|
Abstract:
|
ICH-E9 (R1) defines missing data as ‘data that would be meaningful for the analysis of a given estimand but were not collected. They should be distinguished from data that do not exist or data that are not considered meaningful because of an intercurrent event’. With this definition data may be considered as missing or not depending on the timepoint and type of the ICE and of the strategies to deal with. One difficulty in the studies is to decide whether a study termination is only to be considered as missing value, or whether the discontinuation of study treatment had happened e.g., because of lack of efficacy and therefore should be considered as ICE. Another aspect which causes confusion is that for the hypothetical strategy the way of modelling the data after an ICE can be rather similar to the imputation of missing values. The confusion is even more, if estimands are defined using the same variable but assessed at various timepoints, and the respective ICEs are handled using other strategies than treatment-policy. This presentation will focus on the various steps to ensure the adequate handling of missing data and ICE in the analysis of the above described situation.
|
