rscore: Calculate the r1 or r2 score for a new observation in ones...

In bradleyrava/fasi: Implements the Fair Adjusted Selective Inference (FASI) procedure

Calculate the r1 or r2 score for a new observation in ones test data.

Description

This function calculates an r-score for a given ranking score. It requires a calibration and testing dataset. Both the r-score+ and r-score can be implimented.

Usage

rscore(
  s_test_cur,
  y_class_cur,
  a_cur,
  z_cal,
  z_test,
  rscore_plus,
  r2_indicator
)

Arguments

s_test_cur	The current ranking score from the test data to be evaluated.
y_class_cur	The class label you want to generate the r-scores for.
a_cur	The current protected group from the test data to be evaluated.
z_cal	The calibration data set.
z_test	The test data set.
rscore_plus	Logical variable, T/F, that determines if the r-score or r-score plus is calculated.
r2_indicator	Logical variable, T/F, that determines if the r1 or r2 score is calculated.

Details

Do not call this function externally. It is only meant to be called from within the fasi function.

Value

The r-score corresponding to s_test_cur.

Author(s)

Bradley Rava. PhD Candidate at the University of Southern California's Marshall School of Business. Department of Data Sciences and Operations.

Examples

rscore(s_test_cur, y_class_cur, a_cur, z_cal, z_test, rscore_plus, r2_indicator)

bradleyrava/fasi documentation built on May 12, 2024, 6:23 a.m.