Good morning,
My name is Monica Lanzoni and I'm a statistician. I work at the National Cancer
Institute of Milan (Italy).
I hope you'll understand my English and I apologize to you.
I have a problem using S fitting an epidemiological additive model.
The model is Ljk=Lj* + exp(a+xkß) L= death rate
I have to make the fit using GLM function changing link function and the error.
I know that using program GLIM I can built my own link and error functions as
macros. (see Breslow & Day - STATISTICAL METHODS IN CANCER RESEARCH, Vol.II,
pp.175)
I would like to make the same in S but all my tries to make a family object or
a link function were unsuccessful.
My colleague, Dr. Raffaella Artusi, sent a message to You last week for the
same problem; if someone of yours is trying to solve it we'll wait your answer
together.
Thank you very much.
Dr Monica Lanzoni
____________________________________________________________________
Get free e-mail and a permanent address at http://www.netaddress.com/?N=1
-----------------------------------------------------------------------
This message was distributed by s-news@wubios.wustl.edu. To unsubscribe
send e-mail to s-news-request@wubios.wustl.edu with the BODY of the
message: unsubscribe s-news
|