A Neutral Comparison of Multivariate Hypothesis Tests for Parallel Group Designs in Rare Disease Settings

Martin Geroldinger, Martin Laimer, Verena Wally, Johann W Bauer, Georg Zimmermann · 2026

Read A Neutral Comparison of Multivariate Hypothesis Tests for Parallel Group Designs in Rare Disease Settings by Martin Geroldinger, Martin Laimer, Verena Wally, Johann W Bauer, Georg Zimmermann (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13593806.txt.

Description

Martin Geroldinger, Martin Laimer, and their co-authors ran a neutral contest between four ways of testing several outcomes at once in rare disease trials. Their 2026 study notes that such trials enroll few patients and break the tidy assumptions behind classic methods. Standard multivariate tests can then cry wolf or miss real effects.

The simulation pit a permutation based package, a semiparametric method with two statistic flavors plus bootstrap variants, the classical parametric test, and a set of single outcome rank tests with a correction. Fake trial data were shaped by real anonymized clinical data and expert guidance. Two clinical settings framed the contest. Rare disease researchers gain a fair map of which test to trust when samples stay small.

Catalog record

CREATORMartin Geroldinger, Martin Laimer, Verena Wally, Johann W Bauer, Georg Zimmermann
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE93 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC13593806

Browse the full library · About the Tower of Babel