MIDAS: A SAS macro for multiple imputation using distance-aided selection of donors

摘要: In this paper we describe MIDAS: a SAS macro for multiple imputation using distance aided selection of donors which implements an iterative predictive mean matching hot-deck imputing missing data. This is flexible approach that can handle data in variety formats: continuous, ordinal, and scaled. Because the models are implicit, it not necessary to specify parametric distribution each variable be imputed. MIDAS also allows user address sensitivity their inferences different assumptions concerning mechanism. An example impute presented compared existing software.