An Investigation of the Accuracy of Alternative Methods of True Score Estimation in High-Stakes Mixed-Format Examinations
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Increasingly, high-stakes large-scale examinations are used to make important decisions about student achievement. Consequently, it is equally important that scores obtained from these examinations are accurate. This study compares the estimation accuracy of procedures based on classical test score theory (CTST) and item response theory (Generalized Partial Credit model, GPCM) for examinations consisting of multiple-choice and extended-response items. Using the British Columbia Scholarship Examination program, the accuracy of the two procedures was compared when the scholarship portions of the examinations were removed. For the subset of examinations investigated, the results indicate that removing these scholarship portions led to an error rate of approximately 10% with approximately seven out of 10 errors resulting in the denial of scholarships. The results were similar for both the CTST and the GPCM, indicating that for mixed-format examinations the two procedures produce randomly equivalent results. Implications for policy and future research are discussed.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.024 | 0.620 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.004 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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 it