This is the program for the 2010 Joint Statistical Meetings in Vancouver, British Columbia.

Abstract Details

Activity Number: 157
Type: Topic Contributed
Date/Time: Monday, August 2, 2010 : 10:30 AM to 12:20 PM
Sponsor: Biometrics Section
Abstract - #306708
Title: A Weighted Average Likelihood Ratio Test with Application to RNAseq Data
Author(s): Peng Liu*+ and Yaqing Si
Companies: Iowa State University and Iowa State University
Address: 2117 Snedecor Hall, Ames, IA, 50011,
Keywords: RNAseq ; False Discovery Rate (FDR) ; WALR test ; MAP test ; next-generation sequencing ; optimal test
Abstract:

Next-generation sequencing technology has been exploited to measure the gene expression (mRNA) level and this method is called RNA-seq. The resulting RNA-seq data set is an ultra-high-dimensional discrete data set. Poisson model has been employed to fit RNA-seq data, and several tests including negative binomial and Chi-square test have been proposed to identify differentially expressed (DE) genes followed by a procedure to control false discovery rate (FDR) such as the q-value method. Here we first evaluate the current methods in terms of FDR control and power. Then we construct a new test, the weighted average likelihood ratio (WALR) test, and show that it is the most powerful test among the tests with the same level of FDR control. In addition, we can easily modify the null hypothesis and apply WALR test to detect DE genes with fold-changes above specified level.


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 2010 program




2010 JSM Online Program Home

For information, contact jsm@amstat.org or phone (888) 231-3473.

If you have questions about the Continuing Education program, please contact the Education Department.