%0 Journal Article
%T Power and Stability Properties of Resampling-Based Multiple Testing Procedures with Applications to Gene Oncology Studies
%A Dongmei Li
%A Timothy D. Dye
%J Computational and Mathematical Methods in Medicine
%D 2013
%I Hindawi Publishing Corporation
%R 10.1155/2013/610297
%X Resampling-based multiple testing procedures are widely used in genomic studies to identify differentially expressed genes and to conduct genome-wide association studies. However, the power and stability properties of these popular resampling-based multiple testing procedures have not been extensively evaluated. Our study focuses on investigating the power and stability of seven resampling-based multiple testing procedures frequently used in high-throughput data analysis for small sample size data through simulations and gene oncology examples. The bootstrap single-step min procedure and the bootstrap step-down min procedure perform the best among all tested procedures, when sample size is as small as 3 in each group and either familywise error rate or false discovery rate control is desired. When sample size increases to 12 and false discovery rate control is desired, the permutation max procedure and the permutation min procedure perform best. Our results provide guidance for high-throughput data analysis when sample size is small. 1. Introduction With rapidly developing biotechnology, microarrays and next generation sequencing have been widely used in biomedical and biological fields for identifying differentially expressed genes, detecting transcription factor binding sites, and mapping complex traits using single nucleotide polymorphisms (SNPs) [1¨C7]. The multiple testing error rates associated with thousands, even millions of hypotheses testing, need to be taken into account. Common multiple testing error rates controlled in multiple hypotheses testing are the familywise error rate (FWER), which is the probability of at least one false rejection [8, 9] and the false discovery rate (FDR), which is the expected proportion of falsely rejected null hypotheses [10]. Resampling-based multiple testing procedures are widely used in high-throughput data analysis (e.g., microarray and next generation sequencing), especially when the sample size is small or the distribution of test statistic is nonnormally distributed or is unknown. Resampling-based multiple testing procedures can account for dependent structures among £¿£¿values or test statistics, resulting in lower type II errors. The commonly used resampling techniques include permutation tests and bootstrap methods. Permutation tests are nonparametric statistical significance tests, where the test statistics¡¯ distribution under the null hypothesis is constructed by calculating all possible values or a concrete number of test statistics (usually 1000 or above) from permuted observations under the null
%U http://www.hindawi.com/journals/cmmm/2013/610297/