A note on control of the false discovery proportion

Marcin Dudziński¹ ; Konrad Furmańczyk²

¹Faculty of Applied Informatics and Mathematics Department of Applied Mathematics Warsaw University of Life Sciences (SGGW) Nowoursynowska 159 02-776 Warszawa, Poland
²Faculty of Applied Informatics and Mathematics Department of Applied Mathematics Warsaw University of Life Sciences (SGGW) Nowursynowska 159 02-776 Warszawa, Poland

Applicationes Mathematicae, Tome 36 (2009) no. 4, pp. 397-418

Résumé

We consider the problem of simultaneous testing of a finite number of null hypotheses $H_{i}$, $i=1,\ldots,s$. Starting from the classical paper of Lehmann (1957), it has become a very popular subject of research. In many applications, particularly in molecular biology (see e.g. Dudoit et al. (2003), Pollard et al. (2005)), the number $s$, i.e. the number of tested hypotheses, is large and the popular procedures that control the familywise error rate (FWERM) have small power. Therefore, we are concerned with another error rate measure, called the false discovery proportion (FDP). We prove some theorems about control of the FDP measure. Our results differ from those obtained by Lehmann and Romano (2005).

Détail

DOI : 10.4064/am36-4-2

Keywords: consider problem simultaneous testing finite number null hypotheses ldots starting classical paper lehmann has become popular subject research many applications particularly molecular biology see dudoit pollard number number tested hypotheses large popular procedures control familywise error rate fwerm have small power therefore concerned another error rate measure called false discovery proportion fdp prove theorems about control fdp measure results differ those obtained lehmann romano