6533b873fe1ef96bd12d4892
RESEARCH PRODUCT
Insights into the derivative-based method for nonlinear mediation models
Claudio RubinoChiara Di Mariasubject
mediation analysis derivative method generalised linear models bootstrap Monte Carlo method Bayesian statisticsSettore SECS-S/01 - Statisticadescription
Associational mediation analysis has generally relied on the linearity of models to estimate the indirect effect as a product of regression coefficients. Very few examples of generalisations to nonlinear settings have been proposed, including a derivative-based method that, however, is far from being widely spread among scholars. In this paper, we clarify some aspects of such an approach to nonlinear mediation models, which have not been addressed by the previous literature. In addition, we run a simulation study to compare confidence intervals for the indirect effect obtained through different approaches.
| year | journal | country | edition | language |
|---|---|---|---|---|
| 2022-01-01 |