I don't understand the reluctance, but it can be done. Something like
sysuse auto, clear
bysort foreign rep78 : gen count = _N
bysort foreign rep78 : gen tag = _n == 1
poisson count i.foreign i.rep78 if tag
Nick
On Thu, Jan 24, 2013 at 4:05 PM, Ronald McDowell
<McDowell-R3@email.ulster.ac.uk> wrote:
> I'm looking to fit a loglinear model to a 2x2 contingency table using the glm/poisson/log command/options. I don't want to collapse the data into the cell frequencies but retain all data at the individual level. How do I get started? For some reason I'm having a blank today.
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/faqs/resources/statalist-faq/
* http://www.ats.ucla.edu/stat/stata/
