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

st: xtivreg and instruments in levels


From   "Pedro Martins" <P.Martins@warwick.ac.uk>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: xtivreg and instruments in levels
Date   Wed, 04 Aug 2004 18:44:44 +0100

Hi

I would like to estimate an equation in differences using xtivreg:

Yit = a.Xit + Di + Eit, in which Xit is instrumented by Iit

My concern is that my instrument may only work in levels, in the sense that Xit or even dXit are correlated with Iit but not with dIit. 

However, unless I transform the instrument in some appropriate way, it will be used as in differences by xtivreg, i.e. the first step will be about a regression of dXit on DIit, which doesn't necessarily make sense under my economic model.

Any comments/suggestions would be greatly appreciated. Thank you.

Pedro Martins



****************************************************
Pedro Martins
Department of Economics
University of Warwick
Coventry CV4 7AL
United Kingdom

Tel: +44/0 24765 23935
Fax: +44/0 24765 23032
Email: p.martins@warwick.ac.uk
Web: www.warwick.ac.uk/staff/P.Martins
*****************************************************

*
*   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