Review of Post‐Clustering Inference Methods
International Statistical Review · 2026-12 · 94 (3) · 660-700
DOI: 10.1111/insr.70017 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Statistical Review, online erschienen am 30.12.2025. Verfasst von Nicolas Enjalbert Courrech und 2 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 27 Literaturangaben.
Abstract (Originalsprache)
In a classical testing problem, statistical hypotheses are defined before observing the data. However, this principle is violated when hypotheses are based on a clustering of the observations, leading to an inflation of the type I error rate. Recently, post‐clustering inference methods have been proposed to address this particular type of data‐driven hypothesis selection. These methods are divided into two categories: information partitioning and conditional approaches. This article provides a review of these methods and a numerical comparison on simulated Gaussian data. This contribution sheds some light on the pros and cons of each approach in terms of (i) type I error control and power, (ii) potential dependence on a specific clustering method, and (iii) assumptions on data distribution.
Zitieren
APA
Courrech, N. E., Maugis‐Rabusseau, C., & Neuvial, P. (2026). Review of Post‐Clustering Inference Methods. International Statistical Review, 94(3), 660-700. https://doi.org/10.1111/insr.70017
Vancouver
Courrech NE, Maugis‐Rabusseau C, Neuvial P. Review of Post‐Clustering Inference Methods. International Statistical Review. 2026;94(3):660-700. doi:10.1111/insr.70017
BibTeX
@article{Courrech2026,
author = {Courrech, Nicolas Enjalbert and Maugis‐Rabusseau, Cathy and Neuvial, Pierre},
title = {Review of Post‐Clustering Inference Methods},
journal = {International Statistical Review},
year = {2026},
volume = {94},
number = {3},
pages = {660--700},
doi = {10.1111/insr.70017}
}
EUVIMED