This preview shows page 1. to view the full 5 pages of the document.
Chapter 6 – Topic 6B – Test Bias and Other Controversies
The Question of Test Bias
Test bias is an objective, empirical question, not a matter of personal judgment. Test bias is a
technical concept of amenable to impartial analysis. In contrast, test fairness reflects social values and
philosophies of test use, particularly when test use extends to selection for privilege or employment.
The Test Bias Controversy
The test bias controversy has its origins in the observed differences in average IQ among various
racial and ethnic groups (African Americans on standardized IQ tests). The proof of test bias however
must rest on other criteria listed below.
Criteria of Test Bias and Test Fairness
Test bias refers to objective statistical indices that examine the patterning of test scores for
relevant subpopulations. In general, a test is considered biased if it is differentially valid in different
In contrast to the narrow concept of test bias, test fairness is a broad concept that recognizes the
importance of social values in test usage. Ultimately, test fairness is based on social conceptions such as
one’s image of a just society.
The Technical Meaning of Test Bias: A Definition
Bias is present when a test score has meanings or implications for a relevant, definable subgroup
of test takers that are different from meanings or implications for the remainder of test takers.
Bias in Content Validity
Bias in content validity is probably the most common criticism of those who denounce the use of
standardized tests with minorities. Content bias: an item or subscale of a test is considered to be biased in
content when it is demonstrated to be relatively more difficult for members of one group than another
when the general ability level are held constant.
Attempts to prove that expert-nominated items are culturally biased have not yielded the
conclusive evidence that critics expect. “Expert” judges cannot identify culturally biased test items.
In general, with respect to well known standardized tests of ability and aptitude, research has not
supported the popular belief that the specific content of test items is a source of cultural bias against
Bias in Predictive or Criterion Related Validity
In general, an unbiased test will predict future performance equally well for persons from
different subpopulations. Criterion related or predictive validity bias: A test is considered biased with
respect to predictive validity if the inference drawn from the test score is not made with the smallest
feasible random error or if there is constant error in an inference or prediction as a function of
You're Reading a Preview
Unlock to view full version
Only page 1 are available for preview. Some parts have been intentionally blurred.
membership in a particular group. According to this definition, for a tests to be unbiased the results for all
relevant subpopulations must cluster equally well around a single regression line.
Y= bX + a – higher values of b indicates a steeper slope and more accurate prediction. The value
of a depicts the intercept on the vertical axis. If separate regression lines are not even parallel, the test
possesses a high degree of test bias in criterion related validity.
Bias in Construct Validity
Bias in construct validity: Bias exists in regard to construct validity when a test is shown to
measure different hypothetical traits for one group than for another. If a test is unbiased, comparisons
across relevant subpopulations should reveal a high degree of similarity for 1) the factorial structure of the
test and 2) the rank order of item difficulties within the test.
An essential criterion of nonbias is that the factor structure of test scores should remain invariant
across relevant subpopulations. When test items or subscales of prominent ability and aptitude tests are
factoralyzed separately in white and minority samples, the same factors emerge in the relevant
A second criterion of nonbias in construct validity is that the rank order of item difficulties within
a test should be highly similar for relevant subpopulations. What is essential is that the items most
difficult for one subgroup should also be the most difficult for the other relevant subgroups.
Reprise on Test Bias
In general, ability and aptitude tests fare quite well by the criteria of factor analysis, regression
equations, intergroup comparisons of the difficulty levels for “biased” versus “unbiased” items, and rank
ordering of item difficulties. There is no domain of ability or aptitude testing in which there has been
cumulative evidence suggesting test bias.
Social Values and Test Fairness
Three ethical positions can be distinguished.
Ethical stance of unqualified individualism dictates that, without exception, the best qualified
candidates should be selected for employment, admission, or other privilege.
The ethical stance of quotas acknowledges that many bureaucracies and educational institutions
owe their very existence to the city or state in which they function. Fair share quotas are based initially
upon population percentages.
You're Reading a Preview
Unlock to view full version