Advanced search
1 file | 398.92 KB

Estimation of indirect effects in the presence of unmeasured confounding for the mediator-outcome relationship in a multilevel 2-1-1 mediation model

Wouter Talloen (UGent) , Beatrijs Moerkerke (UGent) , Tom Loeys (UGent) , Jessie De Naeghel (UGent) , Hilde Van Keer (UGent) and Stijn Vansteelandt (UGent)
Author
Organization
Project
G.0111.12
Abstract
To assess the direct and indirect effect of an intervention, multilevel 2-1-1 studies with intervention randomized at the upper (class) level and mediator and outcome measured at the lower (student) level are frequently used in educational research. In such studies, the mediation process may flow through the student-level mediator (the within indirect effect) or a class-aggregated mediator (the contextual indirect effect). In this article, we cast mediation analysis within the counterfactual framework and clarify the assumptions that are needed to identify the within and contextual indirect effect. We show that unlike the contextual indirect effect, the within indirect effect can be unbiasedly estimated in linear models in the presence of unmeasured confounders of the mediator-outcome relationship at the upper level that exert additive effects on mediator and outcome. When unmeasured confounding occurs at the individual level, both indirect effects are no longer identified. We propose sensitivity analyses to assess the robustness of the within and contextual indirect effect under lower and upper-level confounding, respectively.
Keywords
LINEAR-MODELS, LEVEL MEDIATION, multilevel, counterfactual framework, mediation, 2-1-1 settings, CAUSAL INFERENCE, indirect effect, SCHOOL, SEM, MOTIVATION

Downloads

  • (...).pdf
    • full text
    • |
    • UGent only
    • |
    • PDF
    • |
    • 398.92 KB

Citation

Please use this url to cite or link to this publication:

Chicago
Talloen, Wouter, Beatrijs Moerkerke, Tom Loeys, Jessie De Naeghel, Hilde Van Keer, and Stijn Vansteelandt. 2016. “Estimation of Indirect Effects in the Presence of Unmeasured Confounding for the Mediator-outcome Relationship in a Multilevel 2-1-1 Mediation Model.” Journal of Educational and Behavioral Statistics 41 (4): 359–391.
APA
Talloen, Wouter, Moerkerke, B., Loeys, T., De Naeghel, J., Van Keer, H., & Vansteelandt, S. (2016). Estimation of indirect effects in the presence of unmeasured confounding for the mediator-outcome relationship in a multilevel 2-1-1 mediation model. JOURNAL OF EDUCATIONAL AND BEHAVIORAL STATISTICS, 41(4), 359–391.
Vancouver
1.
Talloen W, Moerkerke B, Loeys T, De Naeghel J, Van Keer H, Vansteelandt S. Estimation of indirect effects in the presence of unmeasured confounding for the mediator-outcome relationship in a multilevel 2-1-1 mediation model. JOURNAL OF EDUCATIONAL AND BEHAVIORAL STATISTICS. 2016;41(4):359–91.
MLA
Talloen, Wouter, Beatrijs Moerkerke, Tom Loeys, et al. “Estimation of Indirect Effects in the Presence of Unmeasured Confounding for the Mediator-outcome Relationship in a Multilevel 2-1-1 Mediation Model.” JOURNAL OF EDUCATIONAL AND BEHAVIORAL STATISTICS 41.4 (2016): 359–391. Print.
@article{8152792,
  abstract     = {To assess the direct and indirect effect of an intervention, multilevel 2-1-1 studies with intervention randomized at the upper (class) level and mediator and outcome measured at the lower (student) level are frequently used in educational research. In such studies, the mediation process may flow through the student-level mediator (the within indirect effect) or a class-aggregated mediator (the contextual indirect effect). In this article, we cast mediation analysis within the counterfactual framework and clarify the assumptions that are needed to identify the within and contextual indirect effect. We show that unlike the contextual indirect effect, the within indirect effect can be unbiasedly estimated in linear models in the presence of unmeasured confounders of the mediator-outcome relationship at the upper level that exert additive effects on mediator and outcome. When unmeasured confounding occurs at the individual level, both indirect effects are no longer identified. We propose sensitivity analyses to assess the robustness of the within and contextual indirect effect under lower and upper-level confounding, respectively.},
  author       = {Talloen, Wouter and Moerkerke, Beatrijs and Loeys, Tom and De Naeghel, Jessie and Van Keer, Hilde and Vansteelandt, Stijn},
  issn         = {1076-9986},
  journal      = {JOURNAL OF EDUCATIONAL AND BEHAVIORAL STATISTICS},
  keyword      = {LINEAR-MODELS,LEVEL MEDIATION,multilevel,counterfactual framework,mediation,2-1-1 settings,CAUSAL INFERENCE,indirect effect,SCHOOL,SEM,MOTIVATION},
  language     = {eng},
  number       = {4},
  pages        = {359--391},
  title        = {Estimation of indirect effects in the presence of unmeasured confounding for the mediator-outcome relationship in a multilevel 2-1-1 mediation model},
  url          = {http://dx.doi.org/10.3102/1076998616636855},
  volume       = {41},
  year         = {2016},
}

Altmetric
View in Altmetric
Web of Science
Times cited: