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: [Fwd: Two-step Probit after merging]


From   mmolina@uniroma3.it
To   statalist@hsphsun2.harvard.edu
Subject   st: [Fwd: Two-step Probit after merging]
Date   Wed, 15 Sep 2010 13:27:55 +0200 (CEST)

Dear Statalist,

Thanks Marteen. Appart I agree that it depends on the nature of the data
but I was wondering that as the 2SIV and Newey¡¯s estimator do not
estimate ¥ä and ¥ë but rather

¥ä¥ñ = [1/(1-¥ñ©÷)¨ö]¥ä     and    ¥ë¥ñ = [1/(1-¥ñ©÷)¨ö] ¥ë

where ¥ñ is the correlation coefficient between ui and vi

and we assume that

¥íi = vi©¬ + ui. Because ui and vi are jointly normal, ¥íi is also normal

and I have a merged database of only two years (two observations for each
id) my concern is that I'm not controlling for the possible lack of
independence between the two observation.

Then my question is are these estimates necessarily biased?

Thanks a lot





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