General Framework for Equivalence Testing over a Range of Linear Outcomes with CMC Applications. (3rd April 2019)

• Record Type: Journal Article
• Authors: Zeng, Lingmin; Novick, Steven; Yu, Binbing; Yang, Harry
• Is Part Of: Statistics in biopharmaceutical research. Volume 11:Number 2(2019)
• Page Start: 182
• Page End: 190
• Publication Date: 2019-04-03
• Subjects: Assay transfer -- Bayesian -- Comparability -- Frequentist analysis -- Linearity; Pharmacy -- Statistical methods -- Periodicals; Pharmaceutical biotechnology -- Statistical methods -- Periodicals; Biopharmaceutics -- Periodicals; Biometry -- Periodicals; Pharmacy -- Statistical methods; Periodicals; 615.190727
• DOI: 10.1080/19466315.2018.1470029
• Languages: English
• ISSNs: 1946-6315

Abstract

ABSTRACT: As per regulatory guidance, it is mandatory to demonstrate comparability before and after a change is made to an analytical method for commercial lot release or manufacturing process in the area of Chemistry, Manufacturing, and Controls. The change may include transfer assay or manufacturing process to a different location. Use of statistical methods to assess comparability before and after the change across the range of interest is a regulatory requirement. Regardless of the types of the changes, comparability is often demonstrated using analytical data collected pre- and post-change. For instance, assay transfer requires the demonstration of comparable assay performance over a range of expected responses. Although there are various methods used in practice or proposed in the published literature, there is no consensus on the best practice. For measurements that exhibit linearity in the outcome variable, a general statistical framework of equivalence testing is proposed. The equivalence test can be carried out either through Bayesian or frequentist analyses. The method is illustrated via several real-world examples.