Premium
CONCEPTS OF CULTURE‐FAIRNESS
Author(s) -
THORNDIKE ROBERT L.
Publication year - 1971
Publication title -
journal of educational measurement
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.917
H-Index - 47
eISSN - 1745-3984
pISSN - 0022-0655
DOI - 10.1111/j.1745-3984.1971.tb00907.x
Subject(s) - test (biology) , statistics , set (abstract data type) , fraction (chemistry) , group (periodic table) , mathematics , test score , psychology , econometrics , social psychology , standardized test , computer science , paleontology , chemistry , organic chemistry , biology , programming language
Fairness of a test relates to fair use. One definition of fair use states that a common qualifying score may be used with two groups if the regression line based on one group does not systematically over‐ or under‐predict criterion performance in the other. However, it is shown that when the two groups differ appreciably in mean test score, the above procedure, which is “fair” to individual members of the group scoring lower on the test, is “unfair” to the lower group as a whole in the sense that the proportion qualified on the test will be smaller, relative to the higher‐scoring group, than the proportion that will reach any specified level of criterion performance. An alternate definition would specify that the qualifying scores on a test should be set at levels that will qualify applicants in the two groups in proportion to the fraction of the two groups reaching a specified level of criterion performance.