EUVIMEDAtrasti EUVIMED
Open access · CC BY 4.0

Analysis of Covariance in General Factorial Designs Through Multiple Contrast Tests Under Variance Heteroscedasticity

Matthias Becher iD, Ludwig A Hothorn, Frank Konietschke iD

Statistics in Medicine · 2025

DOI: 10.1002/sim.70018 ↗

At a glance

Journal article in Statistics in Medicine, 2025. Written by Matthias Becher and 2 co-authors. Institution: Institut für Biometrie und klinische Epidemiologie, Charité-Universitätsmedizin Berlin, Berlin, Germany. Major MEDLINE topics: Clinical Trials as Topic. Cited 6 times so far (Crossref); 25 references. The full text is freely available (open access, CC BY 4.0). Funded by: Deutsche Forschungsgemeinschaft.

SantraukaSubjectsBibliografiniai duomenysCiteRelated studies

Abstract (original language)

A common goal in clinical trials is to conduct tests on estimated treatment effects adjusted for covariates such as age or sex. Analysis of Covariance (ANCOVA) is often used in these scenarios to test the global null hypothesis of no treatment effect using an ‐test. However, in several samples, the ‐test does not provide any information about individual null hypotheses and has strict assumptions such as variance homoscedasticity. We extend the method proposed by Konietschke et al. [“Analysis of Covariance Under Variance Heteroscedasticity in General Factorial Designs,” Statistics in Medicine 40 (2021): 4732–4749] to a multiple contrast test procedure (MCTP), which allows us to test arbitrary linear hypotheses and provides information about the global‐ as well as the individual null hypotheses. Further, we can calculate compatible simultaneous confidence intervals for the individual effects. We derive a small sample size approximation of the distribution of the test statistic via a multivariate t‐distribution. As an alternative, we introduce a Wild‐bootstrap method. Extensive simulations show that our methods are applicable even when sample sizes are small. Their application is further illustrated within a real data example.

Subjects

MeSH terms (MEDLINE)

Clinical Trials as TopicHumansComputer SimulationAnalysis of VarianceSample SizeModels, StatisticalConfidence IntervalsResearch DesignData Interpretation, Statistical

Author keywords

ANCOVABox‐type approximationMCTPbootstrapexperimental designs

Authors and institutions

  • Institut für Biometrie und klinische Epidemiologie, Charité-Universitätsmedizin Berlin, Berlin, Germany.
  • Leibniz University Hannover, Hannover, Germany.

ORCID profiles: Matthias Becher, Frank Konietschke

Funding

  • Deutsche Forschungsgemeinschaft

Cite

APA

Becher, M., Hothorn, L. A., & Konietschke, F. (2025). Analysis of Covariance in General Factorial Designs Through Multiple Contrast Tests Under Variance Heteroscedasticity. Statistics in Medicine. https://doi.org/10.1002/sim.70018

Vancouver

Becher M, Hothorn LA, Konietschke F. Analysis of Covariance in General Factorial Designs Through Multiple Contrast Tests Under Variance Heteroscedasticity. Statistics in Medicine. 2025. doi:10.1002/sim.70018

BibTeX
@article{Becher2025,
  author = {Becher, Matthias and Hothorn, Ludwig A and Konietschke, Frank},
  title = {Analysis of Covariance in General Factorial Designs Through Multiple Contrast Tests Under Variance Heteroscedasticity},
  journal = {Statistics in Medicine},
  year = {2025},
  doi = {10.1002/sim.70018}
}
Start for free →