Statistics Seminar
Statistical
Laboratory
Iowa State University
DATE AND TIME:
Monday, April 3, 2006, 4:10 p.m.
PLACE: 319
Snedecor
SPEAKER: Jian Huang, Department of Statistics
and Actuarial Science, Program in Public Health Genetics School of Public
Health,
University of Iowa, Iowa City
TITLE: Regularized
Estimation with High Dimensional
Data
ABSTRACT
The need for fitting regression models with
high-dimensional covariates arises from microarray gene expression profiling
studies of cancer. One of the main purposes of such studies is to find genes
that have predictive values of patient's survival and other important clinical
outcomes. We propose using the gradient directed regularization method for
variable selection and estimation in classification and censored survival
models. We use a simulation based method for evaluating model significance in
terms of prediction, and a resampling approach for assessing variable
importance. We demonstrate the proposed method on data sets from two microarray
gene expression profiling studies of lymphoma cancers in which patient's
survival information is available. We also discuss some theoretical aspects of
regularized methods in fitting regression models with high-dimensional data.
COFFEE: 3:45 p.m., 104 Snedecor
Hall
Seminar schedules and abstracts are available via WWW:
http://www.stat.iastate.edu/
Jeanette La Grange
Department of Statistics
102
Snedecor
Iowa State University
Ames, IA 50010-1210
515 294-3440
(office)
515 294-4040 (fax)
http://www.stat.iastate.edu/directory/staff/jeanette.html