Statalist


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

st: Re: 3SLS and fixed effects


From   mmolina@uniroma3.it
To   statalist@hsphsun2.harvard.edu
Subject   st: Re: 3SLS and fixed effects
Date   Thu, 23 Jul 2009 17:13:24 +0200 (CEST)

Dear Statlist,
After adding the sector dummies I have problems of endogeneity.
Should I suppose that this fact invalidate the model? Or should I conclude
that I need more information to control for sector effects?
Is it better to work with other command tha reg3?
Thanks again



Nothing stops you from creating the dummies and adding them to the
regression, especially as you only have 8 (or 7) of them...


Kit Baum   |   Boston College Economics & DIW Berlin   |  
http://ideas.repec.org/e/pba1.html

An Introduction to Stata Programming |
http://www.stata-press.com/books/isp.html
   An Introduction to Modern Econometrics Using Stata  |  
http://www.stata-press.com/books/imeus.html



On Jul 10, 2009, at 02:33 , Alejandra wrote:


I am hoping someone can help me. I would like to perform 3SLS on

cross-section data. I wish to obtain fixed effects estimates. I need to
controll the sector's effect (8 dummies, one for each sector).

TI = b0 +  b1 FE + b2 TR EMPLOYEES + b3 AGE + b4 JOINT FOREIGN+  b5
IN-HOUSE+ b6 EXPORT SHARE+ è Sectors? Dummies
EXSH = b0 + b1 TI+ b2 TRAINED +  b3 SKILED + b4 SIZE +b5 IN HOUSE + b6
JOINT FOREIGN


The Reg3 command in Stata does not appear to allow this. Could you please
give some advice?






*
*   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   |   What's new   |   Site index