data-extraction

Convert study data into effect sizes and variances for R metafor pipelines.

1|Updated Dec 29, 2025

Search Tags:#meta-analysis #data-extraction #effect-size #data-preparation #metafor #missing-data #escalc

Ready to run

npx skills add https://github.com/matheus-rech/meta-agent-mobile --skill data-extraction-matheus-rech

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: data-extraction
Source: https://github.com/matheus-rech/meta-agent-mobile/tree/main/agentskills/data-extraction
Command: npx skills add https://github.com/matheus-rech/meta-agent-mobile --skill data-extraction-matheus-rech

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The skill helps researchers convert study data into analyzable effect sizes and variances for meta-analysis, reducing manual calculation errors and time.

Core Features & Use Cases

Data extraction and conversion from binary and continuous outcomes to common metrics (OR, RR, SMD, MD).
Automated variance estimation and handling of missing data for incomplete reports.
Use Case: Given a set of studies with mixed reporting formats, convert to standardized effect sizes and prepare a ready-to-analyze dataset for R metafor pipelines.

Quick Start

Input a study dataset and run the data-extraction workflow to generate standardized effect sizes and variances.

Frequently Asked Questions about data-extraction

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I convert study data with mixed reporting formats into standardized effect sizes for meta-analysis?▼

To convert study data for meta-analysis, the Skill extracts binary and continuous outcomes, converting them to common metrics like OR, RR, SMD, and MD. It generates a ready-to-analyze dataset of standardized effect sizes and variances.

Can I calculate effect sizes and variances in R when original studies have missing statistics?▼

Yes, you can calculate effect sizes with missing statistics using R with the metafor and escalc packages. The Skill automates variance estimation and handles incomplete reports to produce analyzable inputs.

What is the best way to prepare a dataset for R metafor pipelines from studies with inconsistent reporting?▼

The best way to prepare data for R metafor pipelines is to input the study dataset into the data-extraction workflow. It converts mixed formats into a standardized dataset complete with computed effect sizes and variances.

Do I need R with escalc and metafor packages to compute effect sizes and variances from raw study data?▼

Yes, you need R with the metafor and escalc packages to compute effect sizes and variances. This Skill requires these specific dependencies to transform raw study data into a common metric for analysis.

Why does meta-analysis data extraction require converting binary and continuous outcomes to a common metric?▼

Meta-analysis data extraction requires converting outcomes to a common metric to synthesize results across mixed reporting formats. This conversion reduces manual calculation errors and prepares a standardized dataset for analysis.

Does this data extraction workflow handle automated variance estimation for incomplete study reports?▼

Yes, the data extraction workflow handles automated variance estimation for incomplete study reports. It specifically addresses missing data to ensure your dataset contains the necessary effect sizes and variances for meta-analysis.