You are here

Mediation analysis in epidemiology


In epidemiological studies, it is often necessary to disentangle the pathways that link an exposure to an outcome. Typically this implies to decompose the total effect of the exposure on the outcome into the part that is explained by a given set of mediators (indirect effect) and the part that is not explained by those mediators (direct effect). A new approach based on counterfactuals has been recently proposed to carry out mediation analyses. The presentation will describe this approach, including its assumptions, interpretation and limits, and provide some empirical examples of mediation analysis.

Lorenzo Richiardi, Cancer Epidemiology Unit, Department of Medical Sciences, University of Turin
Short bio: 

Lorenzo Richiardi is Associated Professor of Biostatistics and Epidemiology at the University of Turin, Italy. He holds a degree in Medicine from the University of Turin and a Phd in Epidemiology from the Karolinska Institutet, Sweden. His research mainly concerns cancer epidemiology, life-course epidemiology and epidemiological methods, with specific interest in causal inference. He has been visiting researcher at the Massey University in New Zealand and at the Harvard School of Public Health in the USA and is member of the editorial board of the international Journal of Epidemiology and Epidemiologia & Prevenzione. Lorenzo Richiardi has co-authored more than 150 publications in international journals and is author of 8 book chapters.

10 March 2016 - 17:00


Vicolo Dallapiccola 12, 38122 Trento