st: AW: mfx & postfile

["Martin Weiss" <martin.weiss1@gmx.de>]

<> 

I think you would be much better off with a specialized tool such as -ssc d estout-. But still:

*************
sysuse auto, clear
probit foreign length weight, nolog
mfx
mat point=e(Xmfx_dydx)
mat se=e(Xmfx_se_dydx)
di point[1,1]
di point[1,2]
di se[1,1]
di se[1,2]
*************



HTH
Martin


-----Ursprüngliche Nachricht-----
Von: owner-statalist@hsphsun2.harvard.edu [mailto:owner-statalist@hsphsun2.harvard.edu] Im Auftrag von Dimitri Szerman
Gesendet: Montag, 8. März 2010 14:58
An: statalist@hsphsun2.harvard.edu
Betreff: st: mfx & postfile

Hello,
I am trying to run many probit regressions and post the marginal
effects/standard errors to a new file. Here's what I am (within a
loop) trying to do:
/****************************************/
postfile `temname' mex1 mex2 sex1 sex2 using myfile.dta, replace

probit y x1 x2
mfx

post `temname' $exp
postclose `temname'
/****************************************/
My question is: what should be in Sexp? mfx returns matrices
e(Xmfx_dydx) and e(Xmfx_se_dydx) with the marginal effects and
standard errors. I don't know how to access them in this context. For
example, if instead I was using
/***************/
regress y x1 x2
/***************/
then $exp would simply be
/***************/
global $exp (_b[x1]) (_b[x2]) (_se[x1]) (_se[x2])
/***************/
but with mfx (or margin) I can't access the marginal effects/std
errors so easily.
I could also use margins, as I am running Stata 11. Any help is much
appreciated.
Thanks,
Dimitri

*
*   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/


*
*   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/