MICT provides a method for multiple imputation for categorical
time-series data such as lifecourse or employment-status
histories that preserves longitudinal consistency, using a
monotonic series of imputations and permitting flexible
predictive models appropriate to the target variable type. Where
transitions are substantially less frequent than once per
time-unit, and where missingness tends to be consecutive, it
produces imputations with better longitudinal consistency than
-mi impute- or -ice-.