Compute the standardized mean difference between two groups, either from descriptive statistics or from a reported t test. Includes the Hedges' g small-sample correction and conversion to r.
Uses d = t × √(1/n₁ + 1/n₂) for an independent samples t test.
Effect sizes computed automatically. ReliCheck Quanta reports d, g, eta squared, and omega squared alongside every relevant test, formatted for APA. Free to try on your Mac. No Mac? Try the Quantitative Studio on the web.
Get QuantaCohen's d expresses a mean difference in standard deviation units. A d of 0.50 means the group means sit half a standard deviation apart, regardless of the original measurement scale. That makes d comparable across studies and essential for meta-analysis and power analysis.
Cohen's rough benchmarks are 0.20 small, 0.50 medium, and 0.80 large. Field context matters more: in education research, an intervention effect of d = 0.20 on standardized achievement can be substantial. Use benchmarks as a starting point, not a verdict.