Crossover versus parallel designs: Dose-escalation design comparisons for first-in-human studies

摘要

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.