Causal Mediation Analysis [ESP69]

Detailed information about this course:

Description

NOTE: THIS COURSE IS ONLINE, COURSE TIMETABLE DEVIATES FROM STANDARD COURSE TIMES

Faculty: Linda Valeri, PhD

The course covers recent developments in causal mediation analysis and provides practical tools to implement these techniques. Mediation analysis concerns assessing the mechanisms and pathways by which causal effects operate. The course covers the relationship between traditional methods for mediation in epidemiology and the social sciences and new methods in causal inference. For dichotomous and continuous outcomes, we discuss when the standard approaches to mediation analysis are valid. Using ideas from causal inference and natural direct and indirect effects, alternative mediation analysis techniques are described when the standard approaches do not work. The no-confounding assumptions needed for these techniques are described.

R packages to implement these techniques are covered and distributed to course participants and will be used in hands on exercises. SAS and Stata macros will be distributed and described as well. The use and implementation of sensitivity analysis techniques to assess the how sensitive conclusions are to violations of assumptions are covered. Discussion will be given to how such mediation analysis approaches can be extended to settings in which data come from a case-control study design. The methods will be illustrated by various applications.

The course will employ a combination of asynchronous learning, in class lecture and discussion, laboratory sessions and software demonstration. In a typical course day, mornings are devoted to in class discussion and laboratory sessions, afternoons are devoted to asynchronous learning. Slides are used to present material in lecture form. Extensive notes are available for students. A wide variety of examples from epidemiology and the social sciences will be used to illustrate the techniques and approaches. Ample time is given for discussion and questions. A variety of software packages will be discussed. Students will have worked exercises that they can complete on their own.

Timetable
08:45 - 11:45 live class
13:00 - 16:00 asynchronous components and homework

Please note that we are currently updating the information for 2024, therefore the course information is still subject to change.

Objectives

• Understand when traditional methods for mediation fail
• Learn the concepts about mediation from causal inference
• Learn methods and sensitivity analysis techniques for mediation
• Develop facility with use of software for mediation
  

Participant profile

Anyone who wants to learn about mediation analysis and is familiar with linear and logistic regression.

Assessment

Attendance