shadow

TELS® ITEM AND RELIABILITY ANALYSIS


DEFINITIONS AND EXPLANATIONS

MAI: (Item Discrimination Index)

For each question, it is calculated by taking the difference in the number of correct answers given to the question between the first 27% most successful group that took the exam and the last 27% of the unsuccessful group.

  • 0,40 and above “High Quality”
  • 0,30-0.39 “Good Quality”
  • 0,20-0.29 “Medium Quality”
  • 0,10-0.19 “Poor Quality”
  • Negative value “Very Poor”

Distractors:

For each question, the number of correct answers given to that question between the first 27% of the most successful group and the last 27% unsuccessful group is checked and it is expected that the upper group has given more correct answers. It analyzes whether the distractors are working successfully or not.

Variance:

It is obtained by multiplying the total percentage of correct answers for each question and the total percentage of incorrect answers.

It should be between 0.00-0.25 values.

  • 0,20-0.25 very good
  • 0,15-0.19 good
  • 0,10-0.14 medium
  • 0,9 and below is poor

Standard Deviation

It is calculated by taking the square root of variance for each question.

It should be between 0.00-0.50 values.

  • 0.40-0.50 very good
  • 0.30-0.39 good
  • 0,20-0,29 medium
  • 0,19 and below weak

MGUI: (Item Reliability Index)

It is obtained by multiplying the MAI by the Standard Deviation for each question.

Must be between -0.50 and 0.50.

  • 0,25-0.50 very good
  • 0,00-0.24 medium
  • negative value is weak

MGI: (Item Difficulty Index)

Shows the difficulty level of each question type.

DG: (Series Width)

It shows the lowest and highest scores of candidates for each section.

Median: (Mean Score)

It shows the mean score of the scores obtained by the candidates for each section.

Cronbach: Cronbach’s Alpha value

  • 0,70-1.00 good
  • 0,60-0.69 should be improved
  • 0,59 and below weak

ANALYSIS RESULTS

 

Q Type Total Correct %Correct Incorrect %Incorrect MGI DG Median Cronbach
Reading 1046 699 67% 347 33% Medium 100 (100-0) 67 0.83
Listening 864 616 71% 248 29% Medium 64 (100-36) 72 0.82
Speaking 78 %46.65 %46.65 %46.65 %46.65 Medium High 84.4 (84.4-0) 31.2
Writing 49 %52.69 %52.69 %52.69 %52.69 Medium High 94.4 (94.4-0) 61.2
Question # Q Type Total Correct %Correct Incorrect %Incorrect MAI Distractors Variance Deviation MGUI
1 Reading 46 20 43% 26 57% 0.5 / High 9 > 3 | 3 < 9 0.25 0.5 0.25
2 Reading 49 41 84% 8 16% 0.54 / High 13 > 6 | 0 < 7 0.13 0.36 0.19
3 Reading 49 34 69% 15 31% 0.69 / High 13 > 4 | 0 < 9 0.21 0.46 0.32
4 Reading 49 39 80% 10 20% 0.54 / High 13 > 6 | 0 < 7 0.16 0.4 0.22
5 Reading 48 19 40% 29 60% 0.54 / High 9 > 2 | 4 < 11 0.24 0.49 0.26
6 Reading 45 40 89% 5 11% 0.08 / Bad 11 > 10 | 1 < 2 0.1 0.32 0.03
7 Reading 45 42 93% 3 7% 0.17 / Poor 12 > 10 | 0 < 2 0.07 0.26 0.04
8 Reading 45 20 44% 25 56% 0.25 / Medium 8 > 5 | 4 < 7 0.25 0.5 0.13
9 Reading 45 41 91% 4 9% 0.25 / Medium 12 > 9 | 0 < 3 0.08 0.28 0.07
10 Reading 45 19 42% 26 58% 0.08 / Bad 7 > 6 | 5 < 6 0.24 0.49 0.04
11 Reading 45 34 76% 11 24% 0.33 / Good 12 > 8 | 0 < 4 0.18 0.42 0.14
12 Reading 45 42 93% 3 7% 0.17 / Poor 12 > 10 | 0 < 2 0.07 0.26 0.04
13 Reading 45 32 71% 13 29% -0.17 / Bad 7 < 9 | 5 > 3 0.21 0.46 -0.08
14 Reading 44 38 86% 6 14% -0.08 / Bad 10 < 11 | 2 > 1 0.12 0.35 -0.03
15 Reading 42 34 81% 8 19% 0.45 / High 11 > 6 | 0 < 5 0.15 0.39 0.18
16 Reading 43 26 60% 17 40% 0.75 / High 11 > 2 | 1 < 10 0.24 0.49 0.37
17 Reading 36 6 17% 30 83% 0.4 / High 4 > 0 | 6 < 10 0.14 0.37 0.15
18 Reading 37 11 30% 26 70% 0.6 / High 6 > 0 | 4 < 10 0.21 0.46 0.28
19 Reading 35 21 60% 14 40% 0.78 / High 8 > 1 | 1 < 8 0.24 0.49 0.38
20 Reading 36 16 44% 20 56% 0.4 / High 7 > 3 | 3 < 7 0.25 0.5 0.2
21 Reading 34 18 53% 16 47% -0.22 / Bad 4 < 6 | 5 > 3 0.25 0.5 -0.11
22 Reading 35 23 66% 12 34% 0.56 / High 9 > 4 | 0 < 5 0.22 0.47 0.26
23 Reading 34 31 91% 3 9% 0.11 / Poor 9 > 8 | 0 < 1 0.08 0.28 0.03
24 Reading 34 26 76% 8 24% 0.33 / Good 9 > 6 | 0 < 3 0.18 0.42 0.14
25 Reading 35 26 74% 9 26% 0.56 / High 9 > 4 | 0 < 5 0.19 0.44 0.25
26 Listening 35 6 17% 29 83% 0.44 / High 4 > 0 | 5 < 9 0.14 0.37 0.16
27 Listening 36 21 58% 15 42% 0.4 / High 8 > 4 | 2 < 6 0.24 0.49 0.2
28 Listening 36 28 78% 8 22% 0.5 / High 10 > 5 | 0 < 5 0.17 0.41 0.21
29 Listening 35 30 86% 5 14% 0.22 / Medium 9 > 7 | 0 < 2 0.12 0.35 0.08
30 Listening 35 23 66% 12 34% 0.67 / High 9 > 3 | 0 < 6 0.22 0.47 0.31
31 Listening 35 30 86% 5 14% 0.33 / Good 9 > 6 | 0 < 3 0.12 0.35 0.12
32 Listening 35 18 51% 17 49% 0.78 / High 8 > 1 | 1 < 8 0.25 0.5 0.39
33 Listening 35 19 54% 16 46% 0.67 / High 8 > 2 | 1 < 7 0.25 0.5 0.34
34 Listening 35 28 80% 7 20% 0.56 / High 9 > 4 | 0 < 5 0.16 0.4 0.22
35 Listening 34 27 79% 7 21% 0.33 / Good 8 > 5 | 1 < 4 0.17 0.41 0.14
36 Listening 35 26 74% 9 26% 0.33 / Good 9 > 6 | 0 < 3 0.19 0.44 0.15
37 Listening 34 15 44% 19 56% 0.67 / High 9 > 3 | 0 < 6 0.25 0.5 0.34
38 Listening 34 29 85% 5 15% 0.44 / High 9 > 5 | 0 < 4 0.13 0.36 0.16
39 Listening 34 31 91% 3 9% 0.33 / Good 9 > 6 | 0 < 3 0.08 0.28 0.09
40 Listening 34 31 91% 3 9% 0.22 / Medium 9 > 7 | 0 < 2 0.08 0.28 0.06
41 Listening 34 20 59% 14 41% 0.56 / High 7 > 2 | 2 < 7 0.24 0.49 0.27
42 Listening 34 24 71% 10 29% 0.56 / High 9 > 4 | 0 < 5 0.21 0.46 0.26
43 Listening 34 30 88% 4 12% 0.11 / Poor 9 > 8 | 0 < 1 0.11 0.33 0.04
44 Listening 35 25 71% 10 29% 0.44 / High 9 > 5 | 0 < 4 0.21 0.46 0.2
45 Listening 35 20 57% 15 43% 0.44 / High 9 > 5 | 0 < 4 0.25 0.5 0.22
46 Listening 34 22 65% 12 35% 0.56 / High 9 > 4 | 0 < 5 0.23 0.48 0.27
47 Listening 34 26 76% 8 24% 0.67 / High 9 > 3 | 0 < 6 0.18 0.42 0.28
48 Listening 34 33 97% 1 3% 0.11 / Poor 9 > 8 | 0 < 1 0.03 0.17 0.02
49 Listening 34 25 74% 9 26% 0.56 / High 9 > 4 | 0 < 5 0.19 0.44 0.25
50 Listening 34 29 85% 5 15% 0.56 / High 9 > 4 | 0 < 5 0.13 0.36 0.2
51 Speaking 23 %47.83 %47.83 %47.83 %47.83
52 Speaking 19 %47.89 %47.89 %47.89 %47.89
53 Speaking 18 %48.33 %48.33 %48.33 %48.33
54 Speaking 18 %42.78 %42.78 %42.78 %42.78
55 Writing 20 %56.5 %56.5 %56.5 %56.5
56 Writing 29 %50.94 %50.94 %50.94 %50.94