running-power-analysis

Calculate sample size for a t-test by providing the test family, alpha, power, and an effect size with explicit provenance. The skill uses these inputs to estimate the required n for your planned study design.

Statistical power analysis is a prospective planning technique that turns an expected effect and target alpha into defensible sample sizes. You need it for pre-registration and grant writing to justify your study design before data collection begins.

No, computing observed power is explicitly refused. The skill focuses strictly on prospective planning, requiring you to define alpha, power, and effect-size scale before data collection rather than calculating post-hoc power.

Determine the minimum detectable effect for an ANOVA by specifying your sample size, alpha, and power. The calculation requires you to choose the test family and state your effect-size provenance to output the MDE.

The best way to plan sample size using pilot data is to derive your effect-size provenance from the pilot results, then run a sensitivity analysis. This ensures fragile assumptions are visible before the main study runs.

Power analysis requires a sensitivity analysis to make fragile effect-size assumptions visible before data collection. Prompting these checks ensures your sample size estimates remain defensible across varying conditions.