Nonparametric independence testing via mutual information

TL;DR

This paper introduces MINT, a nonparametric independence test for multivariate vectors based on mutual information estimation, utilizing efficient entropy estimators and resampling methods to ensure accurate size and power.

Contribution

The paper presents a novel independence testing method, MINT, leveraging mutual information and recent entropy estimators, with theoretical guarantees and practical extensions.

Findings

MINT achieves nominal size through simulation or resampling.

The test demonstrates good power in local alternatives.

Numerical studies validate effectiveness on simulated and real data.

Abstract

We propose a test of independence of two multivariate random vectors, given a sample from the underlying population. Our approach, which we call MINT, is based on the estimation of mutual information, whose decomposition into joint and marginal entropies facilitates the use of recently-developed efficient entropy estimators derived from nearest neighbour distances. The proposed critical values, which may be obtained from simulation (in the case where one marginal is known) or resampling, guarantee that the test has nominal size, and we provide local power analyses, uniformly over classes of densities whose mutual information satisfies a lower bound. Our ideas may be extended to provide a new goodness-of-fit tests of normal linear models based on assessing the independence of our vector of covariates and an appropriately-defined notion of an error vector. The theory is supported by numerical studies on both simulated and real data.