|
Activity Number:
|
283
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Tuesday, July 31, 2007 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Biometrics Section
|
| Abstract - #309455 |
|
Title:
|
FDR Control in Identification of Differentially Expressed Genes Using Mixed Linear Models When Some Variance Components May Be Zero
|
|
Author(s):
|
Cumhur Demirkale*+ and Tapabrata Maiti and Dan Nettleton
|
|
Companies:
|
Iowa State University and Iowa State University and Iowa State University
|
|
Address:
|
Department of Statistics, Ames, IA, 50011-0001,
|
|
Keywords:
|
Microarray data analysis ; False Discovery Rate ; Mixed linear models ; Variance components
|
|
Abstract:
|
In a microarray experiment, one experimental design is used to obtain expression measures for all genes. One popular analysis method involves fitting the same mixed linear model for each gene, obtaining gene-specific p-values for tests of interest involving fixed effects, and then choosing a threshold for significance that is intended to control False Discovery Rate (FDR) at a desired level. When some random factors have zero variance components for some genes, the standard practice of fitting the same full mixed linear model for all genes can result in failure to control FDR. We propose a new method which combines results from the fit of full and selected mixed linear models to identify differentially expressed genes and provide FDR control at target levels when the true underlying random effects structure varies across genes.
|
