st: dynamic panel data model using Arellano-Bond.

["aha teddy" <ahatidy@hotmail.com>]

Hello,

I got a problem with Stata 8 when I estimate a dynamci panel data model 
using Arellano-Bond.

here is the model:

Leverageb=c+(1-alpha)*lag(leverageb)+ c1*ndtsd +c2*profit+ c3*size+c4*tang+ 
c5*growthm  (1)

Where leverageb is the leverage ratio using book value,  lb is the 
lagged leverageb

In Stata 8, first, I generate a lagged variable, lb, for the leverageb, 
then I just specify lreveageb as the dependent variable, and independent 
variables are: ndtsd profit size tang growthm, and the instrument variables 
are: l2.lb, l2.ndtsd, l2.profit, l2.size, l2.tang, l2.growthm, then I click 
ok, is it right or not? 
The command shows:
xtabond leverageb tang profit size growthm ndtsd, lags(1) inst(l2.lb 
l2.profit l2.size l2.tang  l2.growthm l2.ndtsd) artests(2)

Am I right? I am really confused because I don't know whether the Stata 
will run the first difference and use the lag(2) of the lagged dependent 
variable(l2.lb) as instrument for me automaticially rather than I specify 
it (l2.lb).

Can anyone tell me about the sth about this? Thank you very much!

Bean

_________________________________________________________________
�����������ѽ��н�������ʹ�� MSN Messenger:  http://messenger.msn.com/cn  
*
*   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/