A comment for StataCorp. When one runs a DPD regression via -xtabond-, e.g.
xtabond yvar xvar1 xvar2 ..., ...
shouldn't `e(depvar)' interpolate to D.yvar instead of yvar since the
equation is in fact estimated in differences? I am raising this simply in
the interest of consistency with the way other eclass estimators save their
results. Similarly, shouldn't the coefficient table show D.yvar in the
top-left corner?
NB: I am still using Stata 7. This might have been addressed in the latest
release.
Patrick Joly
[email protected]
[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/
