Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
st: Thread-Index: AQHMtDMLhXavyASj7UeLS0V7f9Dsjw==
From
Luca Fumarco <[email protected]>
To
"[email protected]" <[email protected]>
Subject
st: Thread-Index: AQHMtDMLhXavyASj7UeLS0V7f9Dsjw==
Date
Tue, 6 Dec 2011 17:21:02 +0100
Hi Statalister,
I am having an interpretational issue with the hetprobit command.
After I run it, I obtain the estimates of the coeff. plus the estimate of lnsigma2 (which are the estimated gammas of the variable I typed in the het() option). Finally I command mehetprob (to find the mfx in the fastest way)
Now, following Cornelissen 2005, the marginal effect of x is as follows: mfx = [p(Y=1)*(B^k-XBgk)]/exp(Z'*gammals)
Now, how can I obtain the value of exp(Z'*gammas) from the lnsigma2?
Is it perhaps:
predict s, eq(lnsigma2)
replace s=exp(s/2)
Luca Fumarco
Ph.D. Student
Linnæus University
School of Business and Economics
Office: + 46470708410
Mobile: +46765879033
*
* 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/