SOME STATISTICAL CONSIDERATIONS FOR THE INTERPRETATION OF TRIALS OF COMBINED ANDROGEN THERAPY

Since 1989, there have been strongly conflicting opinions regarding th e validity of the proposition that an antiandrogen added to standard h ormonal therapy could improve the outcome in patients with newly diagn osed metastatic prostate cancer. To some degree, these conflicting opi nions arose from misinterpretations of a number of ''negative'' clinic al trials. The misinterpretations happened because these ''negative'' trials had insufficient statistical power to refute the reported ''pos itive trial'', and information illustrating their statistical power wa s absent from their reports. Thus, readers were not given the necessar y information to distinguish between negative and inconclusive results . In addition, many of the negative reports were early analyses of ong oing clinical trials, a practice that always should be avoided. This a rticle reviews and illustrates the statistical principles that are app licable to the interpretation of low-powered negative clinical trials and discusses the design and conduct of clinical trials.