Journal of Computer Science & Systems Biology

Sample Size Calculation for Microarray Studies with Survival Endpoints

Abstract

Sin-Ho Jung

Oftentimes, we want to discover the genes whose expression levels are associated with a time-to-event endpoint, such as progression free survival or overall survival, through microarray studies. In this case, we need to adjust the false positivity in such discovery procedure for multiplicity of the genes using a multiple testing method. The most popular multiple testing methods used for gene discovery in microarray studies are to control the false discovery rate or the family wise error rate. In this paper, we review a FDR-control method to discover the genes associated with a time-to-event outcome and propose a sample size calculation method for microarray studies designed to discover genes whose expression levels are associated the chosen time-to-event outcome. These methods can be easily modified for other types of high throughput genome projects.