Equivalence testing (TOST) indicated the observed jigsaw effect sizes were statistically equivalent to zero in the single-session experiments¶

Claim · All claims
Evidence · 1 study · causal r2 · q3
Currency · newest study 2022 · not yet checked against its sources · not reviewed by a person
Design limits · Arnaud Stanczak 2022: groups were assigned but students were analysed as independent (read from the study by two models, 2026-10-25)

Subclaims¶

q3 i? Two one-sided tests rejected both equivalence bounds in Experiments 1 and 2, indicating observed jigsaw effects were statistically equivalent to zero. → Arnaud Stanczak 2022

Evidence¶

Arnaud Stanczak 2022¶

Arnaud Stanczak, Céline Darnon, Anaïs Robert, Marie Demolliens, Camille Sanrey, Pascal Bressoux, Pascal Huguet, Céline Buchs, Fabrizio Butera, and PROFAN Consortium. (2022). Do Jigsaw classrooms improve learning outcomes? Five experiments and an internal meta-analysis. Journal of Educational Psychology, 114 (6), pp.1461-1476. https://doi.org/10.1037/edu0000730

q3 · i? · causal · r2

Experiment 1 applied the TOST equivalence procedure to the observed jigsaw-versus-individualistic effect. The authors report both bounds rejected (p upper = .004, p lower < .001), so the "observed effect size can be considered as statistically equivalent to zero".

"The results demonstrate that both the upper and lower bounds are rejected under the assumption that the null hypothesis is true, indicating that the observed effect size can be considered as statistically equivalent to zero (p upper = .004 and p lower < .001, respectively)"

Discussion¶

Related Claims¶

• With scrambled randomization and novel material, jigsaw produced no difference versus individualistic learning on a life-sciences test — possibly the same claim (merge candidate)
• After learners adjust their confidence, the degree of socio-cognitive conflict is equivalent to zero as a predictor of information requests — related