I'm working with xtbond in SE 8.0 and need to estimate a regression on
defrd0 but only using a two year lag. My data is a little weird in that
from 1997-2001 it I have observations for every year. Prior to 1997, I only
have observations for every other year. When using the following command:
xtabond defrd0 pi, lags(2) noconst
the one year and two year lags for defrd0 appear. Since that limits my
estimation to data occuring from 1998-2001 I'm severely limiting my
analysis. Does anyone know how I might write the command so that only the
two year lag term and pi show up as the independent variables?
As an aside, does anyone know of a basic level explanation of the benefits
to using xtabond2 v. xtabond?
Thanks for the help,
Kevin Christensen
*
* 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/