Affiliation:
1. Teachers College of Columbia University
2. Graduate Management Admission Council
Abstract
Ensuring fairness is crucial in developing modern algorithms and tests. To address potential biases and discrimination in algorithmic decision making, researchers have drawn insights from the test fairness literature, notably the work on differential algorithmic functioning (DAF) by Suk and Han. Nevertheless, the exploration of intersectionality in fairness investigations, within both test fairness and algorithmic fairness fields, is still relatively new. In this paper, we propose an extension of the DAF framework to include the concept of intersectionality. Similar to DAF, the proposed notion for intersectionality, which we term “interactive DAF,” leverages ideas from test fairness and algorithmic fairness. We also provide methods based on the generalized Mantel–Haenszel test, generalized logistic regression, and regularized group regression to detect DAF, interactive DAF, or other subtypes of DAF. Specifically, we employ regularized group regression with three different penalties and examine their performance via a simulation study. Finally, we demonstrate our intersectional DAF framework in real-world applications on grade retention and conditional cash transfer programs in education.
Funder
National Science Foundation
Publisher
American Educational Research Association (AERA)
Reference50 articles.
1. Barocas S., Hardt M., Narayanan A. (2019). Fairness and machine learning. fairmlbook.org. http://www.fairmlbook.org
2. Barrera-Osorio F., Bertrand M., Linden L. L., Perez-Calle F. (2019). Replication data for: Improving the design of conditional transfer programs: Evidence from a randomized education experiment in Colombia (Technical Reports). Inter-university Consortium for Political and Social Research. https://doi.org/10.3886/E113783V1
3. Improving the Design of Conditional Transfer Programs: Evidence from a Randomized Education Experiment in Colombia
4. Improving the assessment of measurement invariance: Using regularization to select anchor items and identify differential item functioning.
5. Group descent algorithms for nonconvex penalized linear and logistic regression models with grouped predictors