TY - JOUR
T1 - Multiple imputation of incomplete multilevel data using Heckman selection models
AU - Muñoz, Johanna
AU - Efthimiou, Orestis
AU - Audigier, Vincent
AU - de Jong, Valentijn M.T.
AU - Debray, Thomas P.A.
N1 - Publisher Copyright:
© 2023 The Authors. Statistics in Medicine published by John Wiley & Sons Ltd.
PY - 2024/2/10
Y1 - 2024/2/10
N2 - Missing data is a common problem in medical research, and is commonly addressed using multiple imputation. Although traditional imputation methods allow for valid statistical inference when data are missing at random (MAR), their implementation is problematic when the presence of missingness depends on unobserved variables, that is, the data are missing not at random (MNAR). Unfortunately, this MNAR situation is rather common, in observational studies, registries and other sources of real-world data. While several imputation methods have been proposed for addressing individual studies when data are MNAR, their application and validity in large datasets with multilevel structure remains unclear. We therefore explored the consequence of MNAR data in hierarchical data in-depth, and proposed a novel multilevel imputation method for common missing patterns in clustered datasets. This method is based on the principles of Heckman selection models and adopts a two-stage meta-analysis approach to impute binary and continuous variables that may be outcomes or predictors and that are systematically or sporadically missing. After evaluating the proposed imputation model in simulated scenarios, we illustrate it use in a cross-sectional community survey to estimate the prevalence of malaria parasitemia in children aged 2-10 years in five regions in Uganda.
AB - Missing data is a common problem in medical research, and is commonly addressed using multiple imputation. Although traditional imputation methods allow for valid statistical inference when data are missing at random (MAR), their implementation is problematic when the presence of missingness depends on unobserved variables, that is, the data are missing not at random (MNAR). Unfortunately, this MNAR situation is rather common, in observational studies, registries and other sources of real-world data. While several imputation methods have been proposed for addressing individual studies when data are MNAR, their application and validity in large datasets with multilevel structure remains unclear. We therefore explored the consequence of MNAR data in hierarchical data in-depth, and proposed a novel multilevel imputation method for common missing patterns in clustered datasets. This method is based on the principles of Heckman selection models and adopts a two-stage meta-analysis approach to impute binary and continuous variables that may be outcomes or predictors and that are systematically or sporadically missing. After evaluating the proposed imputation model in simulated scenarios, we illustrate it use in a cross-sectional community survey to estimate the prevalence of malaria parasitemia in children aged 2-10 years in five regions in Uganda.
KW - Heckman model
KW - IPDMA
KW - missing not at random
KW - multiple imputation
KW - selection models
UR - http://www.scopus.com/inward/record.url?scp=85179313426&partnerID=8YFLogxK
U2 - 10.1002/sim.9965
DO - 10.1002/sim.9965
M3 - Article
C2 - 38073512
AN - SCOPUS:85179313426
SN - 0277-6715
VL - 43
SP - 514
EP - 533
JO - Statistics in Medicine
JF - Statistics in Medicine
IS - 3
ER -