BayesianHybridDesign: Bayesian Hybrid Design and Analysis

Read full text
Authors: Philip He, Zhaohua Lu
Cited by: 0

Abstract

Implements Bayesian hybrid designs that incorporate historical control data into a current clinical trial. The package uses a dynamic power prior method to determine the degree of borrowing from the historical data, creating a 'hybrid' control arm. This approach is primarily designed for studies with a binary primary endpoint, such as the overall response rate (ORR). Functions are provided for design calibration, sample size calculation, power evaluation, and final analysis. Additionally, it includes functions adapted from the 'SAMprior' package (v1.1.1) by Yang et al. (2023) to support the Self-Adapting Mixture (SAM) prior framework for comparison.

Fields of Study & Subjects

Statistical Methods in Clinical Trials Statistical Methods and Bayesian Inference Optimal Experimental Design Methods

Publication details

Publication date
6 February 2026
Document type
Dataset