Hi, I have a dataset (see attached) with 2 variables "Y" is binary, "x" is a
continuous variable. I want to calculate area under the curve (AUC) for the ROC
curve, but I got different AUC values using ROC() from Epi package vs.
rcorr.cens() from rms package:
test<-read.table("test.txt",sep='\t',header=T,row.names=NULL)
y<-test$y
x<-test$x
library(Epi)
ROC(form=y~x,plot="ROC")
library(rms)
rcorr.cens(x,y)
lrm(y~x)
As you can see, ROC() gave an AUC 0.782, while both rcorr.cens() and lrm()
(C-index) gave AUC 0.813. That's a big difference. And I believe rms package
gave me correct answer. But anyone have any clue about the difference?
Thanks
John
y x
0 -4.93302239136569
0 -1.86090316224316
0 -1.90248869255672
0 -1.90248869255672
0 -1.90248869255672
0 -1.90248869255672
0 -1.86090316224316
0 -4.54372324899329
0 -0.070980902884954
0 -3.10151460169392
0 -3.14310013200748
0 -1.7008914847081
0 -3.53239927437987
0 -3.10151460169392
0 -3.10151460169392
0 -3.10151460169392
0 -4.93302239136569
0 -1.86090316224316
1 -0.070980902884954
0 -2.29178783492911
0 -0.070980902884954
0 -0.070980902884954
0 -3.10151460169392
0 -3.10151460169392
0 -1.86090316224316
0 -3.10151460169392
1 -1.31159234233571
1 -0.070980902884954
0 -1.47160401987077
0 -1.47160401987077
0 -3.69241095191493
0 -1.90248869255672
0 -3.30311180954254
0 -2.71221545932153
0 -1.86090316224316
0 -2.71221545932153
0 -0.070980902884954
0 -3.10151460169392
1 -0.070980902884954
1 -0.070980902884954
0 -4.93302239136569
0 -3.10151460169392
0 -3.10151460169392
1 -1.86090316224316
0 -4.93302239136569
0 -3.10151460169392
1 -3.10151460169392
0 -3.10151460169392
0 -1.90248869255672
0 -1.86090316224316
0 -0.070980902884954
1 -0.070980902884954
0 -3.10151460169392
0 -3.10151460169392
0 -0.070980902884954
0 -3.10151460169392
0 -3.14310013200748
0 -0.070980902884954
0 -2.71221545932153
0 -1.86090316224316
0 -1.86090316224316
0 -3.14310013200748
0 -1.86090316224316
0 -3.10151460169392
0 -3.10151460169392
0 -4.93302239136569
0 -0.070980902884954
0 -4.93302239136569
0 -1.47160401987077
0 -1.86090316224316
0 -4.93302239136569
0 -4.93302239136569
0 -2.71221545932153
0 -2.71221545932153
0 -4.93302239136569
0 -3.69241095191493
0 -1.86090316224316
0 -1.90248869255672
0 -3.10151460169392
0 -3.10151460169392
0 -3.10151460169392
1 -0.070980902884954
0 -3.69241095191493
0 -3.10151460169392
1 -0.070980902884954
0 -4.54372324899329
0 -1.86090316224316
0 -1.86090316224316
0 -2.71221545932153
0 -0.070980902884954
0 -4.93302239136569
0 -0.070980902884954
0 -1.86090316224316
0 -3.10151460169392
0 -3.14310013200748
0 -4.54372324899329
0 -0.070980902884954
0 -2.71221545932153
0 -3.10151460169392
0 -3.10151460169392
0 -3.10151460169392
0 -4.93302239136569
0 -4.93302239136569
0 -1.86090316224316
0 -3.10151460169392
0 -4.93302239136569
0 -3.69241095191493
0 -3.10151460169392
0 -1.47160401987077
0 -1.86090316224316
1 -0.070980902884954
0 -3.10151460169392
0 -4.54372324899329
0 -2.71221545932153
0 -3.30311180954254
0 -1.86090316224316
0 -3.10151460169392
0 -3.10151460169392
1 -0.070980902884954
0 -1.90248869255672
0 -3.10151460169392
0 -4.93302239136569
0 -4.93302239136569
0 -3.14310013200748
1 -0.070980902884954
0 -0.070980902884954
0 -3.10151460169392
0 -4.93302239136569
1 -0.070980902884954
1 -0.070980902884954
1 -3.69241095191493
1 -3.10151460169392
0 -4.93302239136569
0 -1.90248869255672
1 -0.070980902884954
0 -1.31159234233571
1 -0.460280045257347
0 -3.30311180954254
0 -3.30311180954254
0 -4.54372324899329
0 -3.10151460169392
0 -3.69241095191493
0 -0.070980902884954
1 -1.47160401987077
1 -3.30311180954254
0 -1.86090316224316
0 -4.93302239136569
______________________________________________
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.
