Academic tools

For planning theses, papers and studies: sample size and power, diagnostic test calculations and reporting checklists. Everything runs in your browser; nothing you enter is sent.

Sample size

Choose the study type and enter your expectations; the number of participants needed is calculated at once.

Study typeSignificance level (α)Power (1−β)Expected dropout%Effect size (Cohen's d)Hypothesis

Cohen's d = expected difference / standard deviation. Roughly 0.2 small, 0.5 medium, 0.8 large. Example: a difference of 1.5 in SUVmax between groups with a standard deviation of 3 gives d = 0.5.

Per group: 64
Total participants: 128
With dropout allowance: 72 × 2 = 144
Per group, normal approximation: 63

Power by n per group: n=20 → 35% · n=40 → 61% · n=64 → 81% · n=100 → 94% · n=150 → 99%

n = 2 (z₁₋α/₂ + z₁₋β)² / d² (+ z₁₋α/₂² / 4)

Source: Chow, Shao, Wang 2017 §3.2; Guenther 1981

For study planning and education; consult a statistician for a definitive sample size.