[S] about glim

Zhaorong Jiao (z.jiao@fsc.qut.edu.au)
Thu, 06 Aug 1998 16:25:23 +1000 (EST)


Hi, I am using the glim function to model some survival data. So in the
function I specify the parameter "error" to binomial, "link" to loglog. Am
I doing the right thing ? The program is ruming well. But how can I get
the estimated Y and what are the estimated Y ? Are they the estimated
survival values ? How can I get the estimated RR (relative risk) ? Looking
forward to your answer. Thank you in advance.
P.S. the data I am modelling are some grouped-survival data,i.e a survival
value is calculated for each of the conbinations between levels of
two factors, sex(two levels)
and age-group(4 levels, 0-39,40-54,55-69,and 70-99). Is any other way than
glim I can model this kind of data and calculate the RR ?

-----------------------------------------------------------------------
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