st: The use of (time) dummies in a dynamic system GMM framework, usingxtabond2

[Joost Vandewege <joost.vandewege@ugent.be>]

Dear stata-user,

Can you tell me what is the right way to include time dummies, or 
dummies in general when using the xtabond2 command?  The difference 
equation cannot deal with normal dummies, while the level equation does 
need normal (0-1) dummies. I have tried to replicate DPD98-output (where 
there is an option to 'use time dummies') with identical datasets by 
including the dummies as they are (0 or 1)for the level equation, and by 
including a transformed dummy series (that becomes the normal dummy 
series after taking first differences) for the difference equation.
However, this does not lead to the required results, and replication of 
DPD-co�fficients seems impossible.  I know that standard errors are not 
comparable between stata and DPD, because Stata uses Windmeijer 
correction, but the replication of the coefficients themselves ought to 
be possible.  However, I can't seem to succeed.

Thus; in one sentence: how does one correctly enter dummy variables with 
the xtabond2 command? What should those dummies look like?

Kind Regards,

Joost.

--
Joost vandewege
Department of Social Economics
Faculty of Economics and Business Administration
Hoveniersberg 24
9000 Gent
Belgium
phone: +32 (0)92647877
joost.vandewege@UGent.be


*
*   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/