Abstract:  In this talk I will address methods for Bayesian variable selection
for high-dimensional data. I will start from the simple linear regression model 
and then extend methods to probit models for classification and to clustering 
settings. I will also consider models for survival data. I will show examples 
from genomics, in particular DNA microarray studies. The analysis of the high-
dimensional data generated by such studies often challenges standard statistical 
methods. I will also assess performances on simulated data. Models and algorithms 
are quite flexible and allow us to incorporate additional information, such as data 
substructure and/or knowledge on gene functions.