Short Inventory of Learning Patterns
Category: Student Learning
Abstract: We apply Item Response Theory (IRT) to high-school transcript data, treating courses as items and grades as ordered responses, to estimate student transcript strength (θ̂) and course difficulty on a common scale. IRT estimation orders courses plausibly by difficulty, differentiates students with identical GPAs, correlates strongly with SAT scores, and demonstrates more than twice the SAT’s power to predict college completion — also outperforming both GPA and a composite transcript factor (η̂) that combines GPA with counts of AP/IB and STEM courses. θ̂ yields narrower racial/ethnic, but wider gender, disparities than the SAT. θ̂ shows a notably smaller Asian–White disparity than η̂, since Asian–White differences in AP/IB course counts far exceed differences in full-spectrum course difficulty as measured by IRT.
A Chalkboard piece on measuring high school performance beyond GPA. The authors describe their EdWorkingPaper using item response theory on Delaware transcript data to account for course difficulty.