Learn R Programming

⚠️There's a newer version (1.0.7) of this package.Take me there.

fairmetrics (version 1.0.3)

Fairness Evaluation Metrics with Confidence Intervals

Description

A collection of functions for computing fairness metrics for machine learning and statistical models, including confidence intervals for each metric. The package supports the evaluation of group-level fairness criterion commonly used in fairness research, particularly in healthcare. It is based on the overview of fairness in machine learning written by Gao et al (2024) .

Copy Link

Version

Install

install.packages('fairmetrics')

Monthly Downloads

149

Version

1.0.3

License

MIT + file LICENSE

Maintainer

Benjamin Smith

Last Published

June 12th, 2025

Functions in fairmetrics (1.0.3)

eval_eq_opp

Evaluate Equal Opportunity Compliance of a Predictive Model
eval_eq_odds

Examine Equalized Odds of a Predictive Model
eval_cond_acc_equality

Examine Conditional Use Accuracy Equality of a Model
eval_pos_class_bal

Examine Balance for the Positive Class of a Model
eval_acc_parity

Examine Accuracy Parity of a Model
eval_pred_equality

Examine Predictive Equality of a Model
eval_pos_pred_parity

Examine Positive Predictive Parity of a Model
eval_stats_parity

Examine Statistical Parity of a Model
get_fairness_metrics

Compute Fairness Metrics for Binary Classification
eval_neg_pred_parity

Examine Negative Predictive Parity of a Model
eval_bs_parity

Examine Brier Score Parity of a Model
eval_cond_stats_parity

Examine Conditional Statistical Parity of a Model
eval_treatment_equality

Examine Treatment Equality of a Model
eval_neg_class_bal

Examine Balance for Negative Class of a Model
mimic

Clinical data from the MIMIC-II database for a case study on indwelling arterial catheters
mimic_preprocessed

Preprocessed Clinical Data from the MIMIC-II Database