Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: Would _sgmediation_ work for dichotomous dependent variable?

From   Bo MacInnis <>
Subject   Re: st: Would _sgmediation_ work for dichotomous dependent variable?
Date   Sun, 01 Aug 2010 14:19:33 -0700


Thank you so much! As you might have seen Mr. Ender's response, there is another new tool he made just for that purpose. I am excited about using it. Thank you also for your reference on Stata jounral.


At 12:32 PM 8/1/2010, you wrote:
--- On Sun, 1/8/10, Bo MacInnis wrote:
> Interested in using the wonderful _sgmediation_ command
> that Phil Ender provided, I wonder if the use of
> _sgmediation_ is restricted to linear regression with
> continuous dependent variable. I have a case where the
> dependent variable is categorical or even dichotomous, and
> I've been using probit for the main (total effect) for the
> dichotomous dependent variable. I'd like to use
> _sgmediation_ for the mediational analysis.

That is not possible. The estimation of mediation effects is
much more easier in linear regression. This kind of
calculations do not generalize to non-linear models like
-probit-. A discussion of this issue can be found in:

M.L. Buis (2010) "Direct and indirect effects in a logit
model", The Stata Journal, 10(1), pp. 11-29.

This paper also contains one possible sollution.

Hope this helps,
Maarten (author of the above article)

Maarten L. Buis
Institut fuer Soziologie
Universitaet Tuebingen
Wilhelmstrasse 36
72074 Tuebingen

*   For searches and help try:

*   For searches and help try:

© Copyright 1996–2017 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index