I am using Stata to estimate dynamic panel data regression. I was using stata 9 which has xtbond2 command but now I am using stata 12 which does not have xtabond2 command instead it has xtabond command. How can I use xtabond command instead of xtabond2 command?
xtbond2 is a user-written programme (by David Roodman). It can be downloaded - like other user-written programmes - from within Stata.
Geoffrey is correct. You can install the package with {ssc install xtabond2} and then view the documentation with {help xtabond2}.
The package and documentation are also at http://ideas.repec.org/c/boc/bocode/s435901.html
Where a short answer to your question is found:
" The original estimator is sometimes called "difference GMM," and the augmented one, "system GMM." Bond (2002) is a good introduction to these estimators and their use. xtabond2 implements both estimators. As GMM estimators, the Arellano-Bond estimators have one- and two-step variants. But though asymptotically more efficient, the two-step estimates of the standard errors tend to be severely downward biased (Arellano and Bond 1991; Blundell and Bond 1998). To compensate, xtabond2, unlike xtabond, makes available a finite-sample correction to the two-step covariance matrix derived by Windmeijer (2000). This can make twostep robust more efficient than onestep robust, especially for system GMM. Note: the routine requires an up-to-date version of Stata 7 (with the 21jun2002 update installed). Users of Stata version 10 (25feb2008 update) or later can take advantage of speed improvements due to Mata."
A corporate finance paper that demonstrates an application of xtabond2 is Wintoki, Linck, and Netter (2012)
http://www.sciencedirect.com/science/article/pii/S0304405X12000426
One important benefit from running Roodman's GMM xtabond2 over xtabond is that it addresses the instrument proliferation problem especially when using the "collapse option" in STATA. Ofcourse, the validity of intruments should be checked using Sargan and/or Hansen tests in both cases.
Xtabond2, unlike xtabond, makes available a finite-sample correction to the two-step covariance matrix derived by Windmeijer (2000). This can make two-step robust more efficient than one-step robust, especially for system GMM.
- Badges
- Science topic
- Similar topics
- Correction