dear everybody,
it is paradox; I have a (panel) data set (which is correctly tsset)
with 6 observations on y(i) (1, ... 6) and 5 observations on x(i) (2 ...
6).
the results are completely differnt for "xtabond y x" and
"xtabond y x if obs>2" (obs is a variable indicating time).
This is the more surprising as the outpout (correctly) indicates he
use of 4 (time) observations in both cases. Also, the relevant
information in "est list" is identical in both cases (Ti,t_max, t_min).
Can anyone explain this strange results to me?
Thanks a lot,
Best regards
Harald
A further hint: the results are identical for "xtabond y, pre(x)" and
"xtabond y if obs>2, pre(x)"
*
* 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/
