The utility of partial cross-over designs in early phase randomized prevention trials

In this note, we outline the benefits of a partial cross-over design for a class of experiments where the interest is the cumulative effect of dose versus placebo. The goal of our design strategy is to answer several complex question efficiently in a phase II setting with a minimal number of assumptions with an eye towards planning a phase III study. (C) 2004 Elsevier Inc. All rights reserved.