Affordable Access

deepdyve-link
Publisher Website

Multiple imputation by chained equations for systematically and sporadically missing multilevel data.

Authors
  • Resche-Rigon, Matthieu1, 2, 3
  • White, Ian R4
  • 1 1 Service de Biostatistique et Information Médicale, Hôpital Saint-Louis, Paris, France. , (France)
  • 2 2 Université Paris Diderot - Paris 7, Sorbonne Paris Cité, Paris, France. , (France)
  • 3 3 ECSTRA Team, INSERM, Paris, France. , (France)
  • 4 4 MRC Biostatistics Unit, Cambridge Institute of Public Health, Cambridge, UK.
Type
Published Article
Journal
Statistical Methods in Medical Research
Publisher
SAGE Publications
Publication Date
Jun 01, 2018
Volume
27
Issue
6
Pages
1634–1649
Identifiers
DOI: 10.1177/0962280216666564
PMID: 27647809
Source
Medline
Keywords
License
Unknown

Abstract

In multilevel settings such as individual participant data meta-analysis, a variable is 'systematically missing' if it is wholly missing in some clusters and 'sporadically missing' if it is partly missing in some clusters. Previously proposed methods to impute incomplete multilevel data handle either systematically or sporadically missing data, but frequently both patterns are observed. We describe a new multiple imputation by chained equations (MICE) algorithm for multilevel data with arbitrary patterns of systematically and sporadically missing variables. The algorithm is described for multilevel normal data but can easily be extended for other variable types. We first propose two methods for imputing a single incomplete variable: an extension of an existing method and a new two-stage method which conveniently allows for heteroscedastic data. We then discuss the difficulties of imputing missing values in several variables in multilevel data using MICE, and show that even the simplest joint multilevel model implies conditional models which involve cluster means and heteroscedasticity. However, a simulation study finds that the proposed methods can be successfully combined in a multilevel MICE procedure, even when cluster means are not included in the imputation models.

Report this publication

Statistics

Seen <100 times