Publication: Industrial and Organizational
Psychology: Perspectives on Science and Practice
Article: Not Seeing Clearly With Cleary:
What Test Bias Analyses Do and Do Not Tell Us
Authors: A.W. Meade and S. Tonidandel
Sackett and P. Bobko
Reviewed By: Samantha Paustian-Underdahl
When practitioners use pre-employment tests for
selection decisions, they must consider the potential biases that may result
from the assessment. Using biased
tests can lead to poor, ‘unfair’ hiring decisions. Not only can perceptions of
unfairness negatively impact a company’s reputation and bottom line, but legal
issues can arise if selection procedures are not free from bias (Allen v.
Alabama State Board of Education, 2000).
Whether HR professionals are developing their own test or procedure, or
are purchasing a test from a vendor, an understanding of test bias is essential
to ensure there is no adverse impact to any candidate group.
Meade and Tonidandel (2010) argue that despite the
importance of assessing for test bias in the field of I/O psychology, there are
pervasive misunderstandings regarding what tests of bias really tell us. They
believe that the standard technique for evaluating whether a test is biased (the
regression-based approach outlined by Cleary (1968)) fails to tell us what we
really need to know about a test. The authors explain that the Cleary approach
focuses on differences in regression lines across groups, which is known as differential
other words, the Cleary method examines the extent to which predicted
performance matches observed performance when using a common regression line in
a specific selection context. The authors’ main concern with the Cleary method
of assessing test bias is that when differential prediction is found, many
people assume there is a problem with the test itself. However, there are many
other reasons for differential prediction, e.g., the way the outcome variable
(performance) is measured, the reliability of the test, or omitted variables.
In conclusion, Meade and Tonidandel (2010) provide
some recommendations to anyone responsible for selection tests:
should work with clients to attempt to identify the source of the differential
prediction and eliminate it if possible.
entire selection system (all tests used to predict performance) should be
assessed for adverse impact. If the differential prediction occurs for only
part of the selection system, look for a predictor that can reduce the overall
bias. For example, if a cognitive ability test leads to differential prediction
for one group of applicants, practitioners should look for another, non-biased
predictor (personality, motivation, cultural fit, etc.) to add to the selection
system that will account for the mean differences in performance.
should not assume a test is unusable in cases where differential prediction is
encountered. Depending on the organizations’ goals and priorities, differential
prediction does not necessarily make a test unusable for selection. When a
predictor accurately predicts performance, and does not show adverse impact or
mean differences, and the minority group has lower mean differences on
performance, it may well be in an organization’s best interest to not attend to
differential prediction. Suitability of use of the test in such situations
depends on opinions of fairness within the organization and society at large.
The commentaries generally fall into three
categories: commentaries that take issue with aspects of the focal paper
(Sackett & Bobko, 2010), commentaries that are generally supportive of
aspects of the paper yet believe that the authors did not go far enough, and
commentaries that focus on issues related to, but not directly addressed in,
the focal paper. The Sackett and Bobko (2010) commentary is reviewed below, as
it highlights issues most relevant to IOATWork.com’s audience.
Sackett and Bobko (2010) begin their commentary by
clarifying the presumed context of the Meade and Tonidandel focal paper. They
explain that there are generally two reasons for conducting differential
prediction analyses: 1) to comply with equal employment opportunity regulations
under which selection practice often operates and 2) to provide the scientist/
practitioner with insight as to the nature of predictor/criterion (selection
test/job performance) relationship. They believe that Meade and Tonidandel
focus their discussion around the second reason since they state that they
prefer to examine differential prediction regardless of the presence or absence
of mean differences on the predictor, which takes their discussion outside the
bounds of a regulatory framework. Thus, in practice, Sackett and Bobko argue
that personnel selection professionals only need to conduct bias analyses if
there are mean differences on the predictor between groups.
Another key point mentioned in the Sakett and Bobko
commentary is that many personnel selection practitioners use a range of
predictors that may produce a single score, such as an overall rating in an
interview or an assessment center. While the use of such measures to predict a
given outcome (i.e., job performance) can be examined for predictive bias, a
differential prediction analysis for each item is not always applicable.
and Tonidandel, S. (2010). Not Seeing Clearly With Cleary: What Test Bias
Analyses Do and Do Not Tell Us. Industrial and Organizational Psychology: Perspectives
on Science and Practice, 3, 192–205.
Sackett, P. R., & Bobko, P. (2010). Conceptual
and technical issues in conducting and interpreting differential prediction
analyses. Industrial and Organizational Psychology, 3, 213–217.
Allen v. Alabama State Board of Education. U.S. Dist.
LEXIS 123 (M.D. Al 2000).
Cleary, T. A. (1968). Test bias: Prediction of grades
of Negro and White students in integrated colleges. Journal of Educational
Measurement , 5,