Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: xtivreg, fe , multiple reg with interaction effects


From   Stas Kolenikov <skolenik@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: xtivreg, fe , multiple reg with interaction effects
Date   Wed, 3 Nov 2004 12:34:28 -0500

> 1. Sorry, my question wasn't spelled out correctly.
> The models I need to implement are the following:
> 
> 1) Y = const + Z*betta + time_effects*theta + u
> 2) Y = const + Z*betta + time_effects*theta +
> time_effects*Fixed effects*delta + u

Are your time effects actually a variable like year? At any rate, I
don't think that this thing is easily estimable, because you don't
have fixed effects to generate your interaction terms. You can try
this out within the random effect framework with -gllamm-.

> Below is the output. When doing usual OLS fixed
> effects regression, only two of the coefficients are
> insignificant. In 2SLS regression results look ok, but
> in 2SLS with fixed effects significance of all
> coefficients dies out (z-statistics are around zero).

Still no output, but I would suspect that this is a matter of
inefficient estimation: both fixed effect and IV regressions, in
general, lead to inefficient estimates compared to OLS, so you should
not be surprised to see vast standard errors.

-- 
Stas Kolenikov
http://stas.kolenikov.name
*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   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