|
Activity Number:
|
178
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Monday, August 4, 2008 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Bayesian Statistical Science
|
| Abstract - #301898 |
|
Title:
|
A Preliminary Study on Combining Classifiers for Selecting Differentially Expressed Genes
|
|
Author(s):
|
Lynn Kuo*+ and Wangang Xie and Yifang Zhao
|
|
Companies:
|
University of Connecticut and University of Connecticut and University of Connecticut
|
|
Address:
|
215 Glenbrook Rd, Storrs, CT, 06269,
|
|
Keywords:
|
SAM ; LIMMA ; MAANOVA ; semiparametric hierarchical Bayesian ; EM ; MCMC
|
|
Abstract:
|
Many statistical tests are being used to select differentially expressed genes for microarray data analysis. It would be useful to evaluate the sensitivity and specificity of each test given the test results. More importantly, it would be desirable to combine these results intelligently to achieve better power. We propose several models with likelihood-based inference that would allow us to achieve both goals in an integrated and comprehensive fashion. Both EM and Bayesian methods are developed for them.
|
