Validity CHaracteristic of criterion Relevant to the matter of hand

as applied to a test, is a judgment or estimate of how Valid for the purpose of which it is being used
well a test measures what is purports to measure in a Uncontaminated must not be based, at least in part, on
particular context. predictor measures
Validation is the process of gathering and evaluating
evidence about validity. test developer and the test user CONCURRENT VALIDITY
may play a role in the validation of a test. is an index of the degree to which a test score is related
Validation Studies may yield insights regarding a to some criterion measure obtained at the same time
particular population of testtakers as compared to the (concurrently).
norming sample described in a test manual
Local Validation Studies absolutely necessary when PREDICTIVE VALIDITY
the test user plans to alter in some way of the format, is an index of the degree to which a test score predicts
instructions, language, or content of the test some criterion measure.
types of validity
CONTENT VALIDITY Two types of validity under criterion-related Validity
is a measure of validity based on an evaluation of the VALIDITY COEFFICIENT
subject, topics, or content covered by the items in the is a correlation coefficient that provides a measure of the
test. relationship between test scores and scores on the
CRITERION-RELATED VALIDITY criterion measure.
is a measure of validity obtained by evaluating the INCREMENTAL VALIDITY
relationship of scores obtained on the test scores on the the degree to which an additional predictor explains
other test or measures something about the criterion measure that is not
CONSTRUCT VALIDITY explained by predictors already in use
is a measure of validity that is arrived at by executing a Two types of statistcal evidence
comprehensive analysis of CONSTRUCT VALIDITY
a. how scores on the test relate to other test scores and is a judgment about the appropriateness of inferences
measures drawn from test scores regarding individual standings on
b. how scores on the test can be understood within a variable called a construct.
some theoretical framework for understanding the CONSTRUCT
construct that the test was designed to measure. is an informed, scientific idea developed or hypothesized
to describe or explain behavior.
Face validity relates more to what a test appears to Evidence of construct validity
measure to the person being tested than to what the test EVIDENCE OF HOMOGENEITY
actually measures. refers to how uniform a test is in measuring a single
concept. One way a test developer can improve the
judgment concerning how relevant the test items homogeneity of a test containing items that are scored
appears to be is usually from test taker’s, not test user’s dichotomously (such as a true-false test) is by
perspective. eliminating items that do not show significant correlation
coefficients with total test scores
lack of face validity could contribute to a lack of Evidence of construct validity
confidence in the perceived effectiveness of the test— EVIDENCE OF PRETEST-POSTTESTS
with a consequential decrease in the test taker’s changes evidence that test scores change as a result of
cooperation or motivation some experience between a pretest and a posttest can
be evidence of construct validity.
content validity describes a judgment of how adequately
a test samples behavior representative of the universe Evidence of construct validity
of behavior that the test was designed to sample EVIDENCE FROM DISTINCT GROUPS
TEST BLUEPRINT “structure” of the evaluation—that is, Also referred to as the method of contrasted groups, one
a plan regarding the types of information to be covered way of providing evidence for the validity of a test is to
by the items, the number of items tapping each area of demonstrate that scores on the test vary in a predictable
coverage, the organization of the items in the test, etc way as a function of membership in some group.

CRITERION-RELATED VALIDITY is a judgment of how CONVERGENT EVIDENCE

adequately a test score can be used to infer an Evidence for the construct validity of a particular test
individual’s most probable standing on some measure of may converge from a number of sources, such as other
interest—the measure of interest being the criterion. it tests or measures designed to assess the same (or a
measures how closely the result of your test similar) construct
corresponds to the result of a different test
DISCRIMINANT EVIDENCE
CRITERION A validity coefficient showing little (a statistically
we defined a criterion broadly as a standard on which a insignificant) relationship between test scores and/or
judgment or decision may be based. a criterion just a bit other variables with which scores on the test
more narrowly as the standard against which a test or a beingconstruct-validated should not theoretically be
test score is evaluated. correlated provides discriminant evidence of construct
validity.
--
Factory analysis is a shorthand term for a class of
mathematical procedures designed to identify factors or
specific variables that are typically attributes,
characteristics, or dimensions on which people may
differ

Factory Loading conveys information about the extent

to which the factor determines the test score or scores

test bias bias is a factor inherent in a test that

systematically prevents accurate, impartial
measurement.

rating error is a judgment resulting from the intentional

or unintentional misuse of a rating scale.

Halo effect defined as a tendency to give a particular

rate a higher rating than he or she objectively deserves
b e c a u s e o f t h e r a t e r ’ s f ailure to discriminate
a m o n g c o n c e p t u ally dis tin c t a n d p o t e n
tially independent aspects of a ratee’s behavior.