|
Activity Number:
|
286
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Tuesday, August 8, 2006 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Biometrics Section
|
| Abstract - #306641 |
|
Title:
|
Minimax Estimation of Means in Large-Scale Experiments
|
|
Author(s):
|
Tiejun Tong*+ and Liang Chen and Hongyu Zhao
|
|
Companies:
|
Yale University and Yale University and Yale University
|
|
Address:
|
170 Park Street, Apt. 3, New Haven, CT, 06511,
|
|
Keywords:
|
minimax estimator ; multiple test ; false discovery rate ; shrinkage
|
|
Abstract:
|
The development of microarray technologies has revolutionized bio-medical research, and microarrays have become a standard tool in biological studies. Due to the cost and/or experimental difficulties, it is common that thousands of genes are measured only with a small number of replicates. In particular, the gene-specific estimators of means and variances are not reliable and the corresponding tests have low power. Some approaches to improving variance estimation have emerged. However, the impact of the gene-specific means to tests has not caused much attention. In this paper we propose some shrinkage estimators for means. We prove that our proposed estimators are minimax under Stein loss function. We further investigate the performance of the proposed estimators on improving the tests. A real data study is also used for illustration.
|
- 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 2006 program |
