End-point interpretation in clinical trials: the case for discipline

Abstract

The recent submission of a new drug application to the federal Food and Drug Administration (FDA) has led to vigorous discussion concerning the rules of clinical trial conduct. The regulatory importance of prospectively defined end points, long held as a fundamental tenet of well-designed research efforts, and the proper role of alpha-spending functions in clinical trials are current foci of attention. Sound public policy requires that the highest research standards govern statistical analyses to support a new drug application. These research standards should be rooted in the fundamentals of epidemiology and biostatistics, long accepted by clinical trial workers. Also, because the physician-scientists whose research results are disseminated to the community bear considerable responsibility for both that community's protection and the protection of the individual patient, these investigators must provide unambiguous interpretations of type I and type II error rates. This obligation includes clear prospective statements of analysis plans and complete reporting of findings for the prospectively defined endpoints in presentations and in manuscripts. The public health is best served if regulatory agencies continue to join clinical trial workers in repudiating the philosophy of "sound methodology or a small p-value" in judging research efforts. Reviewers of new drug applications might best take the tack "judge first what the investigators set out to do, then judge what else was discovered in an 'exploratory light.'"