What study designs are supported by this skill?

The skill supports independent and paired samples t-tests, One-Way ANOVA, Chi-Square tests, Pearson correlations, and Multiple Regression models.

Can this skill help with NIH grant writing?

Yes, it generates formatted sample size justification sections that include effect size citations, power assumptions, and sensitivity analysis required for NIH rigor standards.

How does it handle participant dropout?

It includes an attrition adjustment formula that calculates the total number of participants to recruit based on the required power and expected dropout rates.

Can I use it for retrospective analysis?

It is designed for sensitivity analysis of existing studies to determine what effect sizes the study was actually powered to detect, which is the scientifically preferred method for interpreting null results.

Does it provide effect size guidelines?

Yes, it offers Cohen's conventions for small, medium, and large effects as well as methods for deriving effect sizes from previous literature or pilot studies.

Statistical Power Analysis

Name: Statistical Power Analysis
Author: astoreyai

byastoreyai

•

Ciencia de Datos y ML

Calculates statistical power and determines required sample sizes for research studies to ensure experimental rigor and reproducibility.

The Statistical Power Analysis skill automates the complex mathematical work required to design robust research studies. By calculating key parameters like effect size, alpha, and power (1-β), it helps researchers determine the exact sample size (N) needed to detect true effects across various study designs, including t-tests, ANOVA, correlations, and regressions. It is specifically designed to help scientists meet NIH rigor and reproducibility standards, justify recruitment targets for grant proposals, and conduct sensitivity analyses to interpret null results effectively.

Características Principales

01Calculate required sample sizes for t-tests, ANOVA, Chi-square, and regressions

02Perform prospective power analysis for grant proposals and pre-registrations

03Provide effect size guidelines and Cohen's conventions for various domains

042 GitHub stars

05Conduct sensitivity analysis to evaluate the adequacy of existing studies

06Generate NIH-compliant sample size justification text with attrition adjustments

Casos de Uso

01Justifying sample sizes for NIH or NSF grant applications and ethical review protocols

02Determining recruitment targets for clinical trials and psychological experiments

03Evaluating the likelihood of Type II errors in studies with null findings

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add astoreyai/ai_scientist power-analysis

For use in Claude.ai and ChatGPT

Download Skill