Hello,
I need some help in understanding xtabond. Here is my model:
Y_{it}=aY_{it-1}+bX_{t-1}+u_i+w_t+v_{it}, where X_{t-1} is predetermined.
To estimate this model using xtabond, I construct my sample as putting
y_t and x_{t-1} in the same row and then run
xtabond Y yr*, pre(X)
Can anyone tell me whether this is the right way to estimate the
model? Should I construct my in the way that have y_t and x_{t-1} in
the same row? I did this because xtabond does not allow "l.X" in pre(
). If this is a wrong practice, please suggest a right one.
Your help is appreciated,
Caro
*
* 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/
