Nonlinear Covariance Shrinkage for Hotelling's $T^2$ in High Dimension

📅 2025-02-04
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
This paper addresses the reduced statistical power of Hotelling’s $T^2$ test in high-dimensional, low-sample-size settings ($p/n o gamma > 0$), where inaccurate covariance matrix estimation severely impairs performance. We propose a nonlinear covariance shrinkage estimator that does not require assumptions on spiked structure or bounded condition number. Leveraging variational inference and a novel local random matrix theory, our method constructs an adaptive, eigenvector-preserving shrinkage estimator capable of accommodating arbitrary spectral shapes and broad rank regimes. Unlike conventional linear shrinkage and existing nonlinear approaches, our estimator is theoretically grounded and provably enhances detection power for mean vector testing. Extensive simulations and real-data analyses—from finance to genomics—demonstrate its robustness and superior performance over state-of-the-art alternatives.

Technology Category

Application Category

📝 Abstract
In this paper we study the problem of comparing the means of a single observation and a reference sample in the presence of a common data covariance matrix, where the data dimension $p$ grows linearly with the number of samples $n$ and $p/n$ converges to a number between 0 and 1. The approach we take is to replace the sample covariance matrix with a nonlinear shrinkage estimator -- i.e., a matrix with the same eigenvectors -- in Hotelling's $T^2$ test. Current approaches of this sort typically assume that the data covariance matrix has a condition number or spiked rank that increases slowly with dimension. However, this assumption is ill-suited to data sets containing many strongly correlated background covariates, as often found in finance, genetics, and remote sensing. To address this problem we construct, using variational methods and new local random-matrix laws, a nonlinear covariance shrinkage method tailored to optimize detection performance across a broad range of spiked ranks and condition numbers. We then demonstrate, via both simulated and real-world data, that our method outperforms existing approaches.
Problem

Research questions and friction points this paper is trying to address.

Develops covariance shrinkage for high-dimensional Hotelling's T²
Maximizes power asymptotically under Gaussian data
Improves power by 50% over competitors
Innovation

Methods, ideas, or system contributions that make the work stand out.

Covariance shrinkage for high-dimensional data
Optimal shrinker via variational problem solving
Power gain over competitors in empirical studies
💼 Related Jobs
No related jobs found.
B
Benjamin D. Robinson
US Air Force Office of Scientific Research
V
Van Latimer
Radial Research and Development, Inc.