Statistics Notes: Concealing treatment allocation in randomised trials

Top Cited Papers
Publisher Website
Google Scholar
Abstract
We have previously explained why random allocation of treatments is a required design feature of controlled trials1 and explained how to generate a random allocation sequence.2 Here we consider the importance of concealing the treatment allocation until the patient is entered into the trial. Regardless of how the allocation sequence has been generated — such as by simple or stratified randomisation2 — there will be a prespecified sequence of treatment allocations. In principle, therefore, it is possible to know what treatment the next patient will get at the time when a decision is taken to consider the patient for entry into the trial. The strength of the randomised trial is based on aspects of design which eliminate various types of bias. Randomisation of patients to treatment groups eliminates bias by making the characteristics of the patients in two (or more) groups the same on average, and stratification with blocking may help to reduce chance imbalance in a particular trial.2 All this good work can be undone if a poor procedure is adopted to …