Table 16.

Cluster‐robust meta‐regression for treatment duration (weeks) for nonacademic effect sizes.

Effect	Hedges’ g	95% CI of g	df	p
Intercepta	0.524	(0.126, 0.922)	9.63	0.015
Within‐study effect by week	0.001	(−0.089, 0.091)	1.00	0.913
Between‐study effect by week	−0.004	(−0.011, 0.003)	4.62	0.167

Note: N of studies = 15, N of effect sizes = 67, assumed ρ = 0.8, I ² = 86.65. Cluster‐robust estimates with df < 4.00 should be interpreted with caution (Tanner‐Smith, Tipton, & Polanin, 2016). Positive effect sizes favor Montessori over traditional education.

Abbreviation: CI, confidence interval.

^a Reference category/intercept.