Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, statalist.org is already up and running.


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

Re: st: Computing Average Partial Effects after xtprobit, re


From   Maarten Buis <maartenlbuis@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Computing Average Partial Effects after xtprobit, re
Date   Mon, 15 Aug 2011 17:33:56 +0200

On Mon, Aug 15, 2011 at 5:24 PM, natasha agarwal wrote:
> I wanted to compute the average partial effects manually after xtprobit, re.

What do you want to do with the random effects? If you want to be
strict, you would have to average over these as well, and that has not
been implemented (yet). You use a hybrid solution, where you fix the
random effects at the mean (0) and average over the remaining
variables. You can do so by typing:

margins, predict(pu0) dydx(*)

A more elegant solution is to forget about probit and xtprobit and
move to logit and xtlogit. After that you can just interpret the odds
ratios, which are independent of the other variables and thus don't
need such hybrid solutions.

Hope this helps,
Maarten

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


http://www.maartenbuis.nl
--------------------------
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index