Hi!
well I found the solution, times from my data are generated by a Gompertz
distribution and have a lots of decimals. When they go through the survfit
function times returned by survfit have only 13 decimals so when my times
are compared to those ones it leads to false.
That's it... so simple.
For the coxphw coming from coxphw package, it seems to be more complicated
because something is cutting off more decimals but I have time that differs
in the first 5 decimals so I can't round them without loosing information. I
will write to the author's of coxphw to see if he have any suggestions.
Thank you again,
Héloïse
2010/4/28 Terry Therneau <thern...@mayo.edu>
> Your problem appears to be with coxphw, not coxph. I have never before
> heard of the coxphw function; you should identify what package it is
> from in your request, and perhaps also contact the author. If you have
> found a similar issue in survfit I would be glad to see an example.
>
> Terry Therneau
> (author of coxph and survfit)
>
>
>
[[alternative HTML version deleted]]
______________________________________________
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
