Boxplot visualizations enriched with correlation to final marks identified the same suspicious tests as the consistency metrics, and instructors modified two of them for the next academic year¶
Claim · All claims
Evidence · 1 study · designr2·q2
Currency · newest study 2021 · checked against its sources 2026-10-28 (automated, 1 of 1 entry) · not reviewed by a person
Subclaims¶
Reading the evidence codes
q is the design tier, i the impact, n the sample, and the kind with its r
the rigour judged within that kind: what each code means.
This claim: no standardized effect is recorded in observations/ for it yet, so no benchmark reading is possible.
q2 i? The tests with the worst results in the boxplot visualization were the same as those flagged by low CIC and unbalanced True Weight values; one suspicious test was an extra attempt taken only by lower-performing students, and the other two were modified. → Josu Arruarte 2021
Evidence¶
Josu Arruarte 2021¶
Josu Arruarte, Mikel Larrañaga, Ana Arruarte & Jon A. Elorriaga. (2021). Measuring the Quality of Test-based Exercises Based on the Performance of Students. International Journal of Artificial Intelligence in Education, 31, 585–602. https://doi.org/10.1007/s40593-020-00208-0
q2 · i? · design · r2
Retrospective analysis of grade distributions in the Fundamentals of Computer Science module using TEA's boxplot visualization with colour saturation representing correlation with overall marks. The article reports "the tests with the worst results were the same as those which were identified as suspicious above". No effect sizes are printed.
"the tests with the worst results were the same as those which were identified as suspicious above, due to their low CIC and unbalancedTrue Weight values."
Discussion¶
Related Claims¶
- Item-level visualizations of discrimination index and discrimination efficiency led instructors to identify troublesome items and replace or modify them — related
- In a retrospective higher-education evaluation, instructors using TEA found low CIC values and unbalanced True Weights in three of the ten tests and marked them for further analysis — a broader claim this one bears on
Page metadata
| Field | Value |
|---|---|
type |
claim |
id |
tea-boxplot-correlation-identified-suspicious-tests |
title |
Boxplot visualizations enriched with correlation to final marks identified the same suspicious tests as the consistency metrics, and instructors modified two of them for the next academic year |
description |
Boxplot visualizations enriched with correlation to final marks identified the same suspicious tests as the consistency metrics, and instructors modified two of them for the next academic year |
status |
review |
evidence_strength |
weak |
newest_evidence |
2021 |
source_checked |
2026-10-28 |
generated |
by process:wiki-ingest on 2026-10-28 |
trust |
unverified — no one has confirmed this page's content |
sources |
1 — josu-arruarte-2021 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.