A METHOD OF ASSESSING BIAS IN TEST ITEMS

By J. Scheuneman. 1979

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

50 Years of Test (Un)fairness: Lessons for Machine Learning (2018, background): “Ten years later, the related idea of Differential Item Functioning (DIF) was introduced by Scheuneman in 1979 [58]: “an item is considered unbiased if, for persons with the same ability in the area being measured, the probability of a correct response on the item is the same regardless of the popula”
The New Faces of Fairness (2001, methodology): “The chi square statistic was used to investigate item fairness by comparing the item performance of people in roughly equivalent score bands (Scheunemann, 1979).”
Mitigating bias in algorithmic hiring: evaluating claims and practices (2019, background): “rential Item Functioning (DIF), which dened an item (i.e., test question or section) as unbiased if, conditioned on the outcome target of the tests, dierent groups had equal performance on the item [68]. Thus, an item demonstrates DIF if individuals from dierent subgroups with similar overall scores”
ETS CONTRIBUTIONS TO THE QUANTITATIVE ASSESSMENT OF ITEM, TEST, AND SCORE FAIRNESS (2013, unknown): “Scheuneman (1979) proposed a test statistic that was like a chi-square.”