 |
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
st: RE: Poisson Rates
I think the best way is to note that a rate is m/exposure. A Poisson
model fits log(m)=log(exposure)+XB, so you only need to use the offset
feature in Stata. The command will be
poisson y xvariables, exposure(exposure)
If you use offset, you first need to take ln(exposure)=lex
poisson y xvariables,offset(lex)
Tony
Peter A. Lachenbruch
Department of Public Health
Oregon State University
Corvallis, OR 97330
Phone: 541-737-3832
FAX: 541-737-4001
-----Original Message-----
From: [email protected]
[mailto:[email protected]] On Behalf Of
[email protected]
Sent: Monday, January 12, 2009 12:01 PM
To: [email protected]
Subject: st: Poisson Rates
I created a poisson model with the number of injuries as the depedent
variable and age, experience and age*experience as the predictors.
Age and experience are categorical variables. We have a lot of people
with the similar ages and experience levels so I'm categorizing age
and experience into 1 year intervals.
My outcome is then the number injuries predicted for each of these
age/experience groups.
I'm first plotting experience vs the number of predicted injuries by
various 1-year age categories.
In order to turn the y-axis (counts) into rates can I divide each of
these 1-year experience groups by the number of hours worked for that
1-year experience group?
Thanks for your help.
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/