What is validity in research?

Validity is how researchers talk about the extent that results represent reality. Research
methods, quantitative or qualitative, are methods of studying real phenomenon – validity
refers to how much of that phenomenon they measure vs. how much “noise,” or unrelated
information, is captured by the results.
Validity and reliability make the difference between “good” and “bad” research
reports. Quality research depends on a commitment to testing and increasing the validity as
well as the reliability of your research results.
Any research worth its weight is concerned with whether what is being measured is
what is intended to be measured and considers the ways in which observations are influenced
by the circumstances in which they are made.
The basis of how our conclusions are made play an important role in addressing the
broader substantive issues of any given study.
For this reason we are going to look at various validity types that have been
formulated as a part of legitimate research methodology

Content Validity:
Content Validity a process of matching the test items with the instructional objectives.

Content validity is the most important criterion for the usefulness of a test, especially of an

achievement test. It is also called as Rational Validity or Logical Validity or Curricular

Validity or Internal Validity or Intrinsic Validity.

Content validity refers to the degree or extent to which a test consists items representing the

behaviours that the test maker wants to measure. The extent to which the items of a test are

true representative of the whole content and the objectives of the teaching is called the

content validity of the test.

Content validity is estimated by evaluating the relevance of the test items; i.e. the test items

must duly cover all the content and behavioural areas of the trait to be measured. It gives idea

of subject matter or change in behaviour.

This way, content validity refers to the extent to which a test contains items representing the

behaviour that we are going to measure. The items of the test should include every relevant

characteristic of the whole content area and objectives in right proportion.

Before constructing the test, the test maker prepares a two-way table of content and

objectives, popularly known as “Specification Table”.

Suppose an achievement test in Mathematics is prepared. It must contain items from Algebra,

Arithmetic, Geometry, Mensuration and Trigonometry and moreover the items must measure

the different behavioural objectives like knowledge, understanding, skill, application etc. So

it is imperative that due weightage be given to different content area and objectives

An example of ‘specification table’ in Mathematics is shown in following table:

The Table reflects the sample of learning tasks to be measured. The closer the test items

correspond to the specified sample, the greater the possibility of having satisfactory content

validity. Therefore, it is desirable that the items in a test are screened by a team of experts.

They should check whether the placement of the various items in the cells of the Table is
appropriate and whether all the cells of the Table have an adequate number of items.

The adequacy is to be judged in terms of the weightage given to the different content-by-
objective Table according to the team of experts who have designed the curriculum
Some general points for ensuring content validity are given below:
1. Test should serve the required level of students, neither above nor below their standard.

2. Language should be upto the level of students.

3. Anything which is not in the curriculum should not be included in test items.

4. Each part of the curriculum should be given necessary weightage. More items should be
selected from more important parts of the curriculum.

Limitations:
1. The weightage to be given to different parts of content is subjective.

2. It is difficult to construct the perfect objective test.

3. Content validity is not sufficient or adequate for tests of Intelligence, Achievement,

Attitude and to some extent tests of Personality.

4. Weightage given on different behaviour change is not objective.

Concurrent Validity:
Concurrent Validity correlating the test scores with another set of criterion scores.

Concurrent validity refers to the extent to which the test scores correspond to already

established or accepted performance, known as criterion. To know the validity of a newly

constructed test, it is correlated or compared with some available information.
Thus a test is validated against some concurrently available information. The scores obtained

from a newly constructed test are correlated with pre-established test performance. Suppose
we have prepared a test of intelligence.

We administer it to group of pupils. The Stanford-Binet test is also administered to the same
group. Now test scores made on our newly constructed test and test scores made by pupils on
the Stanford-Binet Intelligence Test are correlated. If the coefficient of correlation is high,
our intelligence test is said to have high concurrent validity.

The dictionary meaning of the term ‘concurrent’ is ‘existing’ or ‘done at the same time’. Thus
the term ‘concurrent validity’ is used to indicate the process of validating a new test by

correlating its scores with some existing or available source of information (criterion) which

might have been obtained shortly before or shortly after the new test is given.
To ascertain the concurrent validity of an achievement test constructed freshly, its scores are
correlated with the scores obtained by those same students in their recent first-terminal or

terminal examination. Thus a test is validated against some concurrently available

information. To get a criterion measure, we are not required to wait for a long time.

The predictive validity differs from concurrent validity in the sense that in former validity we

wait for the future to get criterion measure. But in ease of concurrent validity we need not

wait for longer gaps.

The term ‘concurrent’ here implies the following characteristics:

1. The two tests—the one whose validity is being examined and the one with proven

validity—are supposed to cover the same content area at a given level and the same

objective;
2. The population for both the tests remains the same and the two tests are administered in

almost similar environments; and

3. The performance data on both the tests are obtainable almost simultaneously.
This type of validity is also known as “External Validity” or “Functional Validity”.
Concurrent validity is relevant to tests employed for diagnosis not for prediction of future
success.

Construct Validity:
Construct Validity the extent is which the test may be said to measure a theoretical construct
or psychological variable.
A construct is mainly psychological. Usually it refers to a trait or mental process. Construct
validation is the process of determining the extent to which a particular test measures the
psychological constructs that the test maker intends to measure.

It indicates the extent to which a test measures the abstract attributes or qualities which are

not operationally defined.

Gronlund and Linn states,” Construct validation maybe defined as the process of determining
the extent to which the test performance can be interpreted in terms of one or more
psychological construct.”

Ebel and Frisbie describes, “Construct validation is the process of gathering

evidence to support the contention that a given test indeed measures the
psychological construct that the test makers intended for it to measure.”

Construct validity is also known as “Psychological Validity” or ‘Trait Validity’ or ‘Logical

Validity’. Construct validity means that the test scores are examined in terms of a construct.
It studies the construct or psychological attributes that a test measures.
The extent to which the test measures the personality traits or mental processes as defined by
the test-maker is known as the construct validity of the test.
While constructing tests on intelligence, attitude, mathematical aptitude, critical thinking,
study skills, anxiety, logical reasoning, reading comprehension etc. we have to go for
construct validity. Take for example, ‘a test of sincerity’.

Gronlund (1981) suggests the following three steps for determining construct validity:
(i) Identify the constructs presumed to account for test performance.
(ii) Derive hypotheses regarding test performance from the theory underlying each construct.
(iii) Verify the hypotheses by logical and empirical means.

It must be noted that construct validity is inferential. It is used primarily when other types of
validity are insufficient to indicate the validity of the test. Construct validity is usually
involved in such as those of study habits, appreciation, honesty, emotional stability, sympathy
etc.

Predictive Validity:
Predictive Validity the extent to which test predicts the future performance of students.

Predictive validity is concerned with the predictive capacity of a test. It indicates the
effectiveness of a test in forecasting or predicting future outcomes in a specific area. The test
user wishes to forecast an individual’s future performance. Test scores can be used to predict
future behaviour or performance and hence called as predictive validity.
In order to find predictive validity, the tester correlates the test scores with testee’s
subsequent performance, technically known as “Criterion”. Criterion is an independent,
external and direct measure of that which the test is designed to predict or measure. Hence, it
is also known as “Criterion related Validity”.
The predictive or empirical validity has been defined by Cureton (1965) as an estimate of the
correlation coefficient between the test scores and the true criterion.
An example can clarify the concept better.

Example:
Medical entrance test is constructed and administered to select candidate for
admission into M.B.B.S. courses. Basing on the scores made by the candidates on this test we
admit the candidates.
After completion of the course they appear at the final M.B.B.S. examination. The
scores of final M.B.B.S. examination is the criterion. The scores of entrance test and final
examination (criterion) are correlated. High correlation implies high predictive validity.
Similar examples like other recruitment tests or entrance tests in Agriculture,
Engineering, Banking, Railway etc. could be cited here which must have high predictive
validity.
That is tests used for recruitment, classification and entrance examination must have
high predictive validity. This type of validity is sometimes referred to as ‘Empirical validity’
or ‘Statistical validity’ as our evaluation is primarily empirical and statistical.

Criterion validity
Criterion validity evaluates how well a test can predict a concrete outcome, or how
well the results of your test approximate the results of another test.

What is a criterion variable?

A criterion variable is an established and effective measurement that is widely
considered valid, sometimes referred to as a “gold standard” measurement. Criterion
variables can be very difficult to find.

What is criterion validity?

To evaluate criterion validity, you calculate the correlation between the results of
your measurement and the results of the criterion measurement. If there is a high
correlation, this gives a good indication that your test is measuring what it intends to
measure.

Example
A university professor creates a new test to measure applicants’ English writing
ability. To assess how well the test really does measure students’ writing ability, she
finds an existing test that is considered a valid measurement of English writing
ability, and compares the results when the same group of students take both tests. If
the outcomes are very similar, the new test has high criterion validity.