Display options
Cite
Grund S, Lüdtke O, Robitzsch A. Multiple imputation of missing data in multilevel models with the R package mdmb: a flexible sequential modeling approach. Behav Res Methods. 2021;53(6):2631-2649doi: 10.3758/s13428-020-01530-0.
Grund, S., Lüdtke, O., & Robitzsch, A. (2021). Multiple imputation of missing data in multilevel models with the R package mdmb: a flexible sequential modeling approach. Behavior research methods, 53(6), 2631-2649. https://doi.org/10.3758/s13428-020-01530-0
Grund, Simon, et al. "Multiple imputation of missing data in multilevel models with the R package mdmb: a flexible sequential modeling approach." Behavior research methods vol. 53,6 (2021): 2631-2649. doi: https://doi.org/10.3758/s13428-020-01530-0
Grund S, Lüdtke O, Robitzsch A. Multiple imputation of missing data in multilevel models with the R package mdmb: a flexible sequential modeling approach. Behav Res Methods. 2021 Dec;53(6):2631-2649. doi: 10.3758/s13428-020-01530-0. Epub 2021 May 23. PMID: 34027594; PMCID: PMC8613130.
Copy Download .nbib Format: NLM
Share it on

Behav Res Methods. 2021 Dec;53(6):2631-2649. doi: 10.3758/s13428-020-01530-0. Epub 2021 May 23.

Multiple imputation of missing data in multilevel models with the R package mdmb: a flexible sequential modeling approach.

Behavior research methods

Simon Grund, Oliver Lüdtke, Alexander Robitzsch

Affiliations

  1. IPN - Leibniz Institute for Science and Mathematics Education, Kiel, Germany. [email protected].
  2. Centre for International Student Assessment, Munich, Germany. [email protected].
  3. IPN - Leibniz Institute for Science and Mathematics Education, Kiel, Germany.
  4. Centre for International Student Assessment, Munich, Germany.

PMID: 34027594 PMCID: PMC8613130 DOI: 10.3758/s13428-020-01530-0

Abstract

Multilevel models often include nonlinear effects, such as random slopes or interaction effects. The estimation of these models can be difficult when the underlying variables contain missing data. Although several methods for handling missing data such as multiple imputation (MI) can be used with multilevel data, conventional methods for multilevel MI often do not properly take the nonlinear associations between the variables into account. In the present paper, we propose a sequential modeling approach based on Bayesian estimation techniques that can be used to handle missing data in a variety of multilevel models that involve nonlinear effects. The main idea of this approach is to decompose the joint distribution of the data into several parts that correspond to the outcome and explanatory variables in the intended analysis, thus generating imputations in a manner that is compatible with the substantive analysis model. In three simulation studies, we evaluate the sequential modeling approach and compare it with conventional as well as other substantive-model-compatible approaches to multilevel MI. We implemented the sequential modeling approach in the R package mdmb and provide a worked example to illustrate its application.

© 2021. The Author(s).

Keywords: Interaction effects; Missing data; Multilevel analysis; Multiple imputation

References

  1. Psychol Methods. 2002 Jun;7(2):147-77 - PubMed
  2. Stat Methods Med Res. 2019 Feb;28(2):555-568 - PubMed
  3. Psychol Methods. 2016 Jun;21(2):222-40 - PubMed
  4. Stat Med. 2016 Jul 30;35(17):2955-74 - PubMed
  5. Psychol Aging. 2009 Dec;24(4):828-40 - PubMed
  6. J Educ Behav Stat. 2018 Oct;43(5):511-539 - PubMed
  7. Adv Methods Pract Psychol Sci. 2019 Sep;2(3):288-311 - PubMed
  8. Psychol Methods. 2017 Mar;22(1):141-165 - PubMed
  9. Behav Res Methods. 2007 Feb;39(1):101-17 - PubMed
  10. Behav Res Methods. 2016 Jun;48(2):640-9 - PubMed
  11. Multivariate Behav Res. 2018 Sep-Oct;53(5):695-713 - PubMed
  12. Biometrics. 2003 Dec;59(4):1140-50 - PubMed
  13. Psychol Methods. 2008 Sep;13(3):203-29 - PubMed
  14. Stat Methods Med Res. 2015 Aug;24(4):462-87 - PubMed
  15. Psychol Methods. 2020 Feb;25(1):88-112 - PubMed
  16. Psychol Methods. 2020 Apr;25(2):157-181 - PubMed
  17. Stat Med. 2015 May 20;34(11):1876-88 - PubMed
  18. Stat Methods Med Res. 2018 Jun;27(6):1634-1649 - PubMed
  19. Biom J. 2019 Jul;61(4):1003-1019 - PubMed
  20. Psychol Methods. 2016 Jun;21(2):189-205 - PubMed
  21. Stat Med. 2016 Jul 30;35(17):2938-54 - PubMed
  22. Stat Modelling. 2011 Aug;11(4):351-370 - PubMed

Publication Types