Raiqah Kamil wrote:
I am trying to estimate the producer specific
technical efficiency (time invariant) using a
firmlevel panel data. When I use the "xtfrontier"
command as outlined in the help, stata is returning an
error:
no observations
I haven't worked with the panels earlier. Can anyone
suggest what is the nature of problem here? I would
appreciate any help on this.
--------------------------------------------------------------------------------
I don't know anything about frontier models or how to use -xtfrontier-, but
that same error message appears whenever I forget to -encode- string
variables before using -anova-.
Are any of your variables string ? (For example, categories for a
predictor.) If so, then try -encode- (or -destring-, if appropriate) to see
if this helps.
Joseph Coveney
. use http://www.stata-press.com/data/r9/xtfrontier1.dta, clear
. xtfrontier lnwidgets lnworkers lnmachines, i(id) t(t) tvd nolog
[successfully fit--output deleted]
. tostring lnwidgets, replace force
lnwidgets was float now str12
lnwidgets was forced to string; some loss of information
. xtfrontier lnwidgets lnworkers lnmachines, i(id) t(t) tvd nolog
no observations
r(2000);
*
* 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/
