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: Cnreg with fixed effect


From   Milet Emmanuel <emmanuel.milet@cepii.fr>
To   statalist@hsphsun2.harvard.edu
Subject   st: Cnreg with fixed effect
Date   Mon, 31 Jan 2011 14:50:51 +0100

Dear Stata users,

I intend to run a Cnreg estimation with fixed effect. The routine on Stata does not include any fixed effect option, so I add them one by one. I have a panel with many dimensions (year*country*firm*product) and my censoring variable is year*country*product specific.

I estimate exports (at the year*country*firm*product level) using GDP, Distance, Population, etc...

I replace all the zero flows by the smallest amount exported to a givern country for a given product a given year. So in the end, my export variable is both firm-specific and has some observations that are year*country*nef specific.

My problem is that the procedure takes too much time to run (when I include all the fixed effects, there are almost 8000). I am looking for a way to transform my variables in order to get rid of the fixed effect (like substracting the mean if I were running an xtreg with 2 dimensions). This cannot work here however, since my censoring variable is not firm-specific.


E.Milet
University Paris 1
Paris, France
*
*   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 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index