Incorporating Multiple Imputation Into Tanezumab Dose-Response Modeling of WOMAC Pain CFB Across Six Randomized Placebo-Controlled Phase 3 Trials.

Abstract

Multiple imputation is increasingly being used to deal with missing data in clinical trials. It is a simulation approach leading to multiple analyses of a pre-defined number of datasets. For a pre-defined statistical model, this is relatively straightforward, but for model development as typically conducted in Pharmacometrics, it is unclear how such an approach could be implemented. This case study describes how this was addressed at the time of a regulatory submission and considers alternative approaches which could be adopted in the future.