Hello,
I have a count of individuals' patents over a 5 year span in a ZINB model.
Some people have shorter exposure time (i.e., graduated less than 5 years
ago) and I adjust for this using STATA's exposure option, where exposure=5
if people graduated more than 4 years ago and exposure=time since graduation
if they worked for less than 5 years. I think that should work.
However, time since graduation is also an important control variable in the
regression. If I add it as a RHS variable into the regression (simple count
of years and its square), is the exposure adjustment still correct? And
should the variable counting years since graduation be interpreted
differently since part of it (the first 5 years) is also included in the
exposure adjustment?
Thanks!
Henry
*
* 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/
