Statalist


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

st: xtdpd, heterogeneous coefficients, time-variant heterogeneity


From   Pandaros@gmx.de
To   statalist@hsphsun2.harvard.edu
Subject   st: xtdpd, heterogeneous coefficients, time-variant heterogeneity
Date   Thu, 19 Feb 2009 15:19:20 +0100

Hello everybody,

I have a balanced panel of 19 countries over 24 time periods. The model is

	g_it= ß_0+δg_(it-1)+ß_1 x_it+ε_it

Now the relationship of g_it,  and x_it is only constant conditional on the country specific time-variant effect μ_it, which is unobserved. μ_it however has no other partial correlation with LHS variable g_it, except through the regressor x_it. Then the coefficients are heterogeneous across the countries. My question is twofold:

Then the system GMM estimator (xtdpd) will deliver an consistent estimation result of ß_1 conditioned on the sample average of μ_it. Is that right?

What can I do to obtain an unconditioned estimate (pure estimate?!) of ß_1, without controlling for the unobserved time-variant effect μ_it?

And perhaps another small question: Is this a case of endogeneity, even though there is no partial relationship between g_it and  μ_it, except through x_it.

Hope you can help me.
Thank you in advance

Markus Baumgarten

-- 
Jetzt 1 Monat kostenlos! GMX FreeDSL - Telefonanschluss + DSL 
für nur 17,95 Euro/mtl.!* http://dsl.gmx.de/?ac=OM.AD.PD003K11308T4569a
*
*   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