The approach of controlling the error rate in an exploratory analysis where number of hypotheses are tested, but where the strict control which is provided by multiple comparison procedures controlling the family wise error rate is not needed.

Assume that the m hypotheses are to be tested, of which m0 relate to cases where the null hypothesis is true and the remaining m-m0 relate to the cases where alternative hypo- thesis is true. The FDR is defined as expected proportion of the incorrectly rejected null hypotheses. Explicitly FDR is given by the formula written below


 

where V represents several true null hypotheses which are rejected and R is the total number of the rejected hypotheses. Procedures which exercise control over the FDR guarantee that the FDR < α, for some fixed value of α.