means
Power and sample-size calculation
Plan sample size or estimate power for a mean comparison.
Requirements
- target effect size
- alpha
- desired power or sample size
- study design
Avoid when
- effect size chosen only from an underpowered pilot
- multiple testing left unaccounted
Formula
Power = 1 − β = P(reject H₀ | H₁ is true)
Interpretation
Power is the probability of detecting the specified effect under the stated assumptions.
Worked example
Estimate the balanced sample size needed to detect a prespecified mean difference.
Open example datasets