Hans-Helge Müller and Helmut Schäfer (University of Marburg, Germany)
Monitoring clinical trials:a general statistical principle for design changes
A general method is presented that allows to change statistical design elements such as the residual sample size during the course of an experiment or to include an interim analysis for early stopping when no formal rule for early stopping was foreseen, to increase or reduce the number of planned interim analyses, and to make other changes, without affecting the type I error risk. The method may be applied at the time of a pre-planned interim analysis or for administrative interim looks. The method is described in the general context of statistical decision functions and is based on the conditional rejection probability of a decision variable. The method is illustrated in an non-inferiority trial comparing extra-corporal shock wave therapy to standard surgical procedure in patients with tendinosis calcarea.