Helmut Finner

Determination of critical values for FDR controlling
step-up-down procedures related to the
asymptotically optimal rejection curve (AORC)

Six Maple worksheets are available for the computation
of critical values for FDR controlling step-up-down procedures
related to the asymptotically optimal rejection curve (AORC)

1.      SU_beta_search.mw
Computes beta-adjusted critical values for a step-up procedure close to AORC

2.       SU_exact_solving.mw
Computation of critical values for step-up procedures such that most FDRs equal alpha

3.      SU_g_functions.mw
Computation of critical values for step-up procedures based on alternative FDR bounding curves

4.      SU_iterative_method.mw
Computation of critical values for step-up procedures based on some heuristic fixpoint arguments

5.      SU_partial_beta_search.mw
Computes beta-adjusted critical values for a step-up procedure close to a modified AORC

6.      SUD_beta_search.mw
Computes beta-adjusted critical values for a step-up-down procedure close to AORC

Optimal beta (beta*) values for n =1, ... , 2000 for step-up and step-down procedures can be found in the Excel-file betas.xlsm

For details see

Finner, H., Gontscharuk, V. & Dickhaus, T. (2012).
False discovery rate control of step-up-down tests with special emphasis on the asymptotically optimal rejections curve.
Scandinavian Journal of Statistics 39, 382-397.