AAPL: assessing association between p‐value lists. (15th February 2013)

• Record Type: Journal Article
• Authors: Yu, Tianwei; Zhao, Yize; Shen, Shihao
• Is Part Of: Statistical analysis and data mining. Volume 6:Number 2(2013)
• Page Start: 144
• Page End: 155
• Publication Date: 2013-02-15
• Subjects: agreement -- false discovery rate; Data mining -- Statistical methods -- Periodicals; 006.312
• DOI: 10.1002/sam.11180
• Languages: English
• ISSNs: 1932-1864

Abstract

Abstract: Joint analyses of high‐throughput datasets generate the need to assess the association between two long lists of p ‐values. In such p ‐value lists, the vast majority of the features are insignificant. Ideally contributions of features that are null in both tests should be minimized. However, by random chance their p ‐values are uniformly distributed between 0 and 1, and weak correlations of the p ‐values may exist due to inherent biases in the high‐throughput technology used to generate the multiple datasets. Rank‐based agreement test may capture such unwanted effects. Testing contingency tables generated using hard cutoffs may be sensitive to arbitrary threshold choice. We develop a novel method on the basis of feature‐level concordance using local false discovery rate. The association score enjoys straight‐forward interpretation. The method shows higher statistical power to detect the association between p ‐value lists in simulation. We demonstrate its utility using real data analysis. The R implementation of the method is available at http://userwww.service.emory.edu/∼tyu8/AAPL/. © 2013 Wiley Periodicals, Inc. Statistical Analysis and Data Mining 6: 144–155, 2013