DAGGER: A sequential algorithm for FDR control on DAGs
arXiv:1709.10250
Abstract
We propose a linear-time, single-pass, top-down algorithm for multiple testing on directed acyclic graphs (DAGs), where nodes represent hypotheses and edges specify a partial ordering in which hypotheses must be tested. The procedure is guaranteed to reject a sub-DAG with bounded false discovery rate (FDR) while satisfying the logical constraint that a rejected node's parents must also be rejected. It is designed for sequential testing settings, when the DAG structure is known a priori, but the -values are obtained selectively (such as in a sequence of experiments), but the algorithm is also applicable in non-sequential settings when all -values can be calculated in advance (such as variable/model selection). Our DAGGER algorithm, shorthand for Greedily Evolving Rejections on DAGs, provably controls the false discovery rate under independence, positive dependence or arbitrary dependence of the -values. The DAGGER procedure specializes to known algorithms in the special cases of trees and line graphs, and simplifies to the classical Benjamini-Hochberg procedure when the DAG has no edges. We explore the empirical performance of DAGGER using simulations, as well as a real dataset corresponding to a gene ontology, showing favorable performance in terms of time and power.
arXiv comment29 pages, 10 figures, accepted for publication by Biometrika
References in corpus (6)
- STAR: A general interactive framework for FDR control under structural constraints
- Combining p-values via averaging
- Online control of the false discovery rate with decaying memory
- Testing hypotheses on a tree: new error rates and controlling strategies
- On Procedures Controlling the FDR for Testing Hierarchically Ordered Hypotheses
- The Control of the False Discovery Rate in Fixed Sequence Multiple Testing