3.2 Blinded SSR Methods

A blinded SSR does not require knowledge of the treatment assignment at the individual patient level. It is designed to modify sample size due to inaccurate assumptions of the variability associated with a continuous endpoint or an assumed background event rate in the control arm for trials with a binary endpoint. Even though the treatment assignment information is very helpful in assessing such parameters, methods have been developed to allow their estimation without using the actual treatment assignment information.
Because blinded SSR does not involve treatment unblinding and can be conducted without worrying about introducing bias into a trial, blinded SSR is classified as a “well-understood” adaptive feature in the ...

Get Modern Approaches to Clinical Trials Using SAS: Classical, Adaptive, and Bayesian Methods now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.