Related Experiment Videos

Subgroup analyses in randomized trials: risks of subgroup-specific analyses; power and sample size for the

Sara T Brookes1, Elise Whitely, Matthias Egger

  • 1Department of Social Medicine, University of Bristol, Whiteladies Road, Bristol, BS8 2PR, UK. sara.t.brookes@bristol.ac.uk

Summary

Subgroup analyses in clinical trials often yield unreliable results, even when formal interaction tests are used. The power to detect treatment-subgroup interactions is frequently insufficient, potentially leading to misinterpretation of findings.

Related Concept Videos