pROC (version 1.13.0)

ci.coords: Compute the confidence interval of arbitrary coordinates

Description

This function computes the confidence interval (CI) of the coordinates of a ROC curves with the coords function. By default, the 95% CI are computed with 2000 stratified bootstrap replicates.

Usage

# ci.coords(...)
# S3 method for roc
ci.coords(roc, x,
input=c("threshold", "specificity", "sensitivity"),
ret=c("threshold", "specificity", "sensitivity"),
best.method=c("youden", "closest.topleft"), best.weights=c(1, 0.5),
best.policy = c("stop", "omit", "random"),
conf.level=0.95, boot.n=2000,
boot.stratified=TRUE,
progress=getOption("pROCProgress")$name, ...) 
# S3 method for formula
ci.coords(formula, data, ...)
# S3 method for smooth.roc
ci.coords(smooth.roc, x,
input=c("specificity", "sensitivity"), ret=c("specificity", "sensitivity"),
best.method=c("youden", "closest.topleft"), best.weights=c(1, 0.5),
best.policy = c("stop", "omit", "random"),
conf.level=0.95, boot.n=2000,
boot.stratified=TRUE,
progress=getOption("pROCProgress")$name, ...)
# S3 method for default
ci.coords(response, predictor, ...)

Arguments

roc, smooth.roc

a “roc” object from the roc function, or a “smooth.roc” object from the smooth function.

response, predictor

arguments for the roc function.

formula, data

a formula (and possibly a data object) of type response~predictor for the roc function.

x, input, ret, best.method, best.weights

Arguments passed to coords. See there for more details. The only difference is on the x argument which cannot be “all” or “local maximas”.

best.policy

The policy follow when multiple “best” thresholds are returned by coords. “stop” will abort the processing with stop (default), “omit” will ignore the sample (as in NA) and “random” will select one of the threshold randomly.

conf.level

the width of the confidence interval as [0,1], never in percent. Default: 0.95, resulting in a 95% CI.

boot.n

the number of bootstrap replicates. Default: 2000.

boot.stratified

should the bootstrap be stratified (default, same number of cases/controls in each replicate than in the original sample) or not.

progress

the name of progress bar to display. Typically “none”, “win”, “tk” or “text” (see the name argument to create_progress_bar for more information), but a list as returned by create_progress_bar is also accepted. See also the “Progress bars” section of this package's documentation.

…

further arguments passed to or from other methods, especially arguments for roc and ci.coords.roc when calling ci.coords.default or ci.coords.formula. Arguments for txtProgressBar (only char and style) if applicable.

Value

A matrix of class “ci.coords”, “ci” and “matrix” (in this order), with the confidence intervals of the CI. The matrix has 3 columns (lower bound, median and upper bound) and as many rows as x * ret were requested. Rows are sorted by x and then by ret and named as “input x: return”.

Additionally, the list has the following attributes:

conf.level

the width of the CI, in fraction.

boot.n

the number of bootstrap replicates.

boot.stratified

whether or not the bootstrapping was stratified.

roc

the object of class “roc” that was used to compute the CI.

Warnings

If boot.stratified=FALSE and the sample has a large imbalance between cases and controls, it could happen that one or more of the replicates contains no case or control observation, producing a NA area. The warning “NA value(s) produced during bootstrap were ignored.” will be issued and the observation will be ignored. If you have a large imbalance in your sample, it could be safer to keep boot.stratified=TRUE.

This warning will also be displayed if you chose best.policy = "omit" and a ROC curve with multiple “best” threshold was generated during at least one of the replicates.

Details

ci.coords.formula and ci.coords.default are convenience methods that build the ROC curve (with the roc function) before calling ci.coords.roc. You can pass them arguments for both roc and ci.coords.roc. Simply use ci.coords that will dispatch to the correct method.

This function creates boot.n bootstrap replicate of the ROC curve, and evaluates the coordinates specified by the x, input, ret, best.method and best.weights arguments. Then it computes the confidence interval as the percentiles given by conf.level.

For more details about the bootstrap, see the Bootstrap section in this package's documentation.

References

James Carpenter and John Bithell (2000) ``Bootstrap condence intervals: when, which, what? A practical guide for medical statisticians''. Statistics in Medicine 19, 1141--1164. DOI: 10.1002/(SICI)1097-0258(20000515)19:9<1141::AID-SIM479>3.0.CO;2-F.

Tom Fawcett (2006) ``An introduction to ROC analysis''. Pattern Recognition Letters 27, 861--874. DOI: 10.1016/j.patrec.2005.10.010.

Hadley Wickham (2011) ``The Split-Apply-Combine Strategy for Data Analysis''. Journal of Statistical Software, 40, 1--29. URL: www.jstatsoft.org/v40/i01.

See Also

roc, coords, ci

CRAN package plyr, employed in this function.

Examples

# NOT RUN {
data(aSAH)

# }
# NOT RUN {
# Syntax (response, predictor):
ci.coords(aSAH$outcome, aSAH$s100b, x="best", input = "threshold", 
          ret=c("specificity", "ppv", "tp"))

# With a roc object:
rocobj <- roc(aSAH$outcome, aSAH$s100b)
ci.coords(rocobj, x=0.9, input = "sensitivity", ret="specificity")
ci.coords(rocobj, x=0.9, input = "sensitivity", ret=c("specificity", "ppv", "tp"))
ci.coords(rocobj, x=c(0.1, 0.5, 0.9), input = "sensitivity", ret="specificity")
ci.coords(rocobj, x=c(0.1, 0.5, 0.9), input = "sensitivity", ret=c("specificity", "ppv", "tp"))

# With a smoothed roc:
rocobj <- roc(aSAH$outcome, aSAH$s100b)
ci.coords(smooth(rocobj), x=0.9, input = "sensitivity", ret=c("specificity", "ppv", "tp"))

# Return everything we can:
rets <- c("threshold", "specificity", "sensitivity", "accuracy", "tn", "tp", "fn", "fp", "npv", 
          "ppv", "1-specificity", "1-sensitivity", "1-accuracy", "1-npv", "1-ppv")
ci.coords(rocobj, x="best", input = "threshold", ret=rets)
# }