What does the Meta-Analysis skill do?

This skill enables Claude to perform quantitative synthesis by pooling effect sizes from multiple research studies, calculating summary effects, and assessing statistical variability across datasets.

When should I use this Claude Code skill?

Use this skill when conducting systematic reviews, combining results from multiple clinical trials, or whenever you need to calculate a weighted average effect size from disparate experimental results.

How does this skill improve my data science workflow?

It automates complex statistical modeling, including fixed and random-effects models, handles effect size conversions (d, OR, RR), and identifies publication bias, significantly reducing manual calculation time.

Can it handle different research metrics?

Yes, the Meta-Analysis skill is designed to extract and convert various metrics, such as Cohen's d, Odds Ratios (OR), and Relative Risk (RR), into standardized formats for accurate pooling.

What specific statistical tests are supported?

The skill supports I² and Q tests for heterogeneity, subgroup analysis, meta-regression, funnel plots, Egger’s test, and trim-and-fill methods to ensure rigorous scientific reporting.

Meta-Analysis

Name: Meta-Analysis
Author: astoreyai

byastoreyai

•

データサイエンスとML

Conducts quantitative synthesis by pooling effect sizes across multiple research studies to calculate summary effects and assess statistical heterogeneity.

概要

The Meta-Analysis skill empowers researchers to perform rigorous quantitative synthesis of empirical data across various studies. By automating the extraction of effect sizes and applying advanced statistical models like fixed-effect or random-effects weighting, it provides a comprehensive overview of research evidence. The skill simplifies complex tasks such as calculating 95% confidence intervals, evaluating heterogeneity via I² statistics and Q tests, and identifying publication bias through funnel plots and Egger's tests. It is an essential tool for systematic reviews, evidence-based decision-making, and identifying trends in scientific literature.

主な機能

Fixed-effect and random-effects statistical modeling
2 GitHub stars
Heterogeneity assessment using I² statistics and Q tests
Subgroup analysis and meta-regression for variability investigation
Standardized effect size extraction and conversion (d, OR, RR)
Publication bias detection via funnel plots and Egger’s test

ユースケース

Synthesizing results for a systematic literature review
Calculating the overall impact of an intervention across multiple clinical trials
Resolving conflicting study findings through statistical pooling

概要

主な機能

Fixed-effect and random-effects statistical modeling
2 GitHub stars
Heterogeneity assessment using I² statistics and Q tests
Subgroup analysis and meta-regression for variability investigation
Standardized effect size extraction and conversion (d, OR, RR)
Publication bias detection via funnel plots and Egger’s test

ユースケース

Synthesizing results for a systematic literature review
Calculating the overall impact of an intervention across multiple clinical trials
Resolving conflicting study findings through statistical pooling