Multiple Partial Imputation, a smart way of filling the Gaps in Longitudinal Data Sets
Biomedical research is plagued with problems of missing data, especially in clinical trials of medical and behavioral therapies adopting longitudinal design. After a thorough review on modeling incomplete longitudinal data based on full-likelihood functions, we proposeed a set of imputation-based strategies for implementing selection, pattern-mixture, and shared-parameter models for handling intermittent missing values and dropouts that are potentially non ignorable according to various criteria. Within the framework of multiple partial imputation, intermittent missing values are first imputed several times; then, each partially imputed data set is analyzed to deal with dropouts with or without further imputation. Depending on the choice of imputation method or measurement model, there exist various strategies that can be jointly applied to the same set of data to study the effect of treatment or intervention from multi-faceted perspectives. Please refer to Yang, Li, Sloptaw (2008) for an example of hot to use MPI in a smoking cessation study.