Statistical Considerations in the Validation of Ligand-Binding Assays

Statistical Considerations in the Validation of Ligand-Binding Assays 

In the pharmaceutical industry, analytical procedures are the necessary eyes and ears of all experiments performed and data produced. If the quality of an analytical procedure is inadequate, the resulting measurements may be questionable and the scientific validity of the study conclusions may be compromised. Therefore, appropriate evaluation of the data from an analytical procedure is critical from both the statistical and scientific perspectives. 

Regulatory documents [1 3] related to analytical and bioanalytical method validations suggest that all analytical methods should comply with specific acceptance criteria to be recognized as validated procedures. The primary aim of these documents is to provide guidelines on the type of evidence needed from the analytical methods to demonstrate that they are suitable for their intended use. There are, nevertheless, some inconsistencies between these documents with respect to the definition of the performance characteristics and their acceptance criteria. In addition, appropriate ways for analyzing the data and estimating the performance characteristics are not provided. 

Ligand Binding Assays Development, Validation, and Implementation in the Drug Development Arena. Edited by Masood N. Khan and John W.A. Findlay Copyright 2010 John Wiley Sons, Inc. 

In this chapter, we will provide a statistical overview of some important concepts, performance characteristics, and acceptance criteria related to analytical validation. We will also attempt to resolve the inconsistencies noted above and clarify the link between the performance criteria established during analytical validation and the required performance of the measurements during the routine use of the analytical method during the in-study phase. 

---

STATISTICAL CONSIDERATIONS IN THE VALIDATION OF LIGAND BINDING ASSAYS... 

---