Mediation Analysis

About

The course will introduce traditional and new methods for mediation analysis. These methods are commonly used to assess social and biological pathways by which causal effects operate. Fundamentals of mediation analysis will be presented for dichotomous, continuous, and time-to-event outcomes, and discussion will be given as to when the standard approaches to mediation analysis are or are not valid. The relationship between traditional methods for mediation in the biomedical and the social sciences and new methods in causal inference will be discussed. The course will also introduce some of the recent developments in the field, including extensions to incorporate multiple mediators and interactions. Stata macros and commands to implement these techniques will be presented, and several applications from epidemiology and the social sciences will be illustrated and discussed. Basic knowledge of linear and logistic regression is recommended.

Course leader

Andrea Bellavia (Harvard School of Public Health)

Target group

Physicians, clinicians and public health professionals from public and private institutions who are looking for systematic training in the principles of epidemiology and biostatistics, or epidemiology applied to health care planning and evaluation. They will acquire familiarity with epidemiological and biostatistical principles and techniques and with the computational tools needed to solve practical problems.

Students in biostatistics and epidemiology, and researchers both from public and private institutions who wish to increase their familiarity with quantitative methods or to deepen their knowledge of a specific area of interest, so they can more effectively address problems in health research. They will gain knowledge in modern, advanced methods useful for health professionals engaged in clinical practice, research and teaching.

Course aim

The course will cover some of the recent developments in causal mediation analysis and provide practical tools to implement these techniques.

Fee info