APS

31st APS Annual Convention · 2019

Improving Causal Inference and Replication in Longitudinal Mediation Analysis.

Washington, DC · May 2019

Poster · Methodology

  • Davood Tofighi
    University of New Mexico
  • Yu-Yu Hsiao
    University of New Mexico
  • Eric Kruger
    University of New Mexico
  • David MacKinnon
    Arizona State University, Tempe
  • M Lee Van Horn
    University of New Mexico
  • Katie Witkiewitz
    University of New Mexico

Abstract

We developed a sensitivity analysis technique for a multiple mediator model with two covarying mediators. We compute the biasing effect of confounding on point and confidence interval estimates of the indirect effects. We illustrate plots to visually summarize the effects of confounding on each indirect effect using an empirical example.

Statistics and Methodology

← Poster Session XIV