Statalist The Stata Listserver


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: RE: Marginal effects in logit of unbalanced panel, re


From   "Scott Merryman" <smerryman@kc.rr.com>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: RE: Marginal effects in logit of unbalanced panel, re
Date   Tue, 29 Aug 2006 21:30:12 -0500

Take a look at [R] mfx or -help mfx-.  From the help file:

"Exactly what mfx can calculate is determined by the previous estimation
command and the predict(predict_option) option."

The default predict_option for -xtlogit- is the linear prediction.  I think
you want: 

-mfx, predict(pu0)-


Scott

> -----Original Message-----
> From: owner-statalist@hsphsun2.harvard.edu [mailto:owner-
> statalist@hsphsun2.harvard.edu] On Behalf Of Rilind Kabashi
> Sent: Tuesday, August 29, 2006 7:04 PM
> To: statalist@hsphsun2.harvard.edu
> Subject: st: Marginal effects in logit of unbalanced panel, re
> 
> Hi everyone,
> 
> I am new in using Stata, so apologies if the question
> seems too elementary.
> I am running logit on an unbalanced panel with random
> effects. I calculated the coefficients. I am
> interested in calculating marginal effects. However,
> when I type the mfx command, what I get is a linear
> prediction: in the column dy/dx the same coefficients
> are returned (as with xtlogit command), and one column
> is added with mean variable values.
> So, could please someone tell me how to calculate
> marginal effects in a logit model of unbalanced panel
> with random effects? Is there any command to do this
> in Stata, or do I need to do it manually? Or maybe
> marginal effects are not possible with an unbalanced
> panel random effects logit model?
> Thanks very much.
> 
> Regards,
> 
> Rilind
> 


*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   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   |   What's new   |   Site index