2004 SSC Annual Meeting

2004 Annual Meeting of the SSC in Montréal

Statistical Learning and Data Mining

May 30, 2004
Montréal, Quebec


Leader: Rob Tibshirani, Stanford University, Hugh Chipman, University of Waterloo

This biostatistics workshop gives an overview of statistical models for data mining, inference and prediction. With the rapid developments in internet technology, genomics and other high tech industries, we rely increasingly on data analysis and statistical models to exploit the vast amounts of data at our fingertips. The course provides an in-depth treatment of some of the main tools in supervised learning, including PRIM, boosting and support vector machines. It also covers many new areas of unsupervised learning and data mining including clustering, principal components, principal curves and self-organizing maps. Several biostatistical applications will be discussed, including DNA expression arrays. Much of the workshop material will be based on Tibshirani's book Elements of Statistical Learning: Inference and Prediction (with Trevor Hastie and Jerome Friedman, SpringerVerlag, 2001).

About the leader.
Rob Tibshirani is currently a Professor in the Department of Health Research and Policy and Department of Statistics at Stanford University. Previously, he held an academic position at the University of Toronto for 13 years. Tibshirani is a Fellow of the Royal Society of Canada and has received several prestigious awards including the CRM-SSC Prize, the COPSS award, an NSERC Steacie Fellowship, and a Guggenheim Foundation Fellowship. A Fellow of the American Statistical Association and the Institute of Mathematical Statistics, Tibshirani is a co-author of two other ground-breaking books: General Additive Models (with Trevor Hastie) and An Introduction to the Bootstrap (with Brad Efron). He has published more than 150 refereed articles covering a wide range of statistical areas, including nonparametric regression, classification and bootstrap technology. With more than fifteen years of experience in consulting on biostatistical problems, Tibshirani has been an active presenter of workshops, counting at least a dozen in the past ten years.

Hugh Chipman is currently an Associate Professor at the Departments of Statistics and Computer Science, University of Waterloo. Previously he held an appointment at the University of Chicago. His awards include the SSC Pierre Robillard Award, and starting July 1 he will hold a Tier II Canada Research Chair at Acadia University. He has made important theoretical contributions on the use of statistical models for extracting information from large and complex datasets, a field in which he also has extensive consulting experience working with large companies. His current Biostatistical interests focus on Drug Discovery and Microarray Data. He has previously conducted workshops in Data Mining.