A simulation-based comparison of estimation methods for adaptive and classical group sequential clinical trials

Statistical methods for controlling the type-I error of hypothesis tests in adaptive group sequential clinical trials are well established and well understood. However, methods for obtaining statistically valid point estimates and confidence intervals for adaptive designs are not as well established or as well understood. At the end of an adaptive trial, one may calculate the repeated confidence interval (RCI), which provides conservative coverage of $$ , or the backward image confidence interval (BWCI), which provides exact coverage of $$ and is an extension of the stagewise adjusted confidence interval (SWCI, used in classical group sequential designs). The BWCI can also provide a median unbiased estimate (MUE) of $$ . There is a need to better understand the coverage and possible biases associated with these methods. We conducted a simulation study exploring parameter estimation following sample size reestimation based on testing methods with strong control of type-I error. Generally, the BWCI provided exact coverage, the naïve CI provided inconsistent coverage, and the RCI provided conservative coverage. Additionally, we note considerable asymmetry in the coverage from above/from below for the RCI, although we did not see any instance where the 95% RCI excluded the true parameter more than 2.5% on either side. At the end of an adaptive group sequential trial, we strongly recommend the use of the BWCI (and associated MUE), with the RCI computed during interim looks; the naïve CI should be avoided. These results and conclusions also hold true for classical group sequential designs.