A Highly Powered Large Outcomes Randomised Controlled Trial Will Usually, but Not Always, Have Balanced Groups at Baseline
Authors' conclusion
One out of every 300-400 large, two-arm outcomes trials have imbalances in the baseline hazard of the primary outcome that are large enough to misrepresent the true effect of the intervention.
Study context
- Population
- Participants in the Outcomes Reduction with an Initial Glargine Intervention (ORIGIN) trial's biomarker studyORIGIN biomarker study
- Participants
- 8,215 participants
- Comparison
- Random assignment to one group vs the other
- Outcome
- Randomisations with HR for death < 0.85 or > 1.18 by chance alone
Methodological detailsrepeated re-randomisation of trial participants, adjusted Cox models
- Repeated re-randomisation of trial participants
- Adjusted Cox models
Main finding
As reported in the abstract
Randomisations of 1000 with imbalanced hazard, median (IQR 2, 4)
3
Proportion of randomisations with imbalanced hazard
0.3%
Further findings
Detection and mitigation of imbalance
- Imbalance not apparent from baseline data and not fully mitigated by adjustment for baseline independent predictors of death (4 imbalanced randomisations)
Parts of this Brief are withheld: the automatic checks could not confirm them against the abstract.
Original publication
A Highly Powered Large Outcomes Randomised Controlled Trial Will Usually, but Not Always, Have Balanced Groups at Baseline. Diabetes Obes Metab. Published 3 July 2026. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →