A comprehensive method validation strategy for bioanalytical applications in the pharmaceutical industry--2. Statistical analyses.

The first paper in this two-part series described [Lang and Bolton, J. Pharm. Biomed. Anal. 9, 357-361 (1991)] an overall validation strategy for bioanalytical methods. This second paper focuses on the statistical analyses performed on the validation data that will allow the analyst to evaluate the reliability and reproducibility of a bioanalytical method. Based on the validation results, acceptance criteria for the quality control concentrations are established and used during the study proper to determine if the analytical run is valid. After analysing the clinical study samples and accepting the analytical runs, the quality control results are incorporated into databases to update their acceptance limits. This continuous validation process enables the analyst to monitor the method's performance over time and be confident that accurate sample concentrations are being reported. It is important to emphasize that the statistical analyses of the data provide information that should be considered from a practical point of view by the analyst. The analyst should use sound judgement in evaluating the reliability of the method.