VALIDITY
By Dr. Suruchi Singh
VALIDITY
■ Validity refers to the degree to which a test measures, what it claims to
measure. It is very necessary for a test to be valid for its proper administration
and interpretation.
■ According to Standard for Educational and Psychological testing (AERA, APA &
NCME 1985, 1999); a test is valid to the extent that inferences drawn from it
are appropriate, meaningful and useful.
■ According to Cronbach (1951) validity is the extent to which a test measures
what it purports to measure.
■ According to Freeman (1971) an index of validity shows the degree to which a
test measures what it purports to measure when compared with accepted
criteria.
■ According to Anastasi (1988) the validity of a test concerns what the test
measures and how well it does so.
Content validity Con current
validity
Criterion-related
validity Predictive validity
Convergent
TYPES OF validity
Construct validity
VALIDITY Discriminate
validity
Face validity
Internal Validity
External Validity
Content Validity
■ According to Mc Burney and White (2007); content validity is the
notion that a test should sample range of behaviour that is
represented by the theoretical concept being measured.
■ It is a non-statistical type of validity with involvement of assessment of
the content of the test to ascertain whether it includes the sample
representative of the behaviour that is intended to be measured.
When a test has content validity, the items on the test represent the
entire range of possible items the test should cover.
■ For instance, if researcher wants to develop an achievement test of
spelling for the third grade children then a researcher could identify
nearly all the possible words that third grade children should know.
Individual test items may be taken from a huge group of items that
include a broad range of items
Content Validity
■ A test has content validity inbuilt in it. Items are selected in
accordance with their compliance with the requirements of the test
after a careful examination of the subject area. In certain cases,
where a test measures a trait which is difficult to define, an expert
can rate the relevance of items.
■ Since, each judge have their own opinion on their rating, two
independent judges will rate the test separately. Items which are
rated as highly relevant by both judges would be included in the
final test.
Criterion-related Validity
■ Criterion related validity is the idea that a valid test should
relate closely to other measure of the same theoretical
concept.
■ A valid test of intelligence should correlate highly with
other intelligence test. If a test demonstrates effective
predicting criterion or indicators of the construct, it is said
to possess criterion – related validity.
■ There are two different types of criterion validity
– Concurrent Validity
– Predictive Validity
Concurrent Validity
■ Its occurrence is found when criterion measures are
achieved at the same time as the test scores.
■ It reflects the degree to which the test scores estimate the
individual’s present status with regards to criterion.
■ For instance, if a test measures anxiety, it would be said to
have concurrent validity if it rightly reflects the current
level of anxiety experienced by an individual.
■ Concurrent evidence of test validity is usually desirable for
achievement tests and diagnostic clinical test.
Predictive Validity
■ Predictive validity occurs when criterion measures are
obtained at a time after the test. For example, aptitude tests
are useful in identifying who will be more likely to succeed
or fail in a particular subject.
■ Predictive validity is part curly relevant for entrance
examination and occupational test.
Construct Validity
■ Construct validity approach is complex than other forms of validity. Mc Burney and
White (2007) defined construct validity as the property of a test that the
measurement actually measures the constructs they are designed to measure.
There are several ways to determine whether a test generate data that have
construct validity.
1. The test should actually measure whatever theoretical construct it supposedly
tests, and not something else. For example a test of leadership ability should not
actually test extraversion.
2. A test that has construct validity should measure what it intends to measure but not
measure theoretically unrelated constructs. For example, a test of musical aptitude
should not require too much reading ability.
3. A test should prove useful in predicting results related to the theoretical concepts it
is measuring. For example, a test of musical ability should predict who will benefit
from taking music lessons, should differentiate groups who have chosen music as a
career from those who haven’t should relate to other tests of musical ability and so
on.
Types of construct validity
■ Convergent Validity
– It means the extent to which a measure is correlated with other
measure which is theoretically predicted to correlate with.
– The words the same concept measured in different ways yields similar results. In
this case, you could include two different tests.
■ Discriminant Validity
– This explains the extent to which the operationalisation is not
correlated with other operationalisations that it theoretically should
not be correlated with.
– In other words, a test should not be highly correlated with measures of
different constructs, ensuring that it captures something unique
rather than overlapping too much with other variables.
Convergent validity
■ For example
■ You could place people on meters on respondent’s television sets to record the time
that people spend with news programs. Then, this record can be compared with
survey results of “exposure to televised news”;
or
■ .You could send someone to observe respondent’s television use at their home, and
compare the observation results with your survey results.
Discriminant validity
■ in the example of TV news exposure, you could include measures of exposure to TV
entertainment programs and determine if they differ from TV news exposure
measures.
■ In this case, the measures of exposure to TV news should not related highly to
measures of exposure to TV entertainment programs.
■ Evidence that the concept as measured can be differentiated from other concepts.
Our theory says that physical aggression and verbal aggression are different
behaviors. In this case, the correlations should be low between questions asked that
dealt with verbal aggression and questions asked that dealt with physical aggression
in the self-report measure.
Face Validity
■ Face validity refers to what appears to measure superficially. It depends on the
judgment of the researcher. Each question is scrutinised and modified until the
researcher is satisfied that it is an accurate measure of the desired construct. The
determination of face validity is based on the subjective opinion of the researcher.
Factor Affecting measuring Test of
Validity
■ History – Events that besides the treatment (events in the environment).
■ Maturation- Physical or psychological changes in the participants.
■ Testing- Effect or experience with the pretest –become test wise.
■ Instrumentation- Learning gain might be observed from pre to post test simply due to nature of the
instrument .Particularly a problem in observation studies when observers more likely to give ratings
based on Expectation (Conscious and Subconscious)
■ Statistical regression – Tendency for Participant whose scores fall at either extreme on a variable to
score nearer the mean when measured a second time.
■ Differential Selection – Effect of treatment confounded with other factors because of differential
selection of participant ,problem in non random samples.
■ Experimental Mortality- Participant lost from the study, attrition.
■ Selection- Maturation Interaction –Similar to differential selection except maturation the confounding
variables.
■ Experimental Treatment Diffusion-Treatment is perceived as highly desirable and members of control
group seek access
Thank You