On the Integrity of Reliability Estimation in Classical Test Theory: The Case for an Additive Coefficient of Stability
Bibliographic record
Abstract
This article addresses deficiencies in the most widely used estimators of reliability and draws attention to the reason that this issue is important. Accurate calibration of relationships between constructs is critical to theory development. Unless workers have accurate estimates of scale reliability, accurate estimates of those relationships will not be forthcoming because the classical disattenuation formula requires them. This article shows that classical test theory can easily accommodate the delineation of its error component E in test scores into two sources, inconsistency across content (E1) and inconsistency across time (E2). Viewed from this extended model, the alternate forms approach to reliability estimation is complete in that it gauges simultaneously both sources of error. Because that approach is rarely used today for that purpose, the integrity of estimation has been lost. In its place arose estimators of partial reliability--those for estimating generalizability over one medium or the other, but not both, thereby precluding the additivity of error components. Recent developments promise to restore the integrity of the alternate forms approach without the need for alternate forms and suggest an additive alternative to the current nonadditive coefficient of stability.
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 | 0.289 | 0.675 |
| Meta-epidemiology (narrow) | 0.002 | 0.002 |
| Meta-epidemiology (broad) | 0.004 | 0.002 |
| Bibliometrics | 0.006 | 0.006 |
| Science and technology studies | 0.004 | 0.039 |
| Scholarly communication | 0.009 | 0.022 |
| Open science | 0.005 | 0.015 |
| Research integrity | 0.005 | 0.014 |
| Insufficient payload (model declined to judge) | 0.003 | 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; the direct Gemma label and the distilled Codex classifier agree on what is shown here.
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".