EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Rank-adaptive covariance testing with applications to genomics and neuroimaging

David Veitch, Yinqiu He iD, Jun Young Park iD

Biometrics · 06.01.2026 · 82 (1)

DOI: 10.1093/biomtc/ujag052 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Biometrics, online erschienen am 28.03.2026. Verfasst von David Veitch und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Statistical Sciences, University of Toronto, Toronto, ON M5S 1A1, Canada. Hauptthemen laut MEDLINE: Genomics, Neuroimaging, Models, Statistical. Die Arbeit nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: University of Toronto, National Science Foundation, Natural Sciences and Engineering Research Council of Canada.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In biomedical studies, testing for differences in covariance may offer scientific insights, especially when differences are driven by complex joint behavior between features. However, when differences in joint behavior are weakly dispersed across many dimensions and arise from differences in low-rank structures within the data, as is often the case in genomics and neuroimaging, existing two-sample covariance testing methods may suffer from power loss. The Ky-Fan(k) norm, defined by the sum of the top k singular values, is a simple and intuitive matrix norm able to capture signals caused by differences in low-rank structures between matrices, but its statistical properties in hypothesis testing have not been studied well. In this paper, we investigate the behavior of the Ky-Fan(k) norm in two-sample covariance testing. Ultimately, we propose a novel methodology, rank-adaptive covariance testing (RACT), which is able to leverage differences in low-rank structures found in the covariance matrices of two groups in order to maximize power. RACT uses permutation for statistical inference, ensuring an exact Type I error control. We validate RACT in simulation studies and evaluate its performance when testing for differences in gene expression networks between two types of lung cancer, as well as testing for covariance heterogeneity in diffusion tensor imaging data taken on two different scanner types.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

GenomicsNeuroimagingModels, StatisticalHumansComputer SimulationData Interpretation, Statistical

Stichwörter der Autor:innen

Ky-Fan(k) normadaptive testinggenomicsneuroimagingpermutationtwo-sample covariance testing

Autor:innen und Institutionen

  • Department of Statistical Sciences, University of Toronto, Toronto, ON M5S 1A1, Canada.
  • Department of Statistics, University of Wisconsin - Madison, Madison, WI 53706, United States.
  • Department of Psychology, University of Toronto, Toronto, ON M5S 1A1, Canada.

ORCID-Profile: Yinqiu He, Jun Young Park

Förderung

  • University of Toronto
  • National Science Foundation
  • Natural Sciences and Engineering Research Council of Canada

Zitieren

APA

Veitch, D., He, Y., & Park, J. Y. (2026). Rank-adaptive covariance testing with applications to genomics and neuroimaging. Biometrics, 82(1). https://doi.org/10.1093/biomtc/ujag052

Vancouver

Veitch D, He Y, Park JY. Rank-adaptive covariance testing with applications to genomics and neuroimaging. Biometrics. 2026;82(1). doi:10.1093/biomtc/ujag052

BibTeX
@article{Veitch2026,
  author = {Veitch, David and He, Yinqiu and Park, Jun Young},
  title = {Rank-adaptive covariance testing with applications to genomics and neuroimaging},
  journal = {Biometrics},
  year = {2026},
  volume = {82},
  number = {1},
  doi = {10.1093/biomtc/ujag052}
}
Kostenlos starten →