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: margins after panel commands

From   Maarten buis <>
Subject   Re: st: margins after panel commands
Date   Thu, 1 Apr 2010 00:08:33 -0700 (PDT)

--- On Thu, 1/4/10, Stephen O Neill wrote:
> I am trying to estimate average partial effects after
> xtprobit. When I use margins, dydx(*) after probit, I get
> average marginal effects ok, however when I try to use
> margins, dydx(*) again after xtprobit ..., re margins just
> returns the original coefficients rather than average
> partial effects. I find a simliar problem after xttobit. Can
> somebody clairfy why this is? 

Because -margins- will take the default prediction if you don't 
specify what kind of dependent variable you want to consider 
(using the -predict()- option inside -margins-). Look at
-help xtprobit postestimation##predict- to see what those defaults

Hope this helps,

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


*   For searches and help try:

© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index