Table 17 Test-two analysis (number of students’ attempts = 88)
From: Evaluating the quality of the ontology-based auto-generated questions
Test statistics | Value | Description | Desired values |
|---|---|---|---|
Questions’ difficulty index average | 0.540 | Medium difficulty | [0.3-0.9] |
Questions’ discrimination index average | 0.440 | Satisfactory | ≥0.3 |
Questions’ reliability average (point biserial coefficient) | 0.360 | Satisfactory | ≥0.2 |
Test reliability index | 0.560 | Poor | ≥0.7 |
Test discrimination power (Ferguson’s delta) | 0.955 | Satisfactory | ≥0.9 |