Some Biostatistical Considerations About Real-World Data and Evidence in Clinical Studies, Especially for Regulatory Purposes

Abstract

A working group of the American Statistical Association (ASA) Biopharmaceutical Section has published three comprehensive articles in this journal that survey the practices and identify opportunities for using real-world data (RWD) and evidence in clinical design and analysis to inform regulatory decision making. This article extends the discussion of bias for RWD and explores the possibilities of patient registries and medical records of excellent quality. Leadership by the FDA for real-world evidence (RWE) is highlighted, with examples of label expansion and new product development. Propensity scores and Bayesian methods for RWD are discussed in the context of regulatory environment.

Keywords:

• Bayesian methods
• Bias in observational studies
• Clinical trial design
• Propensity scores
• Real-world evidence

Funding

The author(s) reported there is no funding associated with the work featured in this article.