Know the questions a skeptical FDA reviewer will probe — before you're in the room.
Last week I published what I submitted to the FDA on their January 2026 Bayesian guidance. Comment 3 argued that when you compose Bayesian trial components (priors, borrowing, sequential monitoring), the system's operating characteristics can diverge from what component-level analysis predicts. This post shows you the math. The
The Bayesian trial design conversation tends to start after patients are assigned to arms. Priors, borrowing, monitoring, posterior inference. All of it assumes the randomization is settled. Stratified permuted block, 1:1 allocation, done. But how you randomize affects power, balance, ethical allocation, and regulatory credibility. Most biostatisticians treat it
My public comments on Docket No. FDA-2025-D-3217, "Use of Bayesian Methodology in Clinical Trials of Drug and Biological Products."
