Effect sizes across shared text reading studies show substantial true heterogeneity (I2 = 80.09)¶

Claim · All claims
Evidence · 1 study · quant-synthesis r3 · q3
Currency · newest study 2024 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q3 i? A heterogeneity test showed significant heterogeneity in effect sizes across studies, with almost 80% of total variability caused by true between-study heterogeneity. → Rachel Sermier Dessemontet 2024

Evidence¶

Rachel Sermier Dessemontet 2024¶

Rachel Sermier Dessemontet, Megan Geyer, Anne-Laure Linder, Myrto Atzemian, Catherine Martinet, Natalina Meuli, Catherine Audrin, Anne-Françoise de Chambrier. (2024). Effects of shared text reading for students with intellectual disability: A meta-analytical review of instructional strategies. Educational Research Review, 44. https://doi.org/10.1016/j.edurev.2024.100615

q3 · i? · quant-synthesis · r3

Heterogeneity test within the multilevel meta-analysis of 19 single-case studies, reported alongside a sensitivity analysis showing stable estimates (LRR = 1.05, τ2 = 0.23) across within-study correlation assumptions ρ = 0 to 1.

"A heterogeneity test shows that there is a significant heterogeneity in effect sizes across the studies: I2 = 80.09. Almost 80% of the total variability among effect sizes was caused by true heterogeneity between studies, indicating that investigating moderator variables was important."

Discussion¶

Related Claims¶

• Shared text reading benefits students with intellectual disability whether or not they need augmentative and alternative communication systems — related
• Effects of game-based learning in STEM education vary substantially across studies, with prediction intervals spanning trivial-to-negative through very strong effects — related
• Effects of grant aid on persistence and completion are heterogeneous across studies, justifying random-effects meta-analysis — related
• Effect-size heterogeneity across Covid-19 studies is essentially total (I2 = 100%), justifying a random-effects model — a narrower finding that bears on this claim
• Effect sizes across studies show substantial heterogeneity, with wide prediction intervals spanning large negative to large positive true effects — related