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

st: Out-of-sample results OLS vs. GMM


From   "Niko Wrede" <wrede@wiso.uni-koeln.de>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: Out-of-sample results OLS vs. GMM
Date   Fri, 16 Sep 2005 10:57:51 +0200

Dear all,

This question is more related to research than to STATA. However, since many
STATALISTER are familar with xtabond2-related research maybe somebody can
help me.

Comparing OLS and GMM after out-of-sample prediction for a dynamic model, my
result is, that prediction based on OLS dominates the prediction based on
GMM. This result surprised me, since the OLS estimator is biased in a
dynamic setting if residuals are autocorrelated.

However, empirical work usually only compares the data fit of OLS and GMM
based on in-sample estimation (see Arellano/Bond for instance). I could not
find empirical results on out-of-sample results.

My question is: Can anybody cite me some sources that deal with
out-of-sample prediction comparison based on OLS and GMM estimator?

Thanks in advance
Niko


*
*   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