plot {nsROC}

Plot an ROC curve object

Description

This function plots a 'groc', 'rocbands' or 'cdroc' object.

Usage

## S3 method for class 'groc'
plot(x, lwd = 2, xlab = "False-Positive Rate",
      ylab = "True-Positive Rate", main = "ROC curve", ...)
## S3 method for class 'rocbands'
plot(x, type='s', lwd=2, xlim=c(0,1), ylim=c(0,1),
     xlab="False-Positive Rate", ylab="True-Positive Rate",
     main=paste("ROC curve \n (", obj$method, " confidence bands)", sep=""),
     col='aquamarine3', col.inside="azure2", col.frontier="azure3",
     lwd.frontier=2, ...)
## S3 method for class 'cdroc'
plot(x, type='s', lwd=3, xlab='1 - Specificity',
     ylab='Sensitivity', xaxs='i', yaxs='i',
     main=paste("ROC curve at time", obj$predict.time), ...)

Arguments

x

a 'groc', 'rocbands' or 'cdroc' object from the gROC, ROCbands or cdROC respectively.

type

what type of plot should be drawn.

lwd

the line width to be used for ROC curve estimate, a positive number. See par.

col

the color to be used for ROC curve estimate. See par.

lwd.frontier

the line width to be used for ROC curve confidence bands estimate.

col.inside, col.frontier

the color to be used for ROC curve confidence bands estimate (col.frontier) and for the area inside (col.inside).

xlim, ylim

numeric vectors of length 2, giving the x and y coordinates ranges. See plot.window.

xlab, ylab

a title for the x and y axis, respectively. See title.

xaxs, yaxs

the style of axis interval calculation to be used for the x and y axis, respectively. See par.

main

an overall title for the plot. See title.

...

further arguments to be passed to methods, such as graphical parameters. See par.

Value

These functions return a plot of the object they were passed.

Examples

# Data generation
set.seed(123)
X <- c(rnorm(45), rnorm(30,2,1.5))
D <- c(rep(0,45), rep(1,30))

# Plot an ROC curve
grocobj <- gROC(X,D)
plot(grocobj)

# Plot ROC curve confidence bands
rocbandsobj <- ROCbands(grocobj)
plot(rocbandsobj)

# Plot cumulative/dynamic ROC curve
set.seed(123)
stime <- rchisq(50,3)
status <- sample(c(rep(1,40), rep(0,10)))
marker <- max(stime) - stime + rnorm(50,0,2)
cdrocobj <- cdROC(stime, status, marker, 2.8, ci=TRUE)
plot(cdrocobj)