Table 13.

Cluster‐robust meta‐regression for random assignment for nonacademic effect sizes.

Effect (n of sizes)	Hedges’ g	95% CI of g	df	p
Nonrandom assignmenta (76)	0.28	(0.10, 0.45)	13.20	0.005
Random assignment (15)	0.31	(−0.54, 1.16)	2.75	0.315

Note: N of studies = 18, N of effect sizes = 91, assumed ρ = 0.8, I ² = 84.12a. 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.