An Empirical Comparison of Multiple Imputation Methods for Categorical Data

Journal Article (Journal Article)

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. In the circumstances of this study, the results suggest that default chained equations approaches based on generalized linear models are dominated by the default regression tree and Bayesian mixture model approaches. They also suggest competing advantages for the regression tree and Bayesian mixture model approaches, making both reasonable default engines for multiple imputation of categorical data. Supplementary material for this article is available online.

Full Text

Duke Authors

Cited Authors

  • Akande, O; Li, F; Reiter, J

Published Date

  • April 3, 2017

Published In

Volume / Issue

  • 71 / 2

Start / End Page

  • 162 - 170

Electronic International Standard Serial Number (EISSN)

  • 1537-2731

International Standard Serial Number (ISSN)

  • 0003-1305

Digital Object Identifier (DOI)

  • 10.1080/00031305.2016.1277158

Citation Source

  • Scopus