[Statistical aspects in planning psychotropic drug trials (author's transl)].

It has become virtually unthinkable to objectively judge trials of comparisons without statistical inference. For studies involving psychopharmaceuticals the requirements have especially grown, since variations of efficacy are difficult to differentiate and objectivate. The basic principles of statistical planning must be applied to studies with psychopharmaceuticals. On the basis of these general principles the relevant points of the clinical and statistical models and their relationship to one another are discussed. Special aspects of the study objectives, the clinical model, the medical trial plan, the statistical model and design, the execution of the trials, statistical evaluation and its interpretation are presented. The setting up of hypotheses, balancing and maintenance of factors of disturbances, sample sizes, randomizing techniques and the confrontation of clinical relevance with statistical significance are some of the important points discussed.