The handling of missing data in clinical trials

Author(s): Michael G Kenward

The problem of handling missing data in clinical trials is discussed, particularly in the light of two recent publications associated with the US and European regulators. The importance of assessing methods in the light of the target of the analysis – the estimand – is emphasized, and two types of estimand, de jure and de facto, are introduced. A key distinction is made between analyses in which missing data are ‘defined away’ and in which they represent a nuisance to be accommodated. The role of sensitivity analysis, which is acknowledged to play a major role in this setting, is considered. Finally, the recent recognition of the importance of collecting outcome data following protocol deviations is touched upon.