In clinical trials, appropriate designs are often chosen to address scienti
fic/medical questions of particular interest to the investigator. For a cho
sen statistical design, however, standard statistical procedures may not be
applicable owing to the nature of the design. In this paper we examine sta
tistical methods for analysis of data collected from a placebo-challenging
design which is often considered for assessment of the efficacy of drug pro
ducts for indication of erectile dysfunction. An example concerning a clini
cal trial conducted with 120 male patients with erectile dysfunction is use
d to illustrate the derived statistical methods, Some recommendations to th
e randomization procedure for the study design of this kind are also made.
Copyright (C) 2000 John Wiley & Sons, Ltd.