| Title: | Computing False Positive Rate from Inter-Rater Reliability |
|---|---|
| Description: | Implements a 'Shiny Item Analysis' module and functions for computing false positive rate and other binary classification metrics from inter-rater reliability based on Bartoš & Martinková (2022) <doi:10.48550/arXiv.2207.09101>. |
| Authors: | František Bartoš [aut, cre] |
| Maintainer: | František Bartoš <[email protected]> |
| License: | GPL-3 |
| Version: | 0.1 |
| Built: | 2024-11-07 04:42:02 UTC |
| Source: | https://github.com/fbartos/irr2fpr |
Compute the false negative rate based on the inter-rater reliability and the proportion of selected candidates
compute_false_negative_rate(IRR, proportion_selected)compute_false_negative_rate(IRR, proportion_selected)
IRR |
The inter-rater reliability |
proportion_selected |
The proportion of selected candidates |
The false negative rate
compute_false_negative_rate(0.75, 0.10)compute_false_negative_rate(0.75, 0.10)
Compute the false positive rate based on the inter-rater reliability and the proportion of selected candidates
compute_false_positive_rate(IRR, proportion_selected)compute_false_positive_rate(IRR, proportion_selected)
IRR |
The inter-rater reliability |
proportion_selected |
The proportion of selected candidates |
The false positive rate
compute_false_positive_rate(0.75, 0.10)compute_false_positive_rate(0.75, 0.10)
Compute proportion of correctly selected candidates based on the inter-rater reliability and the proportion of selected candidates
compute_proportion_of_correctly_selected(IRR, proportion_selected)compute_proportion_of_correctly_selected(IRR, proportion_selected)
IRR |
The inter-rater reliability |
proportion_selected |
The proportion of selected candidates |
The proportion of correctly selected candidates
compute_proportion_of_correctly_selected(0.75, 0.10)compute_proportion_of_correctly_selected(0.75, 0.10)
Compute the true positive rate based on the inter-rater reliability and the proportion of selected candidates
compute_true_positive_rate(IRR, proportion_selected)compute_true_positive_rate(IRR, proportion_selected)
IRR |
The inter-rater reliability |
proportion_selected |
The proportion of selected candidates |
The true positive rate
compute_true_positive_rate(0.75, 0.10)compute_true_positive_rate(0.75, 0.10)
This module allows users to convert inter-rater reliability (IRR) to false positive rate (FPR) as described in Bartoš and Martinková (2022).
František Bartoš
Bartoš, F., & Martinková, P. (2022). Selecting applicants based on multiple ratings: Using binary classification framework as an alternative to inter-rater reliability. doi:10.48550/arXiv.2207.09101
Compute the inter-rater reliability based on the Spearman-Brown formula
spearman_brown_formula(IRR_1, n_raters)spearman_brown_formula(IRR_1, n_raters)
IRR_1 |
The inter-rater reliability of the first rater |
n_raters |
The number of raters |
The inter-rater reliability
spearman_brown_formula(0.5, 3)spearman_brown_formula(0.5, 3)