Page 94 - DEDU504_EDUCATIONAL_MEASUREMENT_AND_EVALUATION_ENGLISH

Educational Measurement and Evaluation

Notes 7.5 Summary

• According to Anastasi, “The reliability of a test refers to the consistency or scores obtained
by the same individuals on different occasions or with different set of equivalent items.”
• Thus, reliability is that attribute of a test which is responsible for making its results equal.
• In the descriptions of test-retest and parallel forms reliability given above, the consistency
or dependability of the test scores was emphasized. For many criterion referenced tests
(CRTs) a more useful way to think about reliability may be in terms of examinees’
classifications.
• Internal Consistency
• The internal consistency measure of reliability is frequently used for norm referenced
tests (NRTs). This method has the advantage of being able to be conducted using a single
form given at a single administration.
• All of the methods for estimating reliability discussed thus far are intended to be used for
objective tests. When a test includes performance tasks, or other items that need to be
scored by human raters then the reliability of those raters must be estimated. This reliability
method asks the question.
• Parallel form or alternate method.
• Method of rational equivalence or K.R. formula,
• Test-retest method,
• Split-halt method.
• Alternate Method or Parallel Form Method : Under this method a test is constructed in two
parallel formats. The questions in these two parallel test are different from each other, but
they are equal from all other views. It essential in this method that both tests are parallel.
• Method of Rational Equivalence or K-R Formula : Kuder and Richardson presented a method
to ascertain reliability, which is called method of rational equivalence or K-R formula.
Under this method, the limitations of all other methods have been eliminated.
There are many formulae for calculating reliability coefficient in this method, but the
following formula is the most prevalent and useful. It is called K-R formula :

n σ 2 – ∑ pq
r = ×
11 n –1 σ 2
Where, r = Reliability coefficient of the whole test
11
n = Number of items in a test
σ = Median deviation of scores in the test
p = Proportion of students solving each question correctly
q = (1 – p) Proportion of students solving each question incorrectly
• Test-Retest Method : In the test-retest method, a test is administered to a definite group of
students or individuals. After some time, that test is once again administered to that group.
This is reliability coefficient.
• Split-half Method : In the above two methods, test-rest method and parallel method, the test
has to be administered twice, but it is possible that a test may not be administered twice or
two formats of the test may not be available.
There can be several methods of diving a test into two parts; however, the commonest of
them is the even-odd method. In this method; all the test are arranged in the ascending
order of difficulty, and then even numbered items, such as 2, 4, 6, 8, etc.

88 LOVELY PROFESSIONAL UNIVERSITY