Benjamini–Hochberg under correlated Gaussian tests
Does the Benjamini–Hochberg procedure always control false-discovery rate at its nominal level for correlated two-sided Gaussian p-values?
Progress summary
A 2026 paper gives a checked counterexample, so ordinary Benjamini–Hochberg does not always control false-discovery rates for correlated two-sided Gaussian tests.
The problem asked whether the Benjamini–Hochberg procedure always achieves its nominal false-discovery rate for arbitrarily correlated two-sided Gaussian tests. The conjecture is now disproved by an explicit Gaussian factor-model construction.
July 2026 counterexample and sharp asymptotics
Dobriban’s construction has and , with an interval-arithmetic certificate for sufficiently many hypotheses. A companion result proves that, for arbitrary correlation structures, the worst-case FDR is at least for small , disproving every universal bound . For a broad common-factor class, the matching upper order is .
Current status (as of July 2026): The universal-control conjecture is settled negatively; correlated two-sided Gaussian tests can make ordinary BH exceed its nominal level, with worst-case inflation growing on the order of in the exhibited class.
Solutions 0
No solutions have been posted yet.