|
Activity Number:
|
404
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Wednesday, August 6, 2008 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Biopharmaceutical Section
|
| Abstract - #302556 |
|
Title:
|
Sample Size for Identifying Differentially Expressed Genes in Microarray Experiment
|
|
Author(s):
|
Zhaoyu Luo*+ and Javier Cabrera+ and Xiang Yu and Peggy Wong
|
|
Companies:
|
Rutgers, The State University of New Jersey and Rutgers, The State University of New Jersey and Merck Reserach Laboratories and Merck Research Laboratories
|
|
Address:
|
149 Nichols Apts., Piscataway, NJ, 08854, Department of Statistics, Puscataway, NJ, 08854,
|
|
Keywords:
|
Microarray ; sample size ; clustering ; differential expression ; power ; covanrance correction
|
|
Abstract:
|
Sample size calculation in the identification of differentially expressed genes is an important problem of microarray experiment. In this paper, we induce clustering and correlation correction to gene expression identification. On one hand, after a cluster analysis, genes performing similar functions or participating in the same genetic pathway would congregate in the same cluster. On the other hand, various researchers have suggested that accounting for correlation among genes could improve the power. There exists, however, three challenges: the first one is which clustering method we choose, the second one is how to reliably estimate the covariance matrix of genes and the last one is how to model the data, perform the appropriate statistical test and calculate the power. Here we present our methodology to tackle the problems.
|
- 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 2008 program |
