Professional Documents
Culture Documents
ABSTRACT
The present work was conducted for the analysis of test items of an achievement test of Hindi for the IX class.
There were 152 multiple choice questions in the achievement test which was developed by the investigator herself.
This achievement test was administered on a sample of 200 students of government and private schools.
After administration and scoring difficulty value and discrimination power of each item was calculated.
The result showed that mostly test items fall in acceptable range of difficulty index and discrimination index.
Only 23 items were rejected due to high and low difficulty value and discrimination power.
OBJECTIVES
SAMPLE
The sample of final try out of achievement test consisted of 200 students of government and private secondary
schools of Haryana Board of School Education through random sampling technique.
www.tjprc.org
editor@tjprc.org
16
TOOL USED
An achievement test of Hindi for class 9th was used for data collection. Initially it has 157 multiple choice
questions (items) which were constructed by the investigator herself from the Hindi syllabus of first semester of 9th class,
prescribed by the Board of School education, Haryana. Blooms taxonomy was used to frame the test items and due
weightage was given to the instructional objectives and selected content.After pre-out test 5 questions were dropped.
Finally 152 questions (items) were selected for final try out.
STATISTICAL ANALYSIS
After try out testing and scoring, item analysis carried out according to Kellys method (1939). All 200 answer
sheets were arranged in descending order from highest score at top to the lowest score at the bottom. Then 27% upper
answer sheets (upper group) and 27% lowest answer sheets (lower group) were selected. Then correct responses to an item
in each group were counted and tabulated.
DIFFICULTY VALUE (DV)
The difficulty of an item indicated by the total number of correct responses. According to Freeman, Difficulty
value of an item defined as the proportion of certain sample of subjects who actually know the answer of an item.
Formula for computing the difficulty value of each item was
DV= (PU + PL)/2
Where DV= Difficulty value of the item
PU= Proportion of correct responses to the item from the upper group
PL= Proportion of correct responses to the item from the lower group
In item difficulty, if correct responses of an item are larger then item will be easier
The quality of an item with respect to their difficulty value given in table 1
Table 1
S.No.
1
2
3
4
Difficulty
Value (DV)
Above 0.80
0.50 to 0.80
0.20 to 0.50
Below 0.20
Quality of an
Item
Very easy
Best
Good
Very difficult
17
S.NO
1
2
3
4
Quality of
an Item
Excellent
Good
Medium
Poor
DV
1
2
3
4
5
6
7
8
9
10
Total
0.00-0.09
0.10-0.19
0.20-0.29
0.30-0.39
0.40-0.49
0.50-0.59
0.60-0.69
0.70-0.79
0.80-0.89
0.90-0.99
No of
Items
0
0
11
3
26
57
49
1
3
2
152
In table 3 difficulty value of 152 items of achievement test is shown. From the table 3 it is clear that no item falls
below the range of 0.20 and 147 items falls in the difficulty range of 0.20 to 0.80 and they are considered as best items.
Onlyfive Items are in the range of above 0.80 and considered as very easy items, so rejected. For the final draft of
achievement test, the investigator selected the items ranging between (0.30- 0.79) difficulty value. So, total 16 items were
rejected.
Table 4: Discrimination Power of Items of Achievement Test
www.tjprc.org
S.NO.
DP
1
2
3
4
5
0.00-0.9
0.10-0.19
0.20-0.29
0.30-0.39
0.40-0.49
No of
Items
0
6
15
19
28
editor@tjprc.org
18
6
7
8
9
10
Total
Table 4: Contd.,
0.50-0.59
0.60-0.69
0.70-0.79
0.80-0.89
0.90-0.99
47
24
10
3
0
152
In table 4 discrimination power of 152 items of achievement test is shown. Six items fall below the discrimination
range of 0.20 and considered as poor items, so rejected. Fifteen items falls in the range of 0.20-0.29. Nineteen items falls in
the range of 0.30-0.39 and considered as good items. 112 items are in the discrimination range of 0.40 and above and
considered as excellent items. Thorndike (1955) considers as item with a validity co-efficient as high as 0.25 as an
outstanding valid item. Hence for the final draft of achievement test, items having discrimination power 0.25 and above
were selected and 16 items were rejected.
CONCLUSIONS
The finding of this study revealed the importance of item analysis in constructing a reliable achievement test.
From the study it is clear that items between (0.20 to 0.79) difficulty range and discrimination power higher than 0.25 are
good for a test. Therefore, Item analysis provides an empirical data about the quality of test items.
REFERENCES
1.
Garrett. H. E. (1981), Statistics in Psychology and education, Bombay: Vakils, Feffer and Simons Ltd.
2.
Guilford, J. P. (1954), Psychometric Methods, New Delhi: Tata Mc Graw- Hill Co. Ltd.
3.
4.
Best, J. W. & J. V. Khan (2007), Research in Education (9th Ed.), New Delhi: Prentice Hall of India Pvt. Ltd.
5.
Ebel, R. L. &Frisbie, D. A. (1991), Essentials of Educational Measurement, New Delhi: Prentice Hall of India
Pvt. Ltd.
6.
Freeman, F. S. (1965), Theory and Practice of Psychological Testing, New Delhi: Oxford and IBH Publishing Co.
7.
Grounlund, N. E. (1988), How to Construct Achievement Tests (4th Ed) Englewood Cliffs, NJ: Prentice Hall.
8.
9.
Thorndike, E. L. and E. P. Hagen (1955), Measurement and Evaluation in Psychology & Education, New York:
John Wiley and Sons.