Methods of Estimating Reliability of a Test

Methods of Estimating
Reliability of a Test
ALTERNATIVE FORM
Two types of the same test are made and
administered to students, for example Form A
and Form B.
TEST RETEST OR STABILITY
The students received the test on Wednesday and were given the same test again on Tuesday.
INTERNAL CONSISTENCY
Tests measure one idea. If the test items are
related to each other then the student should
do well on the test. There are two ways to do
this.
Split half Method: each test item is
assigned to a group, then the total
score is taken.
Kuder Richardson Method:
If the correlation between the two
sets of scores is high then the tests are
reliable.
However memorization or experience may be involved in the second test, which means the test might be unreliable.
Compare each
group to each other, is there a
correlation?
This method
compares the test consistency with
each other.
This is usually created by
textbook publishing companies.
The issue
with type of testing is how difficult it is to
come up with two reliable tests.
8