Statalist The Stata Listserver


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: Q. xtabond "goodness of fit"


From   "Noel Campbell" <NCampbell@uca.edu>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: Q. xtabond "goodness of fit"
Date   Tue, 07 Nov 2006 14:52:58 -0600

Caveat 1: A week ago, I didn't know the Arellano-Bond estimator existed,
now I'm trying to use it.
Caveat 2: I'm not much of a time series guy.  I haven't seen a VAR
since grad school.

Q. 1: I have two models with different specifications; they are
identical except in one I use "variable A" and in the other I use
"variable B."  Both appear to perform similarly, easily passing the Wald
test.  Is there a goodness of fit measure I can use to help me select
between the models?

Q. 2: The z-test on some of my estimates indicate AR(2),
which--according to the stata manuals--indicates my estimates are not
consistent.  Is there a way to "quantify" the inconsistency?  Better
yet, is there an accepted way to correct it?

Thanks to all in advance!

Noel

************
Noel D. Campbell
Assoc. Prof. Econ.
EFIRM
U. Central Arkansas
ncampbell@uca.edu
(501)852-7743

*
*   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