running-power-analysis

What problem does it solve?

This Skill helps you plan a study before data collection by turning a test choice, an expected or minimum meaningful effect, and a target alpha/power trade-off into a sample size, achieved power, or minimum detectable effect.

Core Features & Use Cases

It supports common frequentist planning workflows for t-tests, ANOVA, chi-squared tests, correlation, and regression, including grant writing, pre-registration, pilot-informed planning, and design comparisons such as paired versus independent samples. It also guards against misuse by refusing post-hoc or observed power, requiring an explicit effect-size provenance, and prompting sensitivity checks so fragile assumptions are visible before the study runs.

Quick Start

Use the running-power-analysis skill to estimate the required sample size for a planned two-arm study with 80% power, alpha 0.05, and a clinically meaningful effect based on prior evidence.