max_fp_threshold: Best Threshold Rule for a User's Maximum False Positive Rate

In TheLondonPeacock/SeaClass: Interactive GUI for analyzing a binary response variable

Description

Returns the best threshold rule based on true positive rate, where the rule has a false positive rate not exceeding a user specified maximum.

Usage

max_fp_threshold(x, group, pos_class, max_fp = 0.05)

Arguments

x	a numeric predictor.
group	binary grouping variable.
pos_class	group level for positive class.
max_fp	maximum false positive rate. Defaults to 0.05.

Details

Output quantities for false positive, true positive, and misclassification are percentages.

Value

• FP false positive percentage.

• TP true positive percentage.

• Misclass misclassification percentage.

• Direction text summarizing threshold rule.

See Also

accuracy_threshold, score_threshold

Examples

x <- c(rnorm(100,0,1),rnorm(100,2,1))
group <- c(rep(0,100),rep(2,100))
max_fp_threshold(x=x, group=group, pos_class=2, max_fp = 0.05)
max_fp_threshold(x=x, group=group, pos_class=0, max_fp = 0.05)

TheLondonPeacock/SeaClass documentation built on May 8, 2019, 3:42 p.m.