A comprehensive error rate for multiple testing
- 67 Downloads
Over the last two decades, a large variety of type I error rates and control procedures have been proposed in the field of multiple hypotheses testing. This paper proposes a framework that includes many existing proposals by investigating procedures in which the ordered p-values are compared to an arbitrary positive and non-decreasing threshold sequence. For this case, we derive the error rate being controlled under different assumptions on the p-values. Our focus will be on step-up procedures. The new formulation gives insight into the relations between existing error rates and opens new perspectives for the whole field of multiple testing.
KeywordsFamily-wise error rate False discovery rate Multiple comparisons Ordered p-values Scaled false discovery rate Type I error control
The main part of this work was done while the first author was a Ph.D student in the Signal Processing Laboratory (LTS5), Ecole Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland (Meskaldji 2013). The authors would like to thank Etienne Roquain, Arnold Janssen and Bradley Efron for interesting comments and suggestions. We also thank the referees for their helpful and constructive comments.
This work was supported by the Swiss National Science Foundation [144467, PP00P2-146318].
- Hommel G, Hoffmann T (1987) Controlled uncertainty. In: Bauer P, Hommel G, Sonnemann E (eds) Multiple hypotheses testing. Springer, Heidelberg, pp 154–161Google Scholar
- Meskaldji D-E (2013) Multiple comparison procedures for large correlated data with application to brain connectivity analysis. Ph.D. thesis, Ecole Polytechnique Fédérale de LausanneGoogle Scholar
- Meskaldji D-E, Thiran J-P, Morgenthaler S (2011) A comprehensive error rate for multiple testing. ArXiv e-prints arXiv:1112.4519
- Meskaldji D-E, Vasung L, Romascano D, Thiran J-P, Hagmann P, Morgenthaler S, Ville DVD (2015) Improved statistical evaluation of group differences in connectomes by screening-filtering strategy with application to study maturation of brain connections between childhood and adolescence. Neuroimage 108:251–264CrossRefGoogle Scholar
- Roquain E (2015) Contributions to multiple testing theory for high-dimensional data. Université Pierre et Marie Curie, ParisGoogle Scholar