All Times EDT
Keywords: Sample size re-estimation, optimal design, adaptive design, Bayesian design
Clinical trials with adaptive sample size reassessment based on an unblinded analysis of interim results are perhaps the most popular class of adaptive designs and are typically designed by prespecifying a zone for the interim test statistic, termed the promising zone, along with a decision rule for increasing the sample size within that zone. In this talk I will present the Constrained Promising Zone (CPZ) design, a new promising zone design that is easy to implement, and easy for all stakeholders to understand and accept. It is based on the intuitively plausible notion that any additional investment of sample size at an interim analysis should be contingent on a minimal acceptable return on the investment, expressed in terms of guaranteed conditional power. The CPZ design can potentially achieve the optimality properties of the Jennison and Turnbull (2015) design, which are considered gold-standard for optimality. Bayesian extensions of the design will also be discussed.