Robustness checks with fixed-effect and first-difference models reproduce the three-way interaction; continuous-time growth curve modelling does not¶

Claim · All claims
Evidence · 1 study (2 entries) · causal r2 · q3
Currency · newest study 2023 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q3 i? Fixed-effect panel regression reproduced the gender × time × condition interactions more clearly than the main analysis (self-reported: χ²(2, N = 23,329) = 2.78, p = .025; utility: χ²(2, N = 23,329) = 3.65, p = .006). → Rudmann 2023 q3 i? Continuous-time growth curve modelling reproduced Hypotheses 1 and 2 but not the three-way interactions, which the authors attribute to non-linear change over time. → Rudmann 2023 (2)

Evidence¶

Rudmann 2023¶

Rudmann, O., Batruch, A., Visintin, E. P., Sommet, N., Bressoux, P., Darnon, C., ... Butera, F. (2023). Cooperative Learning Reduces the Gender Gap in Perceived Social Competences. A Large-Scale Nationwide Longitudinal Experiment. Journal of Educational Psychology (accepted for publication). https://osf.io/qarxk/?view_only=e772332576a5421cbf61b3092e567ac9

q3 · i? · causal · r2

Robustness check using fixed-effect panel regression modelling, described by the article as often regarded as the gold standard for longitudinal data; it reproduced Hypotheses 2 and 3 for both outcomes.

"the gender × time × condition interactions were even clearer than in the main analysis for both the self-reported social competences, χ² (2, N = 23,329) = 2.78, p = .025, and the utility value of social competences, χ² (2, N = 23,329) = 3.65, p = .006."

Rudmann 2023 (2)¶

Rudmann, O., Batruch, A., Visintin, E. P., Sommet, N., Bressoux, P., Darnon, C., ... Butera, F. (2023). Cooperative Learning Reduces the Gender Gap in Perceived Social Competences. A Large-Scale Nationwide Longitudinal Experiment. Journal of Educational Psychology (accepted for publication). https://osf.io/qarxk/?view_only=e772332576a5421cbf61b3092e567ac9

q3 · i? · causal · r2

Robustness check treating time as continuous in a standard growth curve approach; it failed to reproduce the three-way interactions, which the article attributes to the non-linear effects of time illustrated in Figures 2 and 3.

"we reproduced the effects for Hypothesis 1 (i.e., the main effects of gender) and Hypothesis 2 (i.e., the gender × time interactions), but not the effects pertaining to Hypothesis 3 (i.e., the gender × time × condition interactions)."

Discussion¶

Related Claims¶

• The gender gap in self-reported social competences widens over two years of vocational high school — related
• The gender gap in perceived utility value of social competences widens over time — related
• Jigsaw classroom curbs the widening gender gap in self-reported social competences, reducing the Time-3 gap by 27% versus business-as-usual and 20% versus resource independence — related
• Jigsaw classroom curbs the widening gender gap in perceived utility value of social competences, reducing the Time-3 gap by 50% versus business-as-usual and 25% versus resource independence — related
• Sensitivity analyses restricting to students assessed in all 15 terms reproduced the full-sample between-group comparisons — related
• Applying the reproducibility checks to TRANSFER performance, the Xie et al. (2018) results are (rather) robust, but RECALL and moderator results are doubtful — related