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: RE:RE: AW: marginal effects after ssm command

From   "Arantza Ugidos" <>
To   <>
Subject   RE: st: RE:RE: AW: marginal effects after ssm command
Date   Tue, 23 Feb 2010 17:13:40 +0100

Thanks Marteen for your help, we are on it.


-----Mensaje original-----
De: [] En nombre de Maarten buis
Enviado el: lunes, 15 de febrero de 2010 14:02
Asunto: Re: st: RE:RE: AW: marginal effects after ssm command

--- On Mon, 15/2/10, Arantza Ugidos wrote:
> We do not know where the error may be. With other commands
> mfx works fine. But after ssm it does not return marginal
> effects but the estimated coefficients again. 

-mfx- looks at the default -predict- function that is 
associated with a command, which should be left behind in
e(predict). If e(predict) is empty then -mfx- looks by default
at the change in the linear prediction, which is what you 
found. Since -ssm- is a wrapper for -gllamm- the authors 
apperently did not think it would be a good idea to provide
such a predict function. Instead, they say in the help file:
"-gllamm- itself should be used to extend the model and for 
prediction and simulation using -gllapred- or -gllasim-". 
The problem is that -mfx- won't work with -gllapred-, so 
you'll probably need to derive the marginal effects yourself.

Hope this helps,

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


*   For searches and help try:

*   For searches and help try:

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