Bookmark and Share

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: Marginal effects after xtprobit


From   Elin Vimefall <Elin.Vimefall@oru.se>
To   "statalist@hsphsun2.harvard.edu" <statalist@hsphsun2.harvard.edu>
Subject   st: Marginal effects after xtprobit
Date   Wed, 2 Oct 2013 07:15:10 +0000

Hi

I'm interested in why some children start school and I analyze this with a probit model. 
Since I believe that there are unobserved characteristics at district level casing the error terms to be correlated I use cluster for the error term.
My model looks like this:

probit School x1 x2, cluster(district)

However now I instead use the panel setting like this

Xtset district

Xtprobit school x1 x2

The result is similar with some changes in significance.

However, when I calculate the marginal effects using

margins dydx(*)

the magnitude if the marginal effects in the panel setting becomes approximately 10 times larger than the marginal effects after the normal probit. 
Can someone help me explain why?


//Elin Vimefall


*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index