Statistical power in single subject trials.

Abstract

A controlled single subject trial compares the efficacy of a new treatment with a control treatment in an individual patient. The treatments are administered in a double-blind, randomized, multi-crossover sequence of periods. During the trial response measures are obtained from each treatment period and form the basis for the statistical evaluation. Similar to the situation in clinical trials using groups of patients the statistical power is dependent on sample size, variability of responses, magnitude of the differential treatment effect and the level of statistical significance. In addition, the randomization procedure is of importance and power estimations show that a pairwise random allocation of treatment periods is more powerful than an unrestricted randomization. Since a single subject trial is a time consuming approach, the total number of treatment periods, the sample size, is restricted in order to make such trials feasible. Accordingly, less rigorous statistical requirements and power must be accepted. The consequence is an increased risk of both Type I and II errors. However, in comparison with the trial and error approach frequently applied in clinical practice, the controlled single subject trial may improve the certainty of therapeutic decisions in the individual patient.