A Primer on Maximum Likelihood Algorithms Available for Use With Missing Data

TLDR

Maximum likelihood algorithms for missing data are increasingly common in statistical software, yet confusion persists regarding the distinctions among the three primary methods: multiple-group, full information maximum likelihood, and the EM algorithm. This article provides a clear, nontechnical overview of these three maximum likelihood algorithms. It also discusses multiple imputation, which is frequently used in conjunction with the EM algorithm.

Abstract

Abstract Maximum likelihood algorithms for use with missing data are becoming commonplace in microcomputer packages. Specifically, 3 maximum likelihood algorithms are currently available in existing software packages: the multiple-group approach, full information maximum likelihood estimation, and the EM algorithm. Although they belong to the same family of estimator, confusion appears to exist over the differences among the 3 algorithms. This article provides a comprehensive, nontechnical overview of the 3 maximum likelihood algorithms. Multiple imputation, which is frequently used in conjunction with the EM algorithm, is also discussed.