Abstract
We study the statistical efficiency for rising-dose designs in the context of first-in-human studies. Specifically, we identify a class of crossover designs that are appealing in terms of both subject safety and statistical efficiency and, for a three-period, two-panel design in such a class, we compare its A-efficiency relative to the corresponding parallel designs and optimal/efficient crossover designs, respectively, under various plausible models. In the meantime, we also evaluate the impact of inclusion of baseline measurements as a covariate in the statistical analysis, for both crossover and parallel studies.
ACKNOWLEDGMENTS
The authors thank the editor in chief, the associate editor, and the two anonymous referees for their constructive comments and helpful suggestions.