StatMeasures (version 1.0)

auc: Area under curve of predicted binary response

Description

Takes in actual binary response and predicted probabilities, and returns auc value

Usage

auc(y, yhat)

Arguments

y

actual binary response

yhat

predicted probabilities corresponding to the actual binary response

Value

area under the ROC curve

Details

Area under the receiver operating characteristic (ROC) curve is the most sought after criteria for judging how good model predictions are.

auc function calculates the true positive rates (TPR) and false positive rates (FPR) for each cutoff from 0.01 to 1 and calculates the area using trapezoidal approximation. A ROC curve is also generated.

See Also

accuracy, ks, iv, gini, splitdata

Examples

# A 'data.frame' with y and yhat
df <- data.frame(y = c(1, 0, 1, 1, 0, 0, 1, 0, 1, 0),
                 yhat = c(0.86, 0.23, 0.65, 0.92, 0.37, 0.45, 0.72, 0.19, 0.92, 0.50))

# AUC figure
AUC <- auc(y = df[, 'y'], yhat = df[, 'yhat'])