Advanced search
1 file | 279.51 KB Add to list

Flexible mediation analysis in the presence of nonlinear relations: beyond the mediation formula

Tom Loeys (UGent) , Beatrijs Moerkerke (UGent) , Olivia De Smet (UGent) , Ann Buysse (UGent) , Johan Steen (UGent) and Stijn Vansteelandt (UGent)
Author
Organization
Abstract
In the social sciences, mediation analysis has typically been formulated in the context of linear models using the Baron & Kenny (1986) approach. Extensions to nonlinear models have been considered but lack formal justification. By placing mediation analysis within the counterfactual framework of causal inference one can define causal mediation effects in a way that is not tied to a specific statistical model and identify them under certain no unmeasured confounding assumptions. Corresponding estimation procedures using parametric or nonparametric models, based on the so-called mediation formula, have recently been proposed in the psychological literature and made accessible through the R-package mediation. A number of limitations of the latter approach are discussed and a more flexible approach using natural effects models is proposed as an alternative. The latter builds on the same counterfactual framework but enables interpretable and parsimonious modeling of direct and mediated effects and facilitates tests of hypotheses that would otherwise be difficult or impossible to test. We illustrate the approach in a study of individuals who ended a romantic relationship and explore whether the effect of attachment anxiety during the relationship on unwanted pursuit behavior after the breakup is mediated by negative affect during the breakup.
Keywords
IDENTIFICATION, OUTCOMES, BIAS FORMULAS, NATURAL DIRECT, CAUSAL INFERENCE, SENSITIVITY-ANALYSIS

Downloads

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

Citation

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

MLA
Loeys, Tom, et al. “Flexible Mediation Analysis in the Presence of Nonlinear Relations: Beyond the Mediation Formula.” MULTIVARIATE BEHAVIORAL RESEARCH, vol. 48, no. 6, 2013, pp. 871–94, doi:10.1080/00273171.2013.832132.
APA
Loeys, T., Moerkerke, B., De Smet, O., Buysse, A., Steen, J., & Vansteelandt, S. (2013). Flexible mediation analysis in the presence of nonlinear relations: beyond the mediation formula. MULTIVARIATE BEHAVIORAL RESEARCH, 48(6), 871–894. https://doi.org/10.1080/00273171.2013.832132
Chicago author-date
Loeys, Tom, Beatrijs Moerkerke, Olivia De Smet, Ann Buysse, Johan Steen, and Stijn Vansteelandt. 2013. “Flexible Mediation Analysis in the Presence of Nonlinear Relations: Beyond the Mediation Formula.” MULTIVARIATE BEHAVIORAL RESEARCH 48 (6): 871–94. https://doi.org/10.1080/00273171.2013.832132.
Chicago author-date (all authors)
Loeys, Tom, Beatrijs Moerkerke, Olivia De Smet, Ann Buysse, Johan Steen, and Stijn Vansteelandt. 2013. “Flexible Mediation Analysis in the Presence of Nonlinear Relations: Beyond the Mediation Formula.” MULTIVARIATE BEHAVIORAL RESEARCH 48 (6): 871–894. doi:10.1080/00273171.2013.832132.
Vancouver
1.
Loeys T, Moerkerke B, De Smet O, Buysse A, Steen J, Vansteelandt S. Flexible mediation analysis in the presence of nonlinear relations: beyond the mediation formula. MULTIVARIATE BEHAVIORAL RESEARCH. 2013;48(6):871–94.
IEEE
[1]
T. Loeys, B. Moerkerke, O. De Smet, A. Buysse, J. Steen, and S. Vansteelandt, “Flexible mediation analysis in the presence of nonlinear relations: beyond the mediation formula,” MULTIVARIATE BEHAVIORAL RESEARCH, vol. 48, no. 6, pp. 871–894, 2013.
@article{4207454,
  abstract     = {{In the social sciences, mediation analysis has typically been formulated in the context of linear models using the Baron & Kenny (1986) approach. Extensions to nonlinear models have been considered but lack formal justification. By placing mediation analysis within the counterfactual framework of causal inference one can define causal mediation effects in a way that is not tied to a specific statistical model and identify them under certain no unmeasured confounding assumptions. Corresponding estimation procedures using parametric or nonparametric models, based on the so-called mediation formula, have recently been proposed in the psychological literature and made accessible through the R-package mediation. A number of limitations of the latter approach are discussed and a more flexible approach using natural effects models is proposed as an alternative. The latter builds on the same counterfactual framework but enables interpretable and parsimonious modeling of direct and mediated effects and facilitates tests of hypotheses that would otherwise be difficult or impossible to test. We illustrate the approach in a study of individuals who ended a romantic relationship and explore whether the effect of attachment anxiety during the relationship on unwanted pursuit behavior after the breakup is mediated by negative affect during the breakup.}},
  author       = {{Loeys, Tom and Moerkerke, Beatrijs and De Smet, Olivia and Buysse, Ann and Steen, Johan and Vansteelandt, Stijn}},
  issn         = {{0027-3171}},
  journal      = {{MULTIVARIATE BEHAVIORAL RESEARCH}},
  keywords     = {{IDENTIFICATION,OUTCOMES,BIAS FORMULAS,NATURAL DIRECT,CAUSAL INFERENCE,SENSITIVITY-ANALYSIS}},
  language     = {{eng}},
  number       = {{6}},
  pages        = {{871--894}},
  title        = {{Flexible mediation analysis in the presence of nonlinear relations: beyond the mediation formula}},
  url          = {{http://doi.org/10.1080/00273171.2013.832132}},
  volume       = {{48}},
  year         = {{2013}},
}

Altmetric
View in Altmetric
Web of Science
Times cited: