the State of Valencia,
http://www.comunitat-valenciana.com

PLEASE NOTE: On April 4th, all Spanish telephone numbers added a "9" after
the country code "34'.
Thus, my more direct  (phone and fax) line is now:  +34.96.364.3560
____________________________________________________________________
Prof. Dr. Jose M. Bernardo, Universidad de Valencia
Dept. Estadistica, Fac. Matematicas, 46100-Burjassot, Valencia, Spain
Tel.  +34.96.364.3560 and  +34.96.386.4313  (direct), +34.96.386.4362 (office).
Fax: +34.96.364.3560 (direct), +34.96.386.4735 (office).
E Mail: jose.m.bernardo at uv.es,
Web Pages: http://www.uv.es/~bernardo/  or http://www.stat.duke.edu/~bernardo/
____________________________________________________________________