|
Activity Number:
|
102
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Monday, July 30, 2007 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Biometrics Section
|
| Abstract - #310045 |
|
Title:
|
Improved Significance of Microarrays
|
|
Author(s):
|
Shunpu Zhang*+
|
|
Companies:
|
University of Nebraska-Lincoln
|
|
Address:
|
Department of Statistics, Lincoln, NE, 68583-0963,
|
|
Keywords:
|
microarray ; null statistics ; test statistics ; false discovery rate ; false positive ; fudge factor
|
|
Abstract:
|
The Significance Analysis of Microarrays (SAM) is a popular method for detecting significantly expressed genes and controlling the false discovery rate (FDR). However, it has been recently reported in the literature that SAM tends to over-estimate the FDR. In this paper, we propose an improved significance analysis of microarrays (ISAM) method. The improvement is achieved by employing the more efficient test and null statistics of Zhang (2006) and a novel way of choosing the fudge factor. Through extensive simulations, we show that our proposed method consistently outperforms SAM in the sense that it tends to contain smaller number of true false positive (FP) given that the same number of significant genes is identified by SAM and our proposed method. We also demonstrate that our proposed method provides reasonably unbiased estimates of the FDR.
|
- The address information is for the authors that have a + after their name.
- Authors who are presenting talks have a * after their name.
Back to the full JSM 2007 program |
