Multiple Imputation for Missing Data: Concepts and New Development

Multiple imputation provides a useful strategy for dealing with data sets with missing values. Instead of filling in a single value for each missing value, Rubin’s (1987) multiple imputation procedure replaces each missing value with a set of plausible values that represent the uncertainty about the right value to impute. These multiply imputed data sets are then analyzed by using standard procedures for com-plete data and combining the results from these analyses. No matter which complete-data analysis is used, the pro-cess of combining results from different imputed data sets is essentially the same. This results in valid statistical in-ferences that properly reflect the uncertainty due to missing values. This paper reviews methods for analyzing missing data, including basic concepts and applications of multiple im-putation techniques. The paper also presents new SAS R procedures for creating multiple imputations for in-complete multivariate data and for analyzing results from multiply imputed data sets. These procedures are still under development and will be available in experimental form in Release 8.1 of the SAS System