Abstract:
This thesis discusses the theoretical and practical basis of multiple hypothesis testing. Multiple testing is a statistical procedure widely used in many fields including biology, genetics, medicine and finance. This thesis describes the main approaches to multiple testing designed to control the Family-Wise Error Rate or the False Discovery Rate. A simulation study is carried out to compare and contrast the multiple testing methods on synthetic data inspired by genome-wide studies in oncology. Finally, a case study is used to further highlight benefits and limits of the methodology discussed in the thesis.
