Statistical Issues in Analytical Method Validation

• Activity Number: 617
• Type: Contributed
• Date/Time: Wednesday, August 12, 2015 : 2:00 PM to 3:50 PM
• Sponsor: Biopharmaceutical Section
• Author(s): Pin Ren* and Lingmin Zeng and Binbing Yu
• Companies: MedImmune and MedImmune and MedImmune
• Keywords: Biological Assays ; Bioanalytical Method Validation ; Accuracy ; Precision ; Variance Component

Abstract

Validation of analytical methods is required in drug development and manufacturing to demonstrate the methods are fit for their intended purpose. Validation of analytical methods is mandatory in the submission to regulatory authorities for clinical trials and marketing application. According to ICH, FDA, EMA guidelines, a number of validation characteristics should be assessed, which included accuracy, precision, linearity among others. To evaluate the accuracy and precision, often multiple analysts, instruments and replicates are involved. Various statistical models and techniques have been used such as log-transformation, fixed effects model, random effects model. We examined and compared the performances of currently available methods with simulations.