Improving the Effectiveness of Sample Size Re-Estimation: An Operating Characteristic Focused, Hybrid Frequentist-Bayesian Approach

Abstract

Sample size re-estimation (SSR) is perhaps the most used adaptive procedure in both frequentist and Bayesian adaptive designs for clinical trials. The primary focus of all current frequentist and Bayesian SSR procedures is type I error control. We propose a hybrid frequentist-Bayesian SSR approach that focuses on optimizing operating characteristics (OC), which uses simulations to investigate the associated OC and adjusts accordingly. The hybrid approach incorporates the Bayesian predictive power into the frequentist framework of SSR. Simulations show that the hybrid approach can substantially outperform popular frequentist type error-focused SSR procedure. The hybrid approach can substantially improve the effectiveness of SSR using Bayesian predictive power.

Keywords: Bayesian; conditional power; hybrid adaptive design; modified predictive power; predictive power; sample size re‐estimation.

FIGURE 1

Comparison of $\widehat{\mathit{CP}}$, PP, MPP, and CI_MPP curves.

FIGURE 2

Comparing $\widehat{\mathit{CP}}$, PP, and ${\mathit{CP}}_{\theta }$ at the planned sample size.

FIGURE 3

Comparing $\widehat{\mathit{CP}}$, PP, and ${\mathit{CP}}_{\theta }$ at $N_{\mathit{max}.}$

FIGURE 4

New sample size comparison.