Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down at the end of May, and its replacement, statalist.org is already up and running.


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

RE: st: Regression diagnostics with panel data (-xtreg-)


From   "Tobias Pfaff" <tobias.pfaff@uni-muenster.de>
To   <statalist@hsphsun2.harvard.edu>
Subject   RE: st: Regression diagnostics with panel data (-xtreg-)
Date   Tue, 30 Aug 2011 12:12:11 +0200

Dear all,

I guess my original email was a bit too long, so I will sum up my questions
regarding regression diagnostics after fixed effects (-xtreg, fe-):


1.) How can you identify influential observations after a fixed effects
panel regression? Is it OK to use -regress- with the same equation and do
the diagnostics with DFITS etc. (as suggested here:
http://www.stata.com/statalist/archive/2006-05/msg00075.html)?

2.) -predict- after -xtreg- calculates either u_i (fixed-error component) or
e_it (overall error component). Concerning the assumption of normality of
residuals, is it correct that u_i needs to be checked for normality?

3.) I understand that the RESET (-ovtest-) after -regress- is a test for the
functional form, but not for omitted or irrelevant variables. Is there a
graphical or formal test for omitted or irrelevant variables after -xtreg-
then?


My panel data set is unbalanced, covers 26 years, 40,000 individuals and
315,000 observations. Standard errors are clustered for region*year (-xtreg
..., fe vce(cluster region_svyyear)). I use Stata SE 11.2.

Any comments & help is appreciated!

Thanks,
Tobias

*
*   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   |   Site index