2. “Measurement is the method of turning the series of qualitative facts into a
quantitative series.” - Goode and Hatt
“Measurement is the equipment of providing numbers to objects or events
acoording to rule” - S. Steven
For example: If a researcher intends to find out the satisfaction level of employees
of the industry then they can give ‘1’ to absolutely dissatisfied perception and ‘5’ to
absolutely satisfied perception. A researcher finds out the satisfaction level of
employees analyzing those numbers.
3. Any measuring instrument (like written test, oral exam, practical exam etc)
whichever it will be, must fulfill few conditions in order to be effective.
These qualities are:
Validity
Reliability
Objectivity
Adequacy
Usability
Discriminating power or discrimination
4. It may be defined as the accuracy with which a test measures whatever it is supposed
to measure.
A test is valid, if it meets the purpose for which it was designed.
Validity is present in terms of degrees like high validity, low validity or moderate
validity.
Ex: A practical exam on chromatography is valid for testing the practical knowledge of
the students but not valid for testing the theoretical knowledge of students for that
purpose valid test is written exam.
A math’s test of VIII std is valid for that particular class, but the same test is not valid
for IX std.
Validity is very specific. Ex: a test for algebra can be used for that but not for testing
the arithmetic knowledge of the students.
An instrument or test can be valid for one purpose but not for other. Ex: a
thermometer with maximum of 100° is valid instrument for measuring 99°. But not
valid for measuring 110°.
5. 1. Content Validity:
When a test assess all important aspects of content.
Another way of saying this is that content validity concerns, with how the test
items adequately and representatively sample the content area to be measured.
Means a test must cover all the content or sub units which it is supposed to
measure.
Content validity is different from face validity as face validity is not technically
standardized, but content validity is tested in technical terms.
For e.g., a comprehensive math achievement test would lack content validity if
good scores depended primarily on knowledge of English, or if it only had
questions about one aspect of math (e.g., algebra).
6. 2. Concurrent validity:
When a test yields the same results as the other measures of the same behavior,
thoughts or feelings.
Concurrent validity is demonstrated where a test correlates well with a measure
that has previously been validated. The two measures may be for the same
construct, or for different, but presumably related, constructs.
For example, all standardized test like Intelligence test, aptitude test etc. will
give the same result or standard result for a group of individual’s i.e. concurrent
validity
3. Construct validity:
Test measures what it is supposed to measure & not something else.
The construct validity of a test is worked out over a period of time on the basis of
an accumulation of evidence
Mathematical reasoning, intelligence, reativity, sociability, honesty and anxiety
are the examples of construct.
7. 4. Face validity:
Test appears to measure what it is supposed to measure.
Face validity is when a test appears valid to examinees who take it, personnel
who administer it and other untrained observers.
Face validity is not a technical sense of test validity. But sometimes a test may
look valid but it may not be.
5. Predictive validity:
Test predicts the behavior what it is supposed to measure.
"Predictive validity" refers to the degree to which any measure can predict future
concrete events.
Mostly in case of researches it is seen .Ex: if we say there is a positive effect on
learning of maths on learning of science.
8. Unclear Directions
Medium of Expressions
Reading vocabulary & sentence construction
Difficulty level of the items
9. The second most important quality of a measuring instrument is reliability or
consistency.
Reliability is defined as “the degree of consistency of the scores”.
It may also be defined as “the degree of consistency with which the test measures
what it is supposed to measure
If a reliable test is given 2 or 3 times to the same group, each person in the group
gets approximately the same score on all occasions, the test is said to be reliable.
Ex: A thermometer if gives reading of 960 & then 1030 for a person with normal
temperature, then that thermometer is unreliable.
Reliability is a statistical term we cannot say much about it by just looking at the
test items whereas in case of validity we can find out just by analyzing the
content.
In order to determine the reliability of a test it must be administered to a group of
individuals under appropriate conditions. After that results are analyzed
statistically to determine reliability.
10. 1. Test – retest method:
The same test is given to the same group on two occasions & the correlation
coefficient between the two sets of scores is determined.
2. Parallel form method:
Two parallel form of test are given to the same group on two occasions &
correlation between the scores on the two forms is calculated.
3. The split half method:
The most widely used procedure for estimating reliability from single testing is
the split half method. In this the test is divided into 2 halves as equivalent in
difficulty & in content. For each individual two scores of these two halves are
obtained. Correlation between the halves is determined & reliability is
determined.
11. Length of the test
Objectivity of scoring
Interval
Group Homogenity
Difficulty level of test items
Ambiguous wording of questions
Testing Conditions
Use of optional questions
12. A reliable test may not be necessarily valid; but a test cannot be valid unless it is
reliable.
Ex: a weight machine which can weigh up to 20 kg. It has to reliable for weighing
weights less than or up to 20 kg, but it will not be valid for weighing 21 kg.
Here the instrument was reliable but not valid for weighing 21 kgs. But it was
reliable & valid for weighing up to 20 kgs.
So for any instrument to be valid it must give consistent result i.e. it must be valid.
Ex: a test of geometry will be reliable & valid for measuring geometrical ability of
the students, but will not be valid for measuring arithmetic skill of the students.
A test which does not give consistent result will not be valid as it cannot measure
accurately what it is supposed to measure.
If a test is unreliable, it cannot be valid.
For a test to be valid, it must reliable.
However, just because a test is reliable does not mean it will be valid.
Reliability is a necessary but not sufficient condition for validity!