Point-biserial item-total correlation is negatively related to test discriminating value and can be expressed via item and test difficulty and discrimination parameters¶

Claim · All claims
Evidence · 1 study · theoretical r2 · q1
Currency · newest study 2021 · not yet checked against its sources · not reviewed by a person · overdue for a recheck since 2024: tool and model accuracy changes quickly

Subclaims¶

q1 i? The derived expression for rpbs(i) depicts a negative relationship between item-total correlation (point-biserial) and the discriminating value of the test, expressible in terms of DiffT, DiscT, Diffi and Disci. → Chakrabartty 2021

Evidence¶

Chakrabartty 2021¶

Chakrabartty, S. N. (2021). Assessment of item and test parameters: Cosine similarity approach. International Journal of Psychology and Educational Studies, 8(3), 28-38. https://dx.doi.org/10.52380/ijpes.2021.8.3.190

q1 · i? · theoretical · r2

Analytical derivation under CTT (equations 1.13–1.15) expressing the point-biserial correlation of item i in terms of item and test parameters; no empirical coefficient for this relationship is printed beyond the derivation.

"(1.14) depicts a negative relationship between item-total correlation, in terms of point biserial correlation and discriminating value of the test."

Discussion¶

Related Claims¶

• Polychotomously scored IF-AT physics exam items show excellent discrimination, with a mean item-total correlation of r′ = 0.41 ± 0.13 across 45 items — related
• Item discriminating value as coefficient of variation decreases monotonically as number of correct answers increases, giving a negative difficulty–discrimination relationship — related
• Intersection point k0 of item difficulty and discriminating curves provides a data-driven item-deletion criterion — related
• Test discriminating value equals the coefficient of variation of test scores (tan∅ = SD/mean) — related
• Test difficulty value defined as ratio of observed to maximum score vector length times cosine of their angle equals test mean divided by number of items — related
• Scores on the debugging-oriented Python proficiency assessment moderately predict successful code repair — related
• CTT item selection dropped five low-discrimination items, retaining 20 items of moderate difficulty — related
• Learned difficulty parameters show a moderate positive correlation with empirical KC difficulty on QATD2k — related
• Intra-testlet items were slightly more difficult than stand-alone questions (p′ = 0.69 ± 0.15 vs 0.75 ± 0.15) — related