Re: st: computing correct marginal effect in xtlogit model

[Richard Williams <richardwilliams.ndu@gmail.com>]

At 04:03 PM 10/25/2011, ramesh wrote:
> Hello,
> I am using xtlogit model with an interaction term (e.g., y=
> b0+b1.x1+b2.x1*x1+b3.x3). I want to compute the marginal effect of 'x1'.
> However stata 'mfx compute, predict(pu0)' code treated 'x1' and 'x1*x1' as
> two separate variables (in fact they are not) and gives two marginal effect
> (marginal effect of 'x1', 'x1*x1'). I want to find the correct marginal
> effect of variable 'x1'. Is there any way to to do this in stata?
>
> Thanking in advance for your kind response!
> Ramesh
If you have Stata 11 or higher, use the -margins- command. Assuming 
x1 is continuous, The command will be something like
xtlogit y x1 c.x1#c.x1

followed by the margins command. If you aren't familiar with margins, 
my notes on this are at http://www.nd.edu/~rwilliam/xsoc73994/Margins01.pdf .

-------------------------------------------
Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
HOME:   (574)289-5227
EMAIL:  Richard.A.Williams.5@ND.Edu
WWW:    http://www.nd.edu/~rwilliam

*
*   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/