Working group home page | Adrian Raftery | Statistics Department | University of Washington

Working Group on Model-based Clustering and Bayesian Model Selection
Summer session: July 9-13, 2001

Monday-Friday (five days) from 9:00am to noon, in room C-301, Padelford Hall, University of Washington Campus.

Our summer session will focus on model-based clustering and applications (in particular to gene expression data), Bayesian model selection and averaging, and on MCMC and importance sampling methodology. There will be eight "long" talks (sessions of about 80 minutes, hopefully divided about equally between presentation and discussion), and six short talks (15 minutes each, plus some discussion). There will be several visitors, and there has been quite a bit of progress to report, so it should be exciting. Watch this space for details as they become known.

Working Group: Monday-Friday, July 9-13, 2001
Day (Chair) Time Speaker Topic
Monday (Adrian Raftery) 9:00-10:20am Matthew Stephens, UW Statistics MCMC for models with varying dimensions -- an alternative to reversible jump?
10:40am-Noon Joshua Goodman, Microsoft Research Predictive clustering: smaller, faster language modeling
Tuesday (Peter Hoff) 9:00-10:20am Brendan Murphy, Trinity College Dublin Model-based clustering for ranking data
10:40-11:00am Sam Bates, UW Statistics Inference for deterministic simulation models
11:05-11:25am Jo Hardin, Fred Hutchinson Cancer Research Center Outlier Detection: an Application to Microarray Data.
11:30-11:50am Naisyin Wang, Texas A+M tba
Wednesday (Russell Steele) 9:00-10:20am Debashis Ghosh, Dept of Biostatistics, U of Michigan Mixture Modelling for the analysis of gene expression data from microarray experiments.
10:40am-Noon Ka Yee Yeung, UW Computer Science Model-based clustering for gene expression microarray data
Thursday (Matthew Stephens) 9:00-10:20am Jeremy Tantrum, UW Statistics Model-based document clustering
10:40-10:55am Monnie Mcgee, Hunter College, City University of New York Mixture Transition Monte Carlo: A generalization of MCMC
11:00-11:15am Eric Anderson, QERM Model-based clustering, and hybridization in fish populations
11:20-11:35am Russ Steele, UW Statistics Multiple Imputation methods
11:40-11.55 noon Mary Emond, UW Biostatistics tba
Friday (Chris Fraley) 9:00-10:20am Chris Fraley, UW Statistics and Insightful Inc Recent developments in model-based clustering and the MCLUST software
10:40-Noon Florence Forbes, INRIA Mean Field like approximations for choosing the number of components in Hidden Markov Models