DART2: a robust multiple testing method to smartly leverage helpful or misleading ancillary information

TL;DR

DART2 is a robust multiple testing method that effectively leverages ancillary information to improve power when helpful, while maintaining control over false discovery rate even when the information is misleading.

Contribution

DART2 introduces a distance-assisted procedure that is both powerful and robust, outperforming existing methods across various scenarios and applications.

Findings

DART2 controls FDR asymptotically when ancillary info is helpful.

DART2 maintains FDR control and high power even when ancillary info is misleading.

Numerical studies show DART2's superior performance over existing methods.

Abstract

In many applications of multiple testing, ancillary information is available, reflecting the hypothesis null or alternative status. Several methods have been developed to leverage this ancillary information to enhance testing power, typically requiring the ancillary information is helpful enough to ensure favorable performance. In this paper, we develop a robust and effective distance-assisted multiple testing procedure named DART2, designed to be powerful and robust regardless of the quality of ancillary information. When the ancillary information is helpful, DART2 can asymptotically control FDR while improving power; otherwise, DART2 can still control FDR and maintain power at least as high as ignoring the ancillary information. We demonstrated DART2's superior performance compared to existing methods through numerical studies under various settings. In addition, DART2 has been applied to a gene association study where we have shown its superior accuracy and robustness under two different types of ancillary information.