TWOFOLD: Stata module to perform multiple imputation using the two-fold fully conditional specification algorithm to impute missing values in longitudinal data

twofold imputes missing values at each time point conditional on observed measurements within a small time window using FCS (or chained equations). Missing values at time point t are imputed by cycling around the specified imputation models, performing 'within-time iterations'. Once these are complete, the variables at time point t+1 are imputed. Each time point is chronologically updated. Once missing values at the last time point are imputed, the first 'among-time iteration' is complete. Further 'among-time iterations' are performed, each one starting from the first time point. At each step of the procedure, the most recent imputations of missing values are carried forward to the next step. When the pre-specified among-time iterations are complete, the current imputations of missing values, together with the originally observed values, form the first imputed dataset. The whole process is repeated to create as many imputed dataset as desired, using the previous imputed dataset as starting values.