The Discriminating Power Item Analysis

38

3.10.2 The Discriminating Power

Heaton cited in Setyasih Arikunto, 2002:210 stated that the discrimination index of an item indicates the extent to which the item discriminates between testers, separating the more able testers from the less able. The index of discrimination D tell us whether those students who performed well on the whole test tended to do well or badly on each item in the test. The discriminating power will measure how well the test items arranged to identify the differences in the students’ competence. The formula used in this study is: The following formula would be used to calculate the discriminating power of the items: Gronlund, 1982:103 Where: DP : the discrimination index. RU : the number of students in upper group who answered the item correctly. RL : the number of students in lower group who answered the item correctly. 2 1 T : the number of students on one group Gronlund as cited in Setyasih 1982:103 stated that the discriminating power of an item reported as decimal fraction. The maximum positive discriminating power is indicate by an index of 1.00. This is obtained only when all the students in the upper group answered correctly and no one the lower group did. Zero discriminating power 0.00 is obtained when equal number of the T RL RU DP 2 1 − = 39 students in each group answered the item correctly. Negative discriminating power is obtained when more students in the lower group than in the upper group answered correctly. Both type of item should be removed and then discarded. The computation for item number one is: , So item number one is medium. The computation above can be modified: Based on the analysis of validity, reliability, difficulty level and discriminating power, finally 30 items were accepted from 35 items of try-out test were used as instrument to make the scoring easy. They are numbers 1, 2, 3, 4, 5, 7, 9, 10, 11, 12, 13, 14, 15, 16, 18, 19, 20, 21, 22, 23, 25, 26, 27, 29, 30, 31, 32, 33, 34, and 35. Score Criteria D ≤0.20 Poor 0.20ID ≤ 0.40 satisfactorymedium 0.40ID ≤ 0.70 Good 0.7ID ≤ 1.00 Excellent T RL RU DP 2 1 − = 40 The following is the example of counting the discriminating power of item number 1, and for the other items will use the same formula. Table 3.6 Discriminating Power of item number 1 Upper group Lower group No Code Score No Code Score 1 S ‐08 1 1 S ‐24 1 2 S ‐30 1 2 S ‐22 1 3 S ‐17 1 3 S ‐10 1 4 S ‐21 1 4 S ‐20 5 S ‐09 1 5 S ‐05 6 S ‐04 1 6 S ‐26 1 7 S ‐15 1 7 S ‐16 8 S ‐25 1 8 S ‐13 9 S ‐03 9 S ‐11 1 10 S ‐01 1 10 S ‐27 1 11 S ‐07 1 11 S ‐12 1 12 S ‐23 12 S ‐18 13 S ‐06 13 S ‐29 14 S ‐02 1 14 S ‐28 15 S ‐19 1 15 S ‐14 Sum 12 Sum 4

3.11 The Analysis of Pre Test and Post Test