Home · Sources · Steenbergen-Hu & Cooper 2013

A Meta-Analysis of the Effectiveness of Intelligent Tutoring Systems on K–12 Students' Mathematical Learning

Steenbergen-Hu & Cooper 2013 · review pooling many studies (meta-analysis) · touches 2 claims · used in 1 attack

Which beliefs it touches

C10 Tutoring software in school use sets a limit on it
K–12 maths meta (26 reports): tutoring systems vs regular classroom teaching g = 0.01–0.09 overall, 0.02 on standardised tests, 0.01 at end of school year; smaller for low achievers. C5 weakened 2026-10-07 (school-use bound). Moved from C5 to C10 at the split on 2026-10-08 (the school-use bound became C10).
C5 Step-based tutoring sets a limit on it
The authors note that VanLehn 2011's near-human-tutor result came from randomised experiments that held content constant, mostly STEM with many college students, using the largest-effect outcome per study; only one small study compared a tutoring system with (small-group) human tutors. Kept on C5 at the split on 2026-10-08 for this point only; the school-use result moved to C10.