Some clinical trials aim to demonstrate therapeutic equivalence on multiple
primary endpoints. For example, therapeutic equivalence studies of agents
for the treatment of osteoarthritis use several primary endpoints including
investigator's global assessment of disease activity, patient's global ass
essment of response to therapy, and pain. In this paper, thoughts on simult
aneous equivalence assessment on three endpoints are presented. As pointed
out by Berger and Hsu (1996), the conventional intersection-union test can
be conservative. Simulation and computation are conducted to provide an ins
ight on the conservativeness. We also provide a method to lower the confide
nce level and at the same time maintain the type I error when endpoints hav
e normal distributions and are independent. If, in a particular analysis, t
he goal is to demonstrate equivalence on as many endpoints as possible, a s
tep-up procedure can be used for selecting those endpoints for which equiva
lence may be demonstrated. This step-up procedure at the same time controls
experimentwise error rate. The techniques are illustrated by a data exampl
e. Copyright (C) 2001 John Wiley & Sons, Ltd.