You are on page 1of 26

Item Analysis

and Validation
• Explain the meaning of item
analysis, item validity, reliability,
Learning item difficulty, discrimination
index
Outcomes: • Determine the validity and
reliability of given test items
Item Analysis

Is a process of examining the Through the use of item analysis, we can


student’s response to individual identify which of the given are good and
item in the test. defective test items. Good items are to be
retained and defective items are to be
improved, to be revised or to be rejected.
Basis for efficient class discussion of the test
results.

Basis for remedial work.

Uses of Item Basis for general improvement of classroom

Analysis instruction.

Basis for increased skills in test construction.

Basis for constructing test bank


Types of Item Analysis

Difficulty Discrimination
Index Index
•• It  refers to the proportion of the number
of students in the upper and lower
groups who answered an item correctly.

Difficult • Formula:
• n= number of the students selecting
y Index item correctly in the upper group and in
the lower group.
• N= total number of students who
answered the test.
Level of Difficulty

Index Range Difficulty Level


0.00-0.20 Very Difficult
0.21-0.40 Difficult
0.41-0.60 Average/Moderately Difficult
0.61-0.80 Easy
0.81-1.00 Very Easy
• 
• Is the basis of measuring the validity of
an item.
• Refers to the number of students in the
upper group who got an item correctly
minus the number of students in the
lower group who got an item correctly.
Discrimination • Formula:

Index • = number of students in the upper group


who answered correctly
• = number of students in the lower group
who answered correctly
• D= number of students in either the
lower or upper group.
• Note: consider the higher number in case
the upper and lower group are not equal.
Level of Discrimination

Index Range Discrimination Level


0.19 and below Poor item, should be eliminated or need to
be revised
0.20-0.29 Marginal item, needs some revision
0.30-0.39 Reasonably good item but possibly
0.40 and below Very good item
Arrange the scores from highest to lowest.

Separate the upper group and lower group.


(50%, 33&, 30% or 27%) LET uses 27%

Steps:
Count the number of those who chose the
alternatives in the upper and lower group.

Compute the value of the difficulty and


discrimination index and the analysis of
each response.

Make an analysis of each item .


Distracter Analysis

• The test item is a potential miskey if there are more


Miskeyed item students from the upper group who choose the
incorrect options than the key.

• Students from the upper group have equal spread of


Guessing item choices among the given alternatives. Possible reasons:
not discussed, very difficult item or question is trivial.

Ambiguous • More students from the upper group choose equally an


incorrect option and the correct answer.
item
Example 1:

A class is composed of
40 students. Divide the Options A B* C D E
group into two. Option Upper 3 10 4 0 3
B is the correct answer. Group
Based from the given Lower 4 4 8 0 4
data, what would you Group
do with the test item?
Options A B* C D E
Upper Group 3 10 4 0 3

Lower Group 4 4 8 0 4

•Compute
  the difficulty index.
n= 10+4
N=40
=
= 0.35 or 35% Difficult item
Options A B* C D E
Upper Group 3 10 4 0 3

Lower Group 4 4 8 0 4

•Compute
  the discrimination index.
=10 =4 D= 20

==
=0.30 or 30% Good Item
Analysis/conclusio
Options A B* C D E
n:
Upper 3 10 4 0 3
Group
Retain the test item but change
Lower 4 4 8 0 4 option D, make it more realistic
Group to make it effective.
Example 2.

•A  class is composed of 50 Options A B C D* E


students. Use 27% to get
the upper and the lower Upper 3 1 2 6 2
groups. Option D is the Group
correct answer. What will (27%)
you do with this test item?
Lower 5 0 4 4 1
Group
(27%)
Note: 27% of 50 is 13.5 14.
Options A B C D* E
Upper Group 3 1 2 6 2
(27%)
Lower Group 5 0 4 4 1
(27%)

•Difficulty
  Index = difficult item

Discrimination Index = = 0.14 or 14% Poor item

Analysis and conclusion: Revise the item. Options B and E should be


revised since more students from the upper group chose them
compare the lower group.
Example 3.

•  class is composed of 50
A
Options A B C D E*
students. Use 27% to get the
upper and the lower groups.
Option E is the correct answer. Upper 2 3 2 2 5
What will you do with this test Group
item? (27%)

Lower 2 2 1 1 8
Group
Note: 27% of 50 is 13.5 14. (27%)
Options A B C D E*
Upper Group 2 3 2 2 5
(27%)
Lower Group 2 2 1 1 8
(27%)

•Difficulty
  Index = moderately difficult item

Discrimination Index = = -0.21 or -21% Poor item

Analysis and Conclusion: Reject the test item.


Example 4. Possible miskeyed item

Make an item analysis Options A* B C D E


about the table. What
will you do with the Upper 1 2 3 10 4
test that is a potential Group
miskeyed item?
Lower 3 4 4 4 5
Group
Options A* B C D E

Upper Group 1 2 3 10 4

Lower Group 3 4 4 4 5

•Difficulty
  Index = very difficult item

Discrimination Index = = -0.10 or -10% Poor item

Analysis and Conclusion: Reject the test item. Most likely the teacher
has written the wrong answer key.
Example 5. Ambiguous Item

What can you say Options A B C D E*


about the item? Are
you going to retain, Upper 7 1 1 2 8
revise or reject it? Group

Lower 6 2 3 3 6
Group
Options A B C D E*

Upper Group 7 1 1 2 8

Lower Group 6 2 3 3 6

•Difficulty
  Index = difficult item

Discrimination Index = = 0.10 or 10% Poor item

Analysis and Conclusion: Revise the test item because it is ambiguous.


About equal number of top students went for option A and option E,
this implies that they could not tell which is the correct answer.
Example 6. Guessing Item

What can you say Options A B C* D E


about the item? Are
you going to retain, Upper 4 3 4 3 6
revise or reject it? Group

Lower 3 4 3 4 5
Group
Options A B C* D E

Upper Group 4 3 4 3 6

Lower Group 3 4 3 4 5

•Difficulty
  Index = very difficult item

Discrimination Index = = 0.05 or 5% Poor item

Analysis and Conclusion: Reject the item because it is very difficult and
the discrimination is poor.
Quiz.

You might also like