An empirical comparison of multiple imputation methods for categorical data

Multiple imputation is a common approach for dealing with missing values in statistical databases. The imputer fills in missing values with draws from predictive models estimated from the observed data, resulting in multiple, completed versions of the database. Researchers have developed a variety of default routines to implement multiple imputation; however, there has been limited research comparing the performance of these methods, particularly for categorical data. We use simulation studies to compare repeated sampling properties of three default multiple imputation methods for categorical data, including chained equations using generalized linear models, chained equations using classification and regression trees, and a fully Bayesian joint distribution based on Dirichlet Process mixture models. We base the simulations on categorical data from the American Community Survey. The results suggest that default chained equations approaches based on generalized linear models are dominated by the default regression tree and mixture model approaches. They also suggest competing advantages for the regression tree and mixture model approaches, making both reasonable default engines for multiple imputation of categorical data.