Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down at the end of May, and its replacement, statalist.org is already up and running.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: Thread-Index: AQHMtFo+KNDs77p3gESnnog4xmJOSQ==


From   Luca Fumarco <luca.fumarco@lnu.se>
To   "statalist@hsphsun2.harvard.edu" <statalist@hsphsun2.harvard.edu>
Subject   st: Thread-Index: AQHMtFo+KNDs77p3gESnnog4xmJOSQ==
Date   Tue, 6 Dec 2011 22:01:38 +0100

Dear Statalisters

I have found the answer, and I share it with you (..maybe you still have some relevant comments on it):
Let's say, as by previous literature, that the Var(e)=[exp(Z'*gamma)]^2

hetprob y B1x1 B2x2 B3x3, het(x1)  [with het(.) I hypothesize the variance volatility is given by x1]
mehetprob [I get the lnsigma2 of x1, that is the estimate of gamma1]

then the mfx1=p(Y=1)*[ B^k - ZBwk]/[exp(gamma1*x1)]

If x1 is a dummy var, then:
-> the id for which x1=0 we have sigma=1
-> the id for which x1=1 we have sigma=exp(gamma1*x1)

you can check your result with the postestimation command:
predict sigmahat, sigma


Luca Fumarco

Ph.D. Student
Linnæus University

*
*   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/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index