Concepts and methods in causal mediation analysis
Date:
07/09/2015
Organised by:
Royal Statistical Society
Presenter:
Bianca De Stavola and Rhian Daniel
Level:
Intermediate (some prior knowledge)
Contact:
Sarah Barker
Description:
The aim of many research areas may involve the study of how the effect of a particular exposure on the outcome of interest is mediated by intermediate factors. Although the study of mediation is well established in the social and behavioural sciences, and often loosely attempted in epidemiology, developments in modern causal inference have highlighted the limitations of these ‘classical’ approaches and led to new definitions based on counterfactuals and novel estimation methods that deal with specific challenges such as intermediate confounding.
In this workshop we will present and compare these two frameworks and stress the greater rigour and generality permitted by the potential outcomes framework.
Knowledge of basic statistics and regression analyses will be assumed.
Cost:
£480 (reductions for early booking and RSS members)
Website and registration:
Region:
South West
Keywords:
Statistical Theory and Methods of Inference, causal , inference
Related publications and presentations:
Statistical Theory and Methods of Inference