I have just created a Stata command to perform the Arellano-Bond (1991) autocorrelation test. It is called abar, and can be downloaded from the Statistical Software Components archive, for example by typing "net search abar" in Stata. It is designed to work in Stata 7 and Stata 8.
The Arellano-Bond (1991) test was originally proposed for a particular linear Generalized Method of Moments dynamic panel data estimator, but is quite general in its applicability--more general than dwstat, durbina, bgodfrey, and xtserial. It can be applied to linear GMM regressions in general, and thus to ordinary least squares (OLS) and two-stage least-squares (2SLS) regressions, which can be seen as special cases of linear GMM. It is appropriate for both time-series and cross-section time-series (panel) regressions. It can also be made consistent in the presence of various patterns of error covariance. Specifically, abar will run after regress, ivreg, ivreg2, and ivreg2, gmm in their "plain" (homoskedastic), robust, and cluster variants. It will also run after newey and newey2. It does assume that regressors are not "post-determined," i.e., not correlated with future errors (a situation that can arise after a mean-deviations transformation for fixed effects regressions).
For more, see the help file. Comments welcome.
David Roodman
Research Fellow
Center for Global Development
1776 Massachusetts Ave. NW
Suite 301
Washington, DC 20036
[email protected]
202-416-0723
fax: 413-410-2602
*
* 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/
