An evaluation of methods to handle missing data in the context of latent variable interaction analysis: multiple imputation, maximum likelihood, and random forest algorithm

DOI10.1007/s42081-022-00176-wzbMath1499.62062OpenAlexW4292790927WikidataQ114217297 ScholiaQ114217297MaRDI QIDQ2103281

Tacksoo Shin, Jeffrey D. Long, Mark L. Davison

Publication date: 13 December 2022

Published in: Japanese Journal of Statistics and Data Science (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s42081-022-00176-w

zbMATH Keywords

maximum likelihood estimationmissing datamultiple imputationrandom forest algorithmlatent interaction model

Mathematics Subject Classification ID

Missing data (62D10)

Uses Software

• SAS
• Mplus
• rsem
• GeneSrF
• randomForest
• MplusAutomation
• missForest

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Bagging predictors
• Random survival forests
• Alternating imputation posterior estimation of models with crossed random effects
• The nature of sensitivity in monotone missing not at random models
• Estimation for the multiple factor model when data are missing
• Likelihood-based inference with singular information matrix
• Maximum likelihood estimation for incomplete multinomial data via the weaver algorithm
• Recursive partitioning for missing data imputation in the presence of interaction effects
• Maximum likelihood estimation of latent interaction effects with the LMS method
• Multiple Imputation After 18+ Years
• Maximum Likelihood Estimates for a Multivariate Normal Distribution when some Observations are Missing
• Fully conditional specification in multivariate imputation
• Multiple Imputation Methods for Treatment Noncompliance and Nonresponse in Randomized Clinical Trials
• Moments and Distributions of Estimates of Population Parameters from Fragmentary Samples
• Estimation for Polynomial Structural Equation Models
• Generating missing values for simulation purposes: a multivariate amputation procedure
• Random forest missing data algorithms
• Missing data techniques for multilevel data: implications of model misspecification
• Multiple imputation: current perspectives
• Random forests