|
Activity Number:
|
526
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Wednesday, August 5, 2009 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Biometrics Section
|
| Abstract - #305417 |
|
Title:
|
Improved Variance Smoothing Method for Testing Differential Expression in Affymetrix Oligonucleotide Microarrays
|
|
Author(s):
|
Parul Gulati*+ and David Jarjoura and Soledad Fernandez and Lianbo Yu and Michael Pennell
|
|
Companies:
|
The Ohio State University and The Ohio State University and The Ohio State University and The Ohio State University and The Ohio State University
|
|
Address:
|
Center for Biostatistics, M200 Starling Loving Hall, Columbus, OH, 43210,
|
|
Keywords:
|
Oligonucleotide ; microarrays ; hierarchical ; empirical Bayes ; t-statistic ; hyperparameters
|
|
Abstract:
|
Oligonucleotide microarray experiments with few replications lead to great variability in estimates of variance across genes, and false positive results when variance estimates are too small. Several hierarchical Bayesian methods have been used to combine variance estimates across genes. A recently developed method incorporates the relationship between the gene expression and the variance of gene expression into an empirical Bayes approach that produces a modified t-statistic with better characteristics than methods that do not smooth variances. However this method assumes a single hyper parameter that determines the distribution of variances (the prior degrees of freedom, d_o). We further extend this method by allowing d_o to vary with gene expression. The performance of the extended method is demonstrated in a simulation study. Results are presented for two public data sets.
|
