When Do Generalized Permutation Tests Achieve Optimal Power? A Dispersion Characterization

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Kim, Yongmin, Kim, Ilmun
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914620324708352
author Kim, Yongmin
Kim, Ilmun
author_facet Kim, Yongmin
Kim, Ilmun
contents We study generalized Monte Carlo permutation tests under a non-uniform distribution on permutations. Focusing on the difference-in-means statistic, we introduce two scalar dispersion measures that quantify departures from complete randomization at the individual and pairwise levels. We show that if both dispersions vanish asymptotically, then the conditional permutation distribution converges to its Gaussian benchmark, the critical value stabilizes, and the test attains optimal Pitman local power. Conversely, if these dispersions fail to vanish, the permutation distribution does not self-average, the critical value need not stabilize, and optimal local power cannot in general be guaranteed. We further show that beyond the standard Pitman local model, suitably chosen non-uniform permutation distributions can strictly dominate the uniform distribution by exploiting nuisance structure in the data.
format Preprint
id arxiv_https___arxiv_org_abs_2606_00578
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle When Do Generalized Permutation Tests Achieve Optimal Power? A Dispersion Characterization
Kim, Yongmin
Kim, Ilmun
Methodology
62G10, 62E20, 62F03
We study generalized Monte Carlo permutation tests under a non-uniform distribution on permutations. Focusing on the difference-in-means statistic, we introduce two scalar dispersion measures that quantify departures from complete randomization at the individual and pairwise levels. We show that if both dispersions vanish asymptotically, then the conditional permutation distribution converges to its Gaussian benchmark, the critical value stabilizes, and the test attains optimal Pitman local power. Conversely, if these dispersions fail to vanish, the permutation distribution does not self-average, the critical value need not stabilize, and optimal local power cannot in general be guaranteed. We further show that beyond the standard Pitman local model, suitably chosen non-uniform permutation distributions can strictly dominate the uniform distribution by exploiting nuisance structure in the data.
title When Do Generalized Permutation Tests Achieve Optimal Power? A Dispersion Characterization
topic Methodology
62G10, 62E20, 62F03
url https://arxiv.org/abs/2606.00578