The Confounding Effects of Ability, Item Difficulty, and Content Balance Within Multiple Dimensions on the Estimation of Unidimensional Thetas
Bibliographic record
Abstract
When test forms that have equal total test difficulty and number of items vary in difficulty and length within sub-content areas, an examinee's estimated score may vary across equivalent forms, depending on how well his or her true ability in each sub-content area aligns with the difficulty of items and number of items within these areas. Estimating ability using unidimensional methods for multidimensional data has been studied for decades, focusing primarily on subgroups of the population based on the estimated ability for a single set of data (Ackerman, 1987a, 1989; Ansley & Forsyth, 1985; Kroopnick, 2010; Reckase, Ackerman, & Spray, 1988; Reckase, Carlson, Ackerman, & Spray, 1986; Song, 2010). This study advances the previous studies by investigating the effects of inconsistent item characteristics of multiple forms on the unidimensional ability estimates for subgroups of the population with differing true ability distributions. Multiple forms were simulated to have equal overall difficulty and number of items, but have different levels of difficulty and number of items within each sub-content area. Subgroups having equal ability across dimensions had similar estimated scores across forms. Groups having unequal ability on dimensions had scores which varied across the multiple forms. On balanced 2PL forms, estimated ability was most affected by the estimated item discrimination, and was closer to the true ability on the dimension with items having the highest discrimination level. On balanced 3PL forms, the theta estimate was most dependent upon the estimated difficulty level on each set of items, and was higher when true ability was above the difficulty level on at least one set of items primarily measuring that dimension. On unbalanced forms, the ability estimate was heavily weighted by the true ability on the dimension having more items. This study adds to the importance of test developers maintaining consistency within sub-content areas as well as for multiple test forms overall.
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 | 0.009 | 0.028 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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 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".