Direct and indirect causal effects: a helpful distinction?

author: Donald Rubin, Department of Statistics, Faculty of Arts and Sciences, Harvard University
published: Oct. 11, 2010,   recorded: September 2010,   views: 7226


Related Open Educational Resources

Related content

Report a problem or upload files

If you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.
Lecture popularity: You need to login to cast your vote.


Although the terminology of direct and indirect causal effects is relatively common, I believe that it is generally scientifically unhelpful without further explication. This assessment is based on repeated experience with the confusion it creates in important examples in the social and biomedical sciences. After reviewing my perspective on causal inference based on the concepts of potential outcomes and assignment mechanisms, this presentation will discuss two distinct ways to formalize the issues that arise in circumstances where this terminology is used.

The first is based on the concept of principal stratification, and the second is based on the concept of a compound assignment mechanism, which is just a special case of general assignment mechanisms. Simple artificial examples will be used to illustrate the differences between the two conceptualizations, and to show that it is easy to become confused when using the direct and indirect jargon to describe causal effects.

Even the great R.A. Fisher was a victim of this confusion, as will be documented.

See Also:

Download slides icon Download slides: as2010_rubin_dic_01.pdf (330.1┬áKB)

Help icon Streaming Video Help

Link this page

Would you like to put a link to this lecture on your homepage?
Go ahead! Copy the HTML snippet !

Write your own review or comment:

make sure you have javascript enabled or clear this field: