A minimum Wasserstein distance approach to Fisher's combination of independent discrete p-values

TL;DR

This paper proposes a novel method using Wasserstein distance to improve Fisher's combination test for discrete p-values, leading to better error control and increased power.

Contribution

It introduces a Wasserstein distance-based adjustment framework and proposes an optimal gamma distribution as a null approximation for Fisher's combination, improving over traditional methods.

Findings

Enhanced type I error control in discrete p-value combination

Increased statistical power of the test

Theoretical justification for the proposed adjustments

Abstract

This paper introduces a comprehensive framework to adjust a discrete test statistic for improving its hypothesis testing procedure. The adjustment minimizes the Wasserstein distance to a null-approximating continuous distribution, tackling some fundamental challenges inherent in combining statistical significances derived from discrete distributions. The related theory justifies Lancaster's mid-p and mean-value chi-squared statistics for Fisher's combination as special cases. However, in order to counter the conservative nature of Lancaster's testing procedures, we propose an updated null-approximating distribution. It is achieved by further minimizing the Wasserstein distance to the adjusted statistics within a proper distribution family. Specifically, in the context of Fisher's combination, we propose an optimal gamma distribution as a substitute for the traditionally used chi-squared distribution. This new approach yields an asymptotically consistent test that significantly improves type I error control and enhances statistical power.