Thanks! I must admit that I had tried using mfx (I'm using Stata 10). The problem is that I'm having difficulties getting Stata to recognize the lincom result as the coefficient I'd like the marginal effect for. I've tried adding the lincom result as a scalar, but I get an error message indicating that too few variables are specified. If there's no option outside mfx, what's the best way to get Stata to recognize what it needs to generate the marginal effect for?
Thanks again,
Melanee
________________________________________
From: [email protected] [[email protected]] On Behalf Of Maarten buis [[email protected]]
Sent: January 21, 2010 12:53 PM
To: [email protected]
Subject: Re: st: dprobit and lincom
--- On Thu, 21/1/10, Melanee Thomas wrote:
> I have a question about dprobit and lincom. Specifically,
> when I run lincom after dprobit, the returned lincom result
> is a probit coefficient, rather than the dF/dx reported by
> dprobit. Is there an option I can use to transform the
> probit coefficient returned by lincom to the dF/dx reported
> by dprobit?
Depending on your version of Stata -mfx- (< 11) or -margins-
(11).
> Stated differently, is there a way to get lincom
> to deliver an unexponentiated result?
This is a common misunderstanding, the exponentiated coeficients
are only meaningful after -logit- but not after -probit-. So,
-dprobit- doesn't exponentiate coefficients.
Hope this helps,
Maarten
--------------------------
Maarten L. Buis
Institut fuer Soziologie
Universitaet Tuebingen
Wilhelmstrasse 36
72074 Tuebingen
Germany
http://www.maartenbuis.nl
--------------------------
*
* 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/