Estimating the false discovery rate using the stochastic approximation algorithm

摘要

Testing of multiple hypotheses involves statistics that are strongly dependent in some applications,udbut most work on this subject is based on the assumption of independence. We proposeuda new method for estimating the false discovery rate of multiple hypothesis tests, in which theuddensity of test scores is estimated parametrically by minimizing the Kullback–Leibler distanceudbetween the unknown density and its estimator using the stochastic approximation algorithm,udand the false discovery rate is estimated using the ensemble averaging method. Our method isudapplicable under general dependence between test statistics. Numerical comparisons between ourudmethod and several competitors, conducted on simulated and real data examples, show that ourudmethod achieves more accurate control of the false discovery rate in almost all scenarios.