A new conditional performance score for the evaluation of adaptive group sequential designs with sample size recalculation

Abstract

In standard clinical trial designs, the required sample size is fixed in the planning stage based on initial parameter assumptions. It is intuitive that the correct choice of the sample size is of major importance for an ethical justification of the trial. The required parameter assumptions should be based on previously published results from the literature. In clinical practice, however, historical data often do not exist or show highly variable results. Adaptive group sequential designs allow a sample size recalculation after a planned unblinded interim analysis in order to adjust the sample size during the ongoing trial. So far, there exist no unique standards to assess the performance of sample size recalculation rules. Single performance criteria commonly reported are given by the power and the average sample size; the variability of the recalculated sample size and the conditional power distribution are usually ignored. Therefore, the need for an adequate performance score combining these relevant performance criteria is evident. To judge the performance of an adaptive design, there exist two possible perspectives, which might also be combined: Either the global performance of the design can be addressed, which averages over all possible interim results, or the conditional performance is addressed, which focuses on the remaining performance conditional on a specific interim result. In this work, we give a compact overview of sample size recalculation rules and performance measures. Moreover, we propose a new conditional performance score and apply it to various standard recalculation rules by means of Monte-Carlo simulations.

Smoothing Corrections for Improving Sample Size Recalculation Rules in Adaptive Group Sequential Study Designs

“… Δ, true standardized treatment effect. a Conditional performance score with an equal weighting of the components and target values as suggested in Herrmann et al 6 …”

“…These variability reductions are only one aspect of the performance for adaptive sample size recalculation, whereas a correct target sample size and power define the other perspective. The performance score by Herrmann et al 6 assessing both—variability and location of power and sample size—shows an overall benefit of smoothing corrections for medium and large effect sizes. Generally, there is no globally optimal approach across all effect sizes.…”

“…We evaluated the scenarios with respect to average conditional power and sample size, their variances, and the conditional performance score. 6 Simulations were performed with the software R. 10…”

Optimal planning of adaptive two‐stage designs

“…When an optimal design is to be defined, the choice of the objective criterion is of high importance and not straightforward 42 . Barber and Jennison 15 proposed to minimize a weighted sum of expected sample size under the null and under the alternative hypothesis.…”

Untitled

“…A good performance is therefore given if the average conditional power meets its target, the average sample size is neither too high nor too low, and the corresponding variances are reasonably small. Recently, Herrmann et al 6 proposed a conditional performance score CPS averaging these indicators (location of conditional power and sample size, variation of conditional power and sample size) within a single performance measure. The location components are constructed as follows…”