On Aug 15, 2010, at 10:52 AM, paaventhan jeyaganth wrote:
Dear all,
when i do the calibration plot,
Not a well defined operation ....
i put the x label y label , there is
some labels are i did not put it , like "resample optimism
added ..." i
want to get rid of the these label , is any body know how can i get
rid of these label.
Jumping ahead these didn't turn out to be "labels" but rather
"subtitles". "Labels" generally refer to the text that are associated
with tick marks.
these are the following command i used
Presumably f is a fit object of some sort ....
cal <- calibrate(f, u=12, method=c("boot"), B=100,m=70, data=a1)
plot(cal,xlab="Predicted Survival", ylab="Actual Survival")
Next time you post you should indicate:
-- what packages and version you are using.
-- what code you used to create the object on which you are working
-- a small example to create something like the object
Guessing that you were using something similar to the rms/Hmisc
combination, I ran the first example in ?cph and then offered it to
calibrate and plot. I then did:
> class(cal)
[1] "calibrate"
> methods(plot) # turns out that plot.calibrate is visible so
getAnywhere was not needed
> plot.calibrate
... and looked at the code. There is a section where the value for
"subtitles" is checked before creating the annotations in question.
Try:
plot(cal,xlab="Predicted Survival", ylab="Actual Survival",
subtitles=FALSE)
I was then going to criticize my own behavior and say that I _should_
have looked at the documentation first but when I did I did not
initially find the subtitles argument documented in the listing of
arguments, but I did eventually see it mentioned in the Usage section
for the function plot.calibrate.
--
David.
David Winsemius, MD
West Hartford, CT
______________________________________________
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.
