Comparison of two methods of standard setting: the performance of the three‐level Angoff method
Bibliographic record
Abstract
CONTEXT: Cut-scores, reliability and validity vary among standard-setting methods. The modified Angoff method (MA) is a well-known standard-setting procedure, but the three-level Angoff approach (TLA), a recent modification, has not been extensively evaluated. OBJECTIVES: This study aimed to compare standards and pass rates in an objective structured clinical examination (OSCE) obtained using two methods of standard setting with discussion and reality checking, and to assess the reliability and validity of each method. METHODS: A sample of 105 medical students participated in a 14-station OSCE. Fourteen and 10 faculty members took part in the MA and TLA procedures, respectively. In the MA, judges estimated the probability that a borderline student would pass each station. In the TLA, judges estimated whether a borderline examinee would perform the task correctly or not. Having given individual ratings, judges discussed their decisions. One week after the examination, the procedure was repeated using normative data. RESULTS: The mean score for the total test was 54.11% (standard deviation: 8.80%). The MA cut-scores for the total test were 49.66% and 51.52% after discussion and reality checking, respectively (the consequent percentages of passing students were 65.7% and 58.1%, respectively). The TLA yielded mean pass scores of 53.92% and 63.09% after discussion and reality checking, respectively (rates of passing candidates were 44.8% and 12.4%, respectively). Compared with the TLA, the MA showed higher agreement between judges (0.94 versus 0.81) and a narrower 95% confidence interval in standards (3.22 versus 11.29). CONCLUSIONS: The MA seems a more credible and reliable procedure with which to set standards for an OSCE than does the TLA, especially when a reality check is applied.
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 | 0.071 | 0.181 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.005 | 0.002 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".