I have a question regarding the cenpois routine for Stata. It works
well with right censoring value above 2. However, if observations are
either 0 or 1+ (i.e., right censoring at 1) I get the error message
"cnpoislf does not compute a continuous nonconstant function; could not
compute numerical derivatives".
Has anyone encountered this before? How can I fix this problem? For me,
the
right censored at one model is a very interesting case since it forms
the input for hurdle Poisson models, and it would be very nice if I
could estimate such a model in Stata.
Any comments are greatly appreciated.
Rainer Winkelmann
*
* 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/
