rocsvm.intercept {rocsvm.path}

Finding an intercept fixed sensitivity or specificity for ROC-SVM

Description

Computes an intercept at a specific sensitivity or specificity level from the ROC-SVM model.

Usage

rocsvm.intercept(obj, lambda = 1, sensitivity = 0.5, specificity = 0.5)

Arguments

obj

The rocsvm.path object

lambda

The regularization parameter that users want in ROC-SVM model.

sensitivity

Sensitivity in ROC curve, which means True Positive Rate (TPR).

specificity

Specificity in ROC curve, which means True Negative Rate (TNR) = 1-FPR.

Author(s)

Seung Jun Shin, Do Hyun Kim

See Also

rocsvm.path

Examples

# library(rocsvm.path)
# The 'obj' comes from an example description of rocsvm.path()

rocsvm.intercept(obj, lambda = 1, sensitivity = 0.9, specificity = 0.1)