Statistical Power
Works out required sample size, minimum detectable effect and power curves.
Install
Ships scriptsnpx skills add K-Dense-AI/scientific-agent-skills
"How many samples do I need", a priori power analysis, minimum detectable effect, or justifying n for a protocol.
- Author
- K-Dense Inc.
- License
- MIT
Handles the closed-form cases — t-tests, ANOVA, proportions, correlation, chi-square, regression — and drops to Monte Carlo simulation for designs with no formula, such as mixed models, cluster-randomized trials or survival endpoints. It also covers the corrections people forget: unequal allocation, attrition, clustering and multiple comparisons. Results are shaped as the sample-size justification a grant, IRB submission or pre-registration expects.
Similar skills
Performance Optimization
SkillProfile first, fix the measured bottleneck, then measure again.
statsmodels
SkillRegression, GLM and time series models with the full inference output.
PluginEval
SkillScores a Claude Code skill on ten dimensions across static checks, an LLM judge and Monte Carlo runs.
Comments(0)
Sign in to comment