The study of mediation has a long tradition in the social sciences anchored within the tradition of path analysis and structural equation models (SEMs), and a more recent school mainly developed in epidemiology which stems from methods developed within the potential outcomes (counterfactual) approach to causal inference.
This session introduces the mediation effects defined in the SEM literature and revisit them through the lens of counterfactual-based causal inference; allowing an appreciation of the similarities of the two approaches, and facilitating a general discussion of the advantages and disadvantages of adopting one over the other.
Presenter profile:
Bianca De Stavola, Professor of Medical Statistics, University College London [ Ссылка ]
Session slides:
[ Ссылка ]
