Statlisters,
First time for me using this list serve.� Hope you can guide me with my following concern.
I am estimating a panel data model that is best described as being of the form,
y(t) = b0 + b1*x + b2*(y(t-1) - z)/q
across 250 cross sectional units each of which has data observed over a 6-year time frame.
I want to approach with xtabond or xtivreg,fd....my question is since my right-hand side variable is not simply the lagged dependent variable, y(t-1) but rather a variable that contains y(t-1), e.g., (y(t-1) - x)/q, what is the preferred approach? Can xtabond and xtivreg deal with that situation and provide with robust standard errors?
Thanks.
*
* 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/
