|
Activity Number:
|
379
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Tuesday, August 4, 2009 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Biometrics Section
|
| Abstract - #305601 |
|
Title:
|
Using Distributions for p-Values in the Two-Component Mixture Models to Estimate the Proportion from Null
|
|
Author(s):
|
Chang Yu*+ and Daniel Zelterman
|
|
Companies:
|
Vanderbilt University School of Medicine and Yale University
|
|
Address:
|
S-2323 Medical Center North, Nashville, TN, 37232-2158,
|
|
Keywords:
|
microarray analysis ; Lehmann alternative ; proportion from null ; chi-square test ; Beta Uniform Mixture ; FDR
|
|
Abstract:
|
In microarray analysis, two-component mixture models are used extensively to estimate the proportion from true null. Among the methods summarized by Broberg (2005), only the Beta Uniform Mixture Model makes explicit parametric assumption about the second component $h(p)$, the distribution of p-values under the alternative. Recent work of Zelterman and Yu (2009) derive such distributions for a broad range of test statistics. They show a Beta distribution is derived only in the case that the distribution functions of the test statistic under the null and the alternative differ by a Lehmann alternative through their survival functions, but not in general. The p-values in Pounds and Morris (2003) were generated by a $\chi^2$ test. We derive the distribution for p-values for $\chi^2$ test and use it for the estimation. We demonstrate our methods on real data sets and through simulations.
|
