Accurate testing procedures in cluster randomized trials (CRTs)

ADs are an emerging trend in clinical research. In phase II/III trials with treatment or subgroup selection at the interim the combination test approach used to preserve the type I error may be compromised due to the small sample size used for the learning phase. We study accurate procedures that overcome the problem. Collaboration with Professor C. Llyod, Melbourne University and Dr C. Morgan, Cardinal Systems.

Related unit(s): Statistics