Kahan and Morris (1) reviewed 258 trials published during 2010 in the British Medical Journal, Journal of the American Medical Association, Lancet, and New England Journal of Medicine with the aim to assess how often stratified randomisation is used, whether the method of randomisation was adequately reported and whether the analysis adjusted for the balancing variables.
The review showed that balanced randomisation was common, with 163 (63%) trials using at least one balancing variable. Block randomisation was used in 85 trials, minimisation in 27, and unclear in 95 reports. Only 67 trials adjusted for all balancing factors in their analysis.
The authors conclude that stratified randomisation is common, but the implications of the balancing is poorly understood. It is important to adjust the primary analysis for balancing factors to obtain correct p-values and confidence intervals and avoid unnecessary lossof power.
Kahan BC, Morris TP. Reporting and analysis of trials using stratified randomisation in leading medical journals: review and reanalysis. BMJ 2012;345:e5840