Power/Sample Size Determination for High Dimensional Data Experiments
View Presentation View Presentation
*Gengqian Cai, GlaxoSmithKline 

Keywords: false discovery rate, mixture model

In high dimensional data analyses, while the false discovery rate (FDR) has been widely used as an appropriate error rate to control, not much progress has been made on the issue of sample size calculation with FDR controlling requirement for the design stage. We investigate powers and the related problem of sample size determination for current FDR controlling procedures under a mixture model involving independent test statistics. A practical sample size/power strategy is proposed for FDR controlling procedures with certain power requirements for high dimensional data experiments.