I would like to correct for multiple testing and I was considering using FDR q-values. In the original paper by Storey, they used this approach for genomewide data, where there are several thousands of variables. However, my dataset is smaller and involves between 30 and 50 variables.
Is there a minimum number of variables recommended for q-values? That is, are q-values reliable when the number of variables is not very large, for instance 30 to 50?
Storey & Tibshirani (2003) Statistical significance for genomewide studies, PNAS, 100 (16) 9440-9445
