MetaIntegrator (version 2.1.3)

calculateROC: Calculate ROC Curve Statistics

Description

Calculates receiver operating characteristic curve data, including AUC (using trapezoidal method). Takes only a vector of labels and a vector of predictions.

Usage

calculateROC(labels, predictions, AUConly = FALSE)

Arguments

labels

Vector of labels; must have exactly two unique values (ie, cases and controls).

predictions

Vector of predictions (for instance, test scores) to be evaluated for ability to separate the two classes. Must be exactly the same length as labels.

AUConly

Return all ROC values, or just the AUC.

Value

Assuming AUConly=F, returns a list of values:

roc

dataframe consisting of two columns, FPR and TPR, meant for plotting

auc

area under the curve

auc.CI

95% confidence interval for AUC

Details

The code borrows its core ROC calculations from the ROCR package. AUC is calculated by the trapezoidal method. AUC standard errors are calculated according to Hanley's method.

References

The code borrows its core ROC calculations from the ROCR package.

See Also

calculateScore, rocPlot

Examples

# NOT RUN {
# expect an AUC near 0.5 with random test
labels <- c(rep(0, 500), rep(1, 500))
scores <- runif(1000)
calculateROC(labels, scores)
#With the real data, AUC should be around 0.85606
scoreResults <- calculateScore(tinyMetaObject$filterResults[[1]], tinyMetaObject$originalData[[1]]) 
rocRes <- calculateROC(predictions=scoreResults, labels=tinyMetaObject$originalData[[1]]$class)
print(rocRes$auc[[1]])
# }