## Additional file 1.
m the simulation runs were increased to 50000 (m = {100;500}), 20000 (m = 1000), and 10000 (m = 5000), because in these scenarios there is a higher variability of the false discovery
proportion such that the estimator of the FDR converges slower. This also holds if
m is large but π_{0} ≈ 1 or Δ is small. Therefore, for these scenarios the number of simulation runs was increased.
The resulting FDR values were plotted as a function of α_{1} for the FDRS design (left column) or as a function of m_{2} for the FNS design (right column), respectively.
Format: PDF Size: 106KB Download file This file can be viewed with: Adobe Acrobat Reader Zehetmayer and Posch |