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: Two way fixed effect model - constant term


From   David Ashcraft <[email protected]>
To   "[email protected]" <[email protected]>
Subject   st: Two way fixed effect model - constant term
Date   Tue, 2 Apr 2013 05:00:15 -0700 (PDT)

Dear Statalist,

(I have posted a similar message previously during the Easter holidays and thought may be, this time, it will get some attention)

I am trying to run a 'two way fixed effect least square regression' on a sample of firms from several different countries. One firm is showing only in one country. I have read the following article aside from the help files of several routines mentioned in this article;

http://myweb.fsu.edu/tsass/Papers/Review%20of%20Stata%20Routines%20for%20Fixed%20Effects%20Estimation.pdf


now I am a little confused, in simple terms, I want to run a two level model where firm's performance is affected by several micro variables and one macro variable calculated from Country level data. This include several macroeconomic variables such as interest rates, gdp, unemployment rates. I thought of using -xtivreg- with country as instrument variable.However -xtivreg2- consider fixed effect only on firm level data or the country level data based on how you define your model. I find it more appealing to use -felsdvregdm-  or -gpreg-. Both commands do not provide coefficient of constant. And also do not report separately the coefficients for country equation. Can somebody tell me, how can I get the estimation of both level as well as constants?
Regards

David


*
*   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