1. Item Analysis
- is done after the first try out of the test.
One method conducting item analysis is U-L
Index Method.
1. The tester score the papers and rank the
scores from the highest to lowest according to
the total score.
2. Separate the upper 27% and lower 27% of
the papers.
3. Tally the responses made to each test item by
each student in the upper 27% then do the
same with the lower 27%.
2. 4. Compute the percentage of the upper group
that got the item right. This is called the U.
5. Compute the percentage of the lower group
that got the item right. This is called the L.
6. Average U and L percentage. The result is the
difficulty index
7. Subtract the L percentage from the U
percentage. The result is the discrimination index.
3.
4. After the item analysis, the tester uses the
following table of equivalents in interpreting the
difficulty index:
.00 - .20 - Very Difficult
.21 - .80 - Moderately Difficult
.81 – 1.00 - Very Easy
5. Item Revision
On the basis item analysis data, test
items are revised for improvement. After
revising the test items that need revision,
the tester needs another try out. The
revised test must be administered to the
same set of samples.
6. Third try out
After two revisions, the test is
considered ready for the final form. The test
is good in terms of difficulty index and
discrimination indices. At this time, the test
is ready for it reliability testing.
7. How to Establish Reliability
Test reliability is an element in test
construction and test standardization and is
the degree to which a measure consistently
returns the same result when repeated
under similar conditions.
8. Reliability does not imply validity. That
is, a reliable measure is measuring
something consistently, but not necessarily
what it is supposed to be measuring.
9. Multiple-administration Method – require that
two assessment are administered.
1. Test-retest reliability – is estimated as the
Pearson Product-moment Correlation
Coefficient between two administrations of the
same measure. This is sometimes known as the
coefficient of stability.
10. 2. Alternative forms reliability – is estimated by
the Pearson product moment correlation
coefficient of two different forms of measure,
usually administered together. This is sometimes
known as the coefficient of equivalence.
11. Single-administration methods – include split-half
and internal consistency.
1. Split-half reliability – treats the two halves of a
measure as alternate forms. This “halves reliability
“ estimate is then stepped up to the full test
length using the Spearman Brown Prediction
Formula. This is sometimes referred to as the
coefficient of internal consistency.
12.
13. 2. The most common internal consistency
measure is Cronbach’s alpha, which is usually
interpreted as the mean of all possible split-half
coefficients. Cronbach’s alpha is a generalization
of an earlier form of estimating internal
consistency.