Random measurement noise in pretest scores produces a negative contribution to the correlation between normalized gain and pretest score¶

Claim · All claims
Evidence · 1 study · theoretical r3 · q2 · i2 medium
Currency · newest study 2007 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i2 A first-order approximation shows pretest noise induces a negative gain–pretest correlation; a rough estimate suggests noise of 0.1 contributes about −0.2 to the correlation. → Lei Bao 2007

Evidence¶

Lei Bao 2007¶

Lei Bao. (2007). Dynamic Models of Learning and Education Measurement. https://arxiv.org/abs/0710.1375 doi:10.48550/arxiv.0710.1375

q2 · i2 · medium effect, r = -0.2 · theoretical · r3

Analytical first-order approximation (Section III) combining random pre- and post-test errors, Eq. (13). The article reports the correlation 'is no longer zero since both contain the same random noise' and gives the rough estimate of −0.2 for noise of 0.1.

"A rough estimation using Eq. (13) with a typical class suggests that a random noise of 0.1 can contribute to about −0.2 in correlation."

Discussion¶

Related Claims¶

• When the γ-process (associative interaction of correct and incorrect knowledge) is considered, the normalized gain correlates positively with pretest score — related
• Pre-instruction LCTSR scores correlate with normalized learning gains, most strongly for theoretical content (TUG-K r=0.59) and more weakly for descriptive content (DIRECT r=0.50) — related
• Hake's survey found interactive-engagement courses achieved average normalized gains about two standard deviations greater than traditional courses, with overall gain–pretest correlation of +0.02 — related
• High-ability students' learning behaves as a dominant α-process even at low pretest scores, while average-ability students show more γ-process behavior — related
• Under a dominant α-process, the normalized gain contains no pretest-score term and is uncorrelated with pretest score if α is uncorrelated with pretest score — related
• Pre-tests reduced adult learners' persistence in a MOOC, though they improved post-test scores among those who completed it — related
• Pre-test scores strongly predict post-test scores but not normalized learning gains — related
• Average homework H-scores correlate negatively with proctored exam performance, with the correlation strengthening from Spring 2024 to Spring 2026 — related
• An approximately hour-long interactive computer tutorial on orthographic projection produced significant pre–post performance gains for most students — related