Sample Size Adjustment in Sequential Multiple Assignment Randomized Trials

Clinical trials are often designed based on limited information about effect sizes and precision parameters with risks of underpowered studies. This is more problematic for SMARTs where strategy effects are based on sequences of treatments. Sample size adjustment offers flexibility through re-estimating sample size during the trial to ensure adequate power at the final analysis. While this adaptation is common for standard clinical trials, corresponding methods to perform sample size adjustment have not been adapted to SMARTs. In this paper, we propose a sample size adjustment procedure for SMARTs. Sample sizes are re-calculated at the interim analysis based on the conditional power derived from a bivariate non-central chi-square distribution. We demonstrate through simulation studies that even with an underpowered initial sample size due to miss-specified parameters at the design stage, the proposed method can maintain desirable power at the end of the study, and additional resources are only invested in trials that show promising conditional power at the interim analysis.