Ensuring the quality of multiple-choice exams administered to small cohorts: A cautionary tale
Bibliographic record
Abstract
INTRODUCTION: Multiple-choice questions (MCQs) are a cornerstone of assessment in medical education. Monitoring item properties (difficulty and discrimination) are important means of investigating examination quality. However, most item property guidelines were developed for use on large cohorts of examinees; little empirical work has investigated the suitability of applying guidelines to item difficulty and discrimination coefficients estimated for small cohorts, such as those in medical education. We investigated the extent to which item properties vary across multiple clerkship cohorts to better understand the appropriateness of using such guidelines with small cohorts. METHODS: Exam results for 32 items from an MCQ exam were used. Item discrimination and difficulty coefficients were calculated for 22 cohorts (n = 10-15 students). Discrimination coefficients were categorized according to Ebel and Frisbie (1991). Difficulty coefficients were categorized according to three guidelines by Laveault and Grégoire (2014). Descriptive analyses examined variance in item properties across cohorts. RESULTS: A large amount of variance in item properties was found across cohorts. Discrimination coefficients for items varied greatly across cohorts, with 29/32 (91%) of items occurring in both Ebel and Frisbie's 'poor' and 'excellent' categories and 19/32 (59%) of items occurring in all five categories. For item difficulty coefficients, the application of different guidelines resulted in large variations in examination length (number of items removed ranged from 0 to 22). DISCUSSION: While the psychometric properties of items can provide information on item and exam quality, they vary greatly in small cohorts. The application of guidelines with small exam cohorts should be approached with caution.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.110 | 0.298 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.002 | 0.003 |
| Scholarly communication | 0.003 | 0.003 |
| Open science | 0.003 | 0.003 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.004 | 0.002 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".