A Stata user just informed me that the glm command has a problem. I want to
advise you of how to avoid the problem until it gets fixed.
The help file shows that one can use the "exposure()" option with the glm
command. You cannot. There is no problem with the "offset()" command. The
correct option is "lnoffset()" when you want to have the glm program itself log
the offset variable. The following commands provide the same table of estimates:
poisson yvar xvars, exposure(off)
glm yvar xvars, lnoffset(off)
I have notified Stata so that the help file can be changed to reflect the
correct option name.
Joe Hilbe
*
* 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/
