If I forget the panel/dynamic nature of your data, your problem recall me of mixed models (-xtmixed- and -gllamm- from ssc).
Nicola
At 02.33 17/01/2008 -0500, you wrote:
>Hi friends. I am hoping I could bother you all with an eocnometrics question
>that has been stumping me.
>
>I am running an estimating equation of the following form in stata:
>
>Yist = Yist-1 + Zist + Xst + error
>
>To estimate this dynamic equation on a panel with short T, I use the
>Arellano-Bond technique (xtabond2). However, my variables of interest
>are the Xs and they are aggregared at the sector level (while other
>variables are
>at the micro, firm level) so there is the possibility that the
>standard errors on the Xs are over-precise. However, there is no easy
>way to combine clustering with Arellano-Bond in stata. I was wondering
>if you could offer a way around this problem...? Thanks very much!
>
>Guru Sethupathy
>
>- --
>Prasanna (Guru) Sethupathy
>Economics, Ph.D.
>Columbia University
>[email protected]
*
* 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/
