A Note on the Significance Adjustment for FA*IR with Two Protected Groups

12/23/2020
by   Meike Zehlike, et al.
0

In this report we provide an improvement of the significance adjustment from the FA*IR algorithm of Zehlike et al., which did not work for very short rankings in combination with a low minimum proportion p for the protected group. We show how the minimum number of protected candidates per ranking position can be calculated exactly and provide a mapping from the continuous space of significance levels (α) to a discrete space of tables, which allows us to find α_c using a binary search heuristic.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/20/2022

MANI-Rank: Multiple Attribute and Intersectional Group Fairness for Consensus Ranking

Combining the preferences of many rankers into one single consensus rank...
research
02/02/2021

On absolutely and simply popular rankings

Van Zuylen et al. introduced the notion of a popular ranking in a voting...
research
07/19/2019

Fair quantile regression

Quantile regression is a tool for learning conditional distributions. In...
research
04/30/2021

Efficient Multiple Testing Adjustment for Hierarchical Inference

Hierarchical inference in (generalized) regression problems is powerful ...
research
05/27/2019

FairSearch: A Tool For Fairness in Ranked Search Results

Ranked search results and recommendations have become the main mechanism...
research
02/10/2017

Compressing Green's function using intermediate representation between imaginary-time and real-frequency domains

New model-independent compact representations of imaginary-time data are...

Please sign up or login with your details

Forgot password? Click here to reset