Causal Mediation Analysis
An On-Demand Seminar Taught by
Tyler VanderWeele, Ph.D.
To see a sample of the course slides, click here.
This seminar will focus on some of the recent developments in causal mediation analysis and will provide practical tools to implement those techniques. Mediation analysis deals with the mechanisms and pathways by which causal effects operate. The course will discuss the relationship between traditional methods for mediation in the biomedical and social sciences and new methods of causal inference for dichotomous, continuous, and time-to-event outcomes.
The course takes place online in a series of four weekly installments of videos, quizzes, readings, and exercises, and requires about 8 hours/week. You may participate at your own convenience; there are no set times when you are required to be online.
This four-week course can be accessed with any recent web browser on almost any platform, including iPhone, iPad, and Android devices. It consists of several modules, which contain videos of the live, 4-day remote version of the course in its entirety. Each module is followed by a short multiple-choice quiz to test your knowledge. There are also weekly exercises that ask you to apply what you’ve learned to a real data set.
There is also an online discussion forum where you can post questions or comments about any aspect of the course. All questions will be promptly answered by Dr. VanderWeele.
MORE DETAILS ABOUT THE COURSE CONTENT
We will also consider when standard approaches to mediation analysis are valid and when they are not valid. These approaches will be extended to more complex settings. The no-confounding assumptions needed for these techniques will be discussed in detail. SAS, SPSS, Stata, and R macros to implement mediation methods will be demonstrated and distributed to course participants.
Other topics include the use and implementation of sensitivity analysis (to assess how sensitive conclusions are to violations of assumptions) and extensions to multiple mediators.
In all cases, methods will be illustrated using software, with SAS, Stata, SPSS, and R examples and syntax. To do the exercises, you will need to use your own computer with a recent version of SAS, Stata, SPSS, or R. SAS and Stata will be supported by the instructor. Macros in SPSS and R will also be accessible, but SPSS and R will not be directly supported by the instructor.
If you’d like to use R for this course but don’t yet have much experience with that package, here are some excellent on-line resources for building your R skills.
WHO SHOULD Register?
Course prerequisites: Familiarity with linear and logistic regression. Some knowledge of counterfactual or potential outcomes notation is helpful, but not necessary.
REVIEWS OF Causal Mediation Analysis
“This course is excellent. I learned far more than I expected (and I already had some previous exposure to these methods). Dr. VanderWeele made these complex topics comprehensible and I very much appreciated his focus on teaching us techniques that can be practically implemented in SAS, Stata, R, and SPSS. In addition, his coverage of surrogate outcomes vs. mediators was very thoughtful and an important new area for me. I plan to recommend future sessions of this seminar to my colleagues who are doing or contemplating mediation analyses.”
Tor Neilands, University of California, San Francisco
“Dr. VanderWeele is an excellent teacher and provides detailed, thorough explanation of mediation analysis in this course. The course is well set up, exposes students to advanced analytical approaches, and provides some excellent guidance on how I can improve my approach in answering the scientific hypotheses of my interests. I took this course for my dissertation research and it has been very helpful in every possible way.”
Ninad Chaudhary, University of Alabama, Birmingham
“Dr. VanderWeele is an expert in the field of causal mediation analysis and this is a great opportunity to obtain a personal instruction on a new methodology. The applied assignment allows individuals to apply the newly acquired knowledge in a setting where you can receive live feedback from an instructor that is easy to understand. All around great experience.”
Michael Flores, Harvard Medical School / Cambridge Health Alliance
“The course provided practical tips and analytical skills that you can easily understand and apply despite its convoluted concepts and theories. The instructor’s explanation was clear, easy to understand, and free of any jargon. I highly recommend this course to supplement analytical skills.”
Machiko Minegishi, Harvard University
“This course provides a great opportunity to learn causal mediation analysis and have a hands-on experience with statistical programs. Very helpful feedback from Dr. VanderWeele. Great opportunity to meet researchers with similar interests. Highly recommended!”
Shu Xu, New York University