Application of Multiple Imputation using the Two-Fold Fully Conditional Specification Algorithm in Longitudinal Clinical Data

摘要: Electronic health records of longitudinal clinical data are a valuable resource for care research. One obstacle using databases in epidemiological analyses is that general practitioners mainly record if they clinically relevant. We can use existing methods to handle missing data, such as multiple imputation (mi), we treat the unavailability measurements missing-data problem. Most software implementations MI do not take account and dynamic structure difficult implement large with millions individuals long follow-up. Nevalainen, Kenward, Virtanen (2009, Statistics Medicine 28: 3657-3669) proposed two-fold fully conditional specification algorithm impute data. It imputes values at given time point, on information same point immediately adjacent points. In this article, describe new command, twofold, implements algorithm. extended accommodate databases.