Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: Re: marginal effects for logit


From   May Boggess <mboggess@stata.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Re: marginal effects for logit
Date   08 Mar 2004 08:30:26 -0600

On Saturday, Amrita asked for advice on obtaining marginal effects after
-logit-. She is concerned that she may experience some of the problems
she has read about on Statalist, particularly after the recent mails
concerning -xtlogit-.

Amrita doesn't have anything to worry about when using -mfx- after
-logit-. 

First of all, she should find that -mfx- runs relatively quickly after
-logit-. (Running -mfx- after -mlogit- can take a long time because
-mlogit- is a multiple equation estimator and the number of coeficients
can be very large.) 

Second, no matter what prediction option she chooses after -logit-
(probably p), Amrita will not encounter any of the problems one can run
into after -xtlogit-. That is because -xtlogit- has some prediction
options that predict values that depend on the grouping variable, and
such functions are not suitable for obtaining marginal effects.   

--May

mmb@stata.com



*
*   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