The use of unequal randomisation in clinical trials — An update

ObjectiveTo update a 2005 review of the reasons researchers have given for the use of unequal randomisation in randomised controlled trials (RCTs).Main measuresIntervention being tested; type of study; number of participants; randomisation ratio; sample size calculation and reason given for using unequal randomisation.MethodsReview of trials using unequal randomisation.Databases and sourcesCochrane library, Medline and CINAHL.ResultsA total of 86 trials were identified. Of these 82 trials (95%) recruited patients in favour of the experimental group. Various reasons for the use of unequal randomisation were given including: gaining treatment experience; identification of adverse events; ethical; logistic and enhancing recruitment. No trial reported explicitly used it for cost-effectiveness. Most of the papers (i.e. 47, 55%) did not state why they had used unequal randomisation and only 38 trials (44%) appeared to have taken the unequal randomisation into account in their sample size calculation.ConclusionMost studies did not mention the rationale for unequal allocation, and a significant proportion did not appear to account for it in the sample size calculations. Unlike the previous review economic considerations were not stated as a rationale for its use. A number of trials used it to enhance recruitment, although this has not been tested.