plot.optimal.cutpoints {OptimalCutpoints}

Default optimal.cutpoints plotting

Description

On the basis of an optimal.cutpoints object, three plots are currently available: (1) a plot of the Receiver Operating Characteristic (ROC) curve; (2) a plot of the Predictive ROC (PROC) curve; and, in some methods, (3) a plot of the values of the optimal criterion used as a function of the cutoffs.

Usage

## S3 method for class 'optimal.cutpoints'
plot(x, legend = TRUE, which = c(1,2), ...)

Arguments

x

an object of class optimal.cutpoint as produced by optimal.cutpoints().

legend

a logical value for including the legend of optimal coordinates with specific characteristics. The default is TRUE.

which

a numeric vector with the required plots. By default, both the ROC and the PROC curves are plotted.

...

further arguments passed to method plot.default.

Author(s)

Monica Lopez-Raton and Maria Xose Rodriguez-Alvarez

See Also

optimal.cutpoints, control.cutpoints

Examples

library(OptimalCutpoints)
data(elas)
###########################################################
# Youden Index method ("Youden"): Covariate gender
###########################################################
optimal.cutpoint.Youden<-optimal.cutpoints(X = "elas", status = "status", tag.healthy = 0, 
methods = "Youden", data = elas, pop.prev = NULL, categorical.cov = "gender", 
control = control.cutpoints(), ci.fit = TRUE, conf.level = 0.95, trace = FALSE)

# Plot by default
plot(optimal.cutpoint.Youden)

#  Not including the optimal coordinates
plot(optimal.cutpoint.Youden, legend = FALSE)
# Change the colour
plot(optimal.cutpoint.Youden, col = "blue")