An Empirical Bayes Robust Meta-Analytical-Predictive Prior to Adaptively Leverage External Data

TL;DR

This paper introduces an empirical Bayes robust MAP prior that adaptively leverages external data, balancing model simplicity and flexibility, applicable across various endpoint types, and demonstrated to be robust and powerful through simulations and real clinical data.

Contribution

It presents a novel EB-rMAP prior framework based on Box's prior predictive p-value, enhancing robustness and computational efficiency in meta-analytical contexts.

Findings

Robustness in prior-data conflict scenarios

Preserves statistical power in simulations

Effective application to oncology clinical trials

Abstract

We propose a novel empirical Bayes robust MAP (EB-rMAP) prior to adaptively leverage external/historical data. Built on Box's prior predictive p-value, the EB-rMAP prior framework balances between model parsimony and flexibility through a tuning parameter. The proposed framework can be applied to binary, normal, and time-to-event endpoints. Computational aspects of the framework are efficient. Simulations results with different endpoints demonstrate that the EB-rMAP prior is robust in the presence of prior-data conflict while preserving statistical power. The proposed EB-rMAP prior is then applied to a clinical dataset that comprises of ten oncology clinical trials, including the perspective study.