The aim of the workshop is to provide a forum to discuss recent statistical modelling strategies to solve complex problems, with a focus on biomedicine, Bayesian methods and high-dimensional inference. Some specifics topics of interest are:
- Prior choice: objective approaches, model separation and the value of informative priors
- High-dimensional model selection, including graphical models and correlated data
- Bayesian non-parametrics
- Bioinformatics and medical applications
Place and time: University of Warwick, Feb 27 2014
URL:
http://www2.warwick.ac.uk/fac/sci/statistics/crism/workshops/bayesianapproches
Registration: free, but registration in advance is required. The capacity is limited, we recommend registering as soon as possible.
PROGRAM
- Guido Consonni (Universitá Cattolica di Milano). Objective Bayesian Search of Gaussian Directed Acyclic Graphical Models for Ordered Variables with Non-Local Priors
- Andrew Gelman (Columbia University). Toward Routine Use of Informative Priors
- Mark Girolami (UCL and Warwick University). Bayesian Model Selection: An Aid to the Cell Biologist?
- Luca Larocca (Universita degli studi de Modena e Reggio Emilia). Cutting-edge issues in objective Bayesian model comparison
- Jun Liu (Harvard University)
- Jianhua Hu (MD Anderson Cancer Center). High dimensional variable selection for correlated data
- Valen Johnson (Texas A&M University). Implications of uniformly most powerful Bayesian tests for the reproducibility of scientific research
- Peter Müller (University of Texas, Austin). A Bayesian Feature Allocation Model for Tumor Heterogeneity
- Donatello Telesca (University of California, Los Angeles). Mixture representations of Non Local priors and graphical model determination and estimation
- Rich Savage (Warwick University). The data deluge and what to do with it
ORGANIZERS
David Rossell (Dept. of Statistics, Univ. of Warwick), Graham Cormode (Dept. of Computer Science, Univ. of Warwick)
--