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

st: tsset error in panel estimation


From   armen@uni-hohenheim.de
To   statalist@hsphsun2.harvard.edu
Subject   st: tsset error in panel estimation
Date   Fri, 25 Feb 2005 17:10:08 +0100

Dear all,

I have a balanced panel data. I used xtgls with heteroscedasticity and psar1 
options specifying first iis district and tis year. That worked perfectly.
However, when I went estimating my model with Beck and Katz's panel-corrected 
standard errors, i.e. applied xtpcse I got an error message saying I have to 
tsset! The same occurs when I try to test for cross-district correlation and 
for homoscadsticity using xttest2 and xttest3 respectively?!

What am I doing wrong? 

Using the opportunity may be a two more questions? 

I would like namely to calculate elasticities. Does that work for panel 
(N=235, T=29) the usual way with mfx, eyex?

Finally, what I assume with my IVs that one or two are actually endogenous.
I would have applied 3SLS in a "normal" (non-panel) setting to address 
endogeniety. Is there any way to do "3SLS" for xt? I could not find anything 
like that in the literature. May be that is too dumn what I think?
Actually, intuitively I think I take would-be-3sls structure, estimate each of 
them SEPARATELY with xt (the first equation being the principal) and then put 
the results next to each other and treat them as a "real" 3SLS. Figuring out 
elasticities I make a distinction in so-called direct and indirect effects of 
my RHS variables on the main DV?!!

Any hint will be much appreciated. 

Thanks in advance.

Armen
Doctorate student
University of Hohenheim
Germany

*
*   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