Detection of Outlying Correlation Coefficients in Multicenter Clinical Trials
Pharmaceutical Statistics · 2025
DOI: 10.1002/pst.70013 ↗Kurz gefasst
Fachartikel in der Zeitschrift Pharmaceutical Statistics, 2025. Verfasst von Lieven Desmet und 4 weiteren Autor:innen. Beteiligte Einrichtung: Institut de Statistique, Biostatistique et Sciences Actuarielles, Université Catholique de Louvain, Louvain-la-Neuve, Belgium. Hauptthemen laut MEDLINE: Multicenter Studies as Topic, Clinical Trials as Topic. Die Arbeit nennt 22 Literaturangaben.
Abstract (Originalsprache)
Central statistical monitoring aims at finding centers whose data distribution differs significantly from the other centers in multicentric clinical trials. Such differences may point to data quality issues due to negligence, misconduct, or fraud. Data distributions can be compared across centers in many different ways, depending on the type of data (e.g., numerical or categorical), whether a univariate or a multivariate comparison is performed, and so on. In that framework, we present two methods aimed at detecting centers with outlying bivariate Pearson correlation coefficients. One of the methods directly compares the correlations across centers. The other method conditions the test on one of the marginal standard deviations, which makes the test on correlation independent of the centers' standard deviations. Both methods are shown to perform equally well on simulated data. They are also applied on real world data, where they identify centers with outlying correlations. The findings of the two tests are compared, showing that they concord for centers with average standard deviations, but differ for centers with extreme standard deviations. While the focus here is on central statistical monitoring, the methods are general and can be used in other settings.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Institut de Statistique, Biostatistique et Sciences Actuarielles, Université Catholique de Louvain, Louvain-la-Neuve, Belgium.
- Institut Jules Bordet, Université Libre de Bruxelles, Brussels, Belgium.
- CluePoints, Louvain-la-Neuve, Belgium.
- International Drug Development Institute (IDDI), Louvain-la-Neuve, Belgium.
- Data Science Institute, Hasselt University, Hasselt, Belgium.
- Department of Biostatistics and Medical Informatics, Medical University of Bialystok, Bialystok, Poland.
ORCID-Profile: Lieven Desmet, Tomasz Burzykowski
Zitieren
APA
Desmet, L., Venet, D., Trotta, L., Burzykowski, T., & Buyse, M. (2025). Detection of Outlying Correlation Coefficients in Multicenter Clinical Trials. Pharmaceutical Statistics. https://doi.org/10.1002/pst.70013
Vancouver
Desmet L, Venet D, Trotta L, Burzykowski T, Buyse M. Detection of Outlying Correlation Coefficients in Multicenter Clinical Trials. Pharmaceutical Statistics. 2025. doi:10.1002/pst.70013
BibTeX
@article{Desmet2025,
author = {Desmet, Lieven and Venet, David and Trotta, Laura and Burzykowski, Tomasz and Buyse, Marc},
title = {Detection of Outlying Correlation Coefficients in Multicenter Clinical Trials},
journal = {Pharmaceutical Statistics},
year = {2025},
doi = {10.1002/pst.70013}
}
EUVIMED