Leave-one-out testing for node-level differences in Gaussian graphical models
Methodology
2026-01-23 v1
Abstract
We study two-sample equality testing in Gaussian graphical models. Classical likelihood ratio tests on decomposable graphs admit clique-wise factorizations, offering limited localization and unstable finite-sample behaviour. We propose node-level inference via a leave-one-out Bartlett-adjusted test on a fully connected graph. The resulting increments have standard chi-square null limits, enabling calibrated significance for single nodes and fixed-size subsets. Simulations confirm validity, and a case study shows practical utility.
Keywords
Cite
@article{arxiv.2601.15896,
title = {Leave-one-out testing for node-level differences in Gaussian graphical models},
author = {Davide Benussi and Ester Alongi and Erika Banzato},
journal= {arXiv preprint arXiv:2601.15896},
year = {2026}
}