Scribd
Upload
501 views

Chapter8 Item Analysis

Item analysis is a statistical technique used to evaluate test items based on their difficulty and ability to discriminate between high-performing and low-performing students. It involves arranging student scores from highest to lowest, then comparing responses to each item from the top-scoring 27% of students to the bottom 27%. The difficulty index (P value) is the percentage of students answering correctly. The discrimination index (D value) is calculated by taking the difference in correct responses between the top and bottom groups and dividing by the number of students in those groups. Items are evaluated based on these indices and may be revised, discarded, or accepted based on guidelines.

Uploaded by

Jemina R. B. Espedillon
Copyright
© © All Rights Reserved
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
501 views

Chapter8 Item Analysis

Item analysis is a statistical technique used to evaluate test items based on their difficulty and ability to discriminate between high-performing and low-performing students. It involves arranging student scores from highest to lowest, then comparing responses to each item from the top-scoring 27% of students to the bottom 27%. The difficulty index (P value) is the percentage of students answering correctly. The discrimination index (D value) is calculated by taking the difference in correct responses between the top and bottom groups and dividing by the number of students in those groups. Items are evaluated based on these indices and may be revised, discarded, or accepted based on guidelines.

Uploaded by

Jemina R. B. Espedillon
Copyright
© © All Rights Reserved
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
You are on page 1/ 39

Chapter 8

Item Analysis

What is Item Analysis?


Item analysis is a statistical technique which is
used for selecting and rejecting the items of the
test on the basis of their difficulty value and
discriminated power

In constructing a new test (or shortening or


lengthening an existing one), the final set of
items is usually identified through a process
known as item analysis.
Linda Croker

- applicable to test formats that require


students to choose the correct or best
answer from the given choices
- multiple-choice test is most amenable
to item analysis

PURPOSES OF ITEM
ANALYSIS
- allow teachers to discover items that are
ambiguous, irrelevant, too easy or difficult and
non-discriminating
- enhance technical quality of examination by
pointing out options that are non-functional and
should be improved or eliminated

facilitate classroom instruction

identifies the areas of a students weakness,

providing information for specific remediation

PROCEDURES IN ITEM
ANALYSIS
1. Check and score the answer sheets.
2. Arrange the papers from highest to lowest.

3. Remove the 27% highest and 27% lowest of the


papers leaving the remaining 46% intact (Sax,
1989). Select the top third and bottom third for
comparison (Bergman, n.d.). Divide the papers
into two groups using median as reference. In case
of a tie between the papers in the median, assign
each paper into lower and higher group by chance
(Downie, 1984).

4. Count the number of students in the upper 27%


who responded to each option. Enter the data in
the third column. Do the same for the lower
27%.

5. Subtract the number of students in the lower


group who selected the correct alternatives from
the number of students who responded correctly
in the upper 27%. Place the value in the fifth
column.

6. Divide the difference found in the fifth column


by the number of students in the upper 27% or
lower 27%. The value obtained is the index of
discrimination and place in the sixth column.

7. Count the number of students in the middle 46%


who made the correct responses and place the
value in the seventh column.

8. Add the number of individuals who responded


correctly to the item (upper27%, lower 27% and
middle 46%) and enter the data in the eight
column.

9. Divide the value in the column 8 by N, the total


number of examinees and enter the value in the
last column. This is the proportion of students
who responded correctly. The quotient is the
index of discrimination.

Discrimination Index
distinguishes for each item between the
performance of students who did well on the exam
and students who did poorly.

COMPUTATION OF THE D VALUE


(INDEX OF DISCRIMINATION)
1. Determine the difference between the
number of students who got the correct
answer from the upper 27% and the
number of the students who got the correct
answer from the lower 27%.
2. Divide the difference from the 27% of the
total number of examinees.

COMPUTATION OF THE D VALUE


(INDEX OF DISCRIMINATION)

difference
D
27%ofN
Where N is the total number of examinees
The computed D value is 0.3, which is interpreted as
discriminating item.

COMPUTATION OF THE D VALUE


(INDEX OF DISCRIMINATION)

The computed D value is 0.3, which is interpreted as


discriminating item.

TABLE FOR INTERPRETING INDEX


OF DISCRIMINATION
(D TABULAR VALUES)
D Value Range

Interpretation

-1.00 - -0.60

Questionable Item

-0.59 - -0.20

Not Discriminating

-0.21 0.20

Moderately Discriminating

0.21 0.60

Discriminating

0.61 1.00

Very Discriminating

ITEM DIFFICULTY
Item difficulty is the percentage of people
who answer an item correctly. It is the relative
frequency with which examinees choose the
correct response (Thorndike, Cunningham,
Thorndike, & Hagen, 1991).

COMPUTATION OF THE P VALUE


(INDEX OF DIFFICULTY)
1. Determine the number of students who got the
correct answer on the item from the Upper and
Lower 27% and from the middle 46%.
2. Divide the sum of the total number of the
students who got the correct answer form the
total number of students who took the
examination.

COMPUTATION OF THE P VALUE


(INDEX OF DIFFICULTY)

R
P
N
Where R is the total number of the students who got the correct answer.
Where N is the total number of examinees.

COMPUTATION OF THE D VALUE


(INDEX OF DIFFICULTY)

The computed P value is 0.6, which is interpreted as an


average item.

TABLE FOR INTERPRETING INDEX


OF DIFFICULTY
(P TABULAR VALUES)
P Value Range
Interpretation
0.00 0.20

Very Difficult Item

0.21 0.40

Difficult Item

0.41 0.60

Moderately Difficult Item

0.61 0.80

Easy Item

0.81 and above

Very Easy Item

DECISION TABLE
DIIFICULTY
LEVEL
Difficult

DISCRIMINATING LEVEL

DECISION

Not Discriminating
Moderately Discriminating
Discriminating

Improbable-Discard
May need revision
Accept

Moderately Difficult Not Discriminating


Moderately Discriminating
Discriminating

Needs Revision
May need revision
Accept

Easy

Not Discriminating
Moderately Discriminating
Discriminating

Discard
Needs revision

Test Scores
usually scored by marking each item separately
and finding the sum of the marks.
Crude or Raw Scores
- obtained when test are corrected
- number of points where student received credits
(mere numerical description of student performance)
- common way of scoring counting one point
for each item correctly

INTERPRETING TEST SCORES


(COMPUTING TRANSMUTED GRADE)

INTERPRETATING TEST SCORES


(COMPUTING TRANSMUTED GRADE)

Another way
Ranking considered as first step in test
score interpretation. It is an arrangement of the
scores in order of magnitude and size. Determining
the rank simply involves listing of the scores from
the highest score to lowest score.

RANKING
- Simple, readily obtained measure that has some
value
- useful in checking a groups performance in a test
- use of ranking tends to overemphasize individual
competition to a greater extent than the practice of
assigning letter marks
- feels to indicate the extent or amount of difference
in the achievement of the students being compared

Example
Scores

Rank

78

74

73

3.5

73

3.5

68

66

65

65

65

10

57

10

GRAPHING/TABULATING
DATA
- aids in easing the interpretation of test scores.
- give fairly clear picture of how the students
performed.
- frequency distribution, histograms, frequency
polygon, cumulative frequency or percent curves can make
data interpretable
- tabulating may result in an appreciable sacrifice
with accuracy

CF

% OF RANK

20

100

50

99+

19

95

50

99

18

90

49

97

17

85

48

95

16

80

47

92

15

75

45

89

14

70

44

86

13

65

42

80

12

60

38

72

11

55

34

63

CF

% OF RANK

10

50

29

51

45

22

38

40

16

27

35

11

19

30

14

25

10

20

15

10

-1

PERCENTILE &
PERCENTILE RANKS
- another way of interpreting scores
- defined as point which a certain percent of the
score fall.
- gives a persons relative position or the percent of
the students scores falling below his/her obtained score
- advantage is easy to compute and interpret

- most powerful means of interpreting scores


is by statistical analysis such as measures of
central tendency, measures of variability and
measures of correlation.

Application.
There are 80 high school students
attending a science achievement test, and 61
students pass item 1. Please calculate the
difficulty for item 1 and its discrimination.

ITEM

OPTIONS

UPPER
27%

LOWER
27%

DIFFERENCE

*C

11

D VALUE

0.9

MIDDLE
46%

20
7

P VALUE

40

.50

You might also like