On Nov 20, 2014, at 7:56 AM, Dewi VERNEREY wrote:
>
> Hi Franck,
>
> I am using the calibrate function from the package rms (4.2-1) with R
(3.1.2) in a Mac OS 10.10.1 environment .
That's the Yosemite platform. I'm running R 3.1.2 with the current CRAN
binaries (which were recently updated) and I get no error with the example in
the help page for `calibrate`. At the moment you example is not reproducible
since we do not have your data. Do you get an error with the code on
`?calibrate` (and are you using the most up-to-date versions of
everything?>
> With my previous configuration (other computer) the function calibrate
worked very well.
>
> Unfortunately, now the calibrate function doesn?t work. Do you have an idea
to help me in order to solve this problem. The validate function works.
>
> Thank you very much for your help
>
> Kind regards,
>
> Dewi
>
>
> Please find bellow my code :
>
>
> W
=read.table("export_R_model_proba.txt",sep="\t",header=TRUE)
>
> W= as.data.frame(W)
>
> ls()
>
> summary(W)
>
> library(survival)
>
> library(survplot)
>
> library(rms)
>
> library(SvyNom)
>
> library(SvyNom)
>
> library(survey)
>
>
> f <- cph(Surv(OS_time_months, OS_event) ~ CT + VE + Nratio_rcd +
log_LYPREOP + log_LYPO , dist='lognormal',data=W,surv=T,dxy =
TRUE,time.inc =48,x=TRUE, y=TRUE)
>
> f
>
> Cox Proportional Hazards Model
>
> cph(formula = Surv(OS_time_months, OS_event) ~ CT + VE + Nratio_rcd +
>
> log_LYPREOP + log_LYPO, data = W, x = TRUE, y = TRUE, surv = T,
>
> time.inc = 48, dist = "lognormal", dxy = TRUE)
>
>
> Model Tests Discrimination
>
> Indexes
>
> Obs 241 LR chi2 42.15 R2 0.161
>
> Events 179 d.f. 5 Dxy -0.283
>
> Center -5.6749 Pr(> chi2) 0.0000 g 0.608
>
> Score chi2 46.25 gr 1.837
>
> Pr(> chi2) 0.0000
>
>
> Coef S.E. Wald Z Pr(>|Z|)
>
> CT -0.6056 0.1891 -3.20 0.0014
>
> VE 0.4153 0.1640 2.53 0.0114
>
> Nratio_rcd 0.6746 0.1778 3.79 0.0001
>
> etc etc
>
>
plot(calibrate(f,u=48,method="boot",cmethod="KM",xlim=c(0,1),ylim=c(0,1),surv=T,m=33),xlim=c(0,1),ylim=c(0,1))
>
> Erreur dans UseMethod("calibrate") :
>
> pas de m?thode pour 'calibrate' applicable pour un objet de classe
"c('cph', 'rms', 'coxph')"
>
>
> [[alternative HTML version deleted]]
>
> ______________________________________________
> R-help at 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.
David Winsemius
Alameda, CA, USA