heterogeneity-source-analysis

$npx mdskill add yogsoth-ai/de-anthropocentric-research-engine/heterogeneity-source-analysis

Classifies sources of between-study heterogeneity for meta-analysis

  • Analyzes clinical, methodological, and statistical variability across studies
  • Uses study characteristics, effect sizes, and moderator candidates as inputs
  • Prioritizes heterogeneity sources based on magnitude and plausibility
  • Delivers structured results for subgroup analysis and meta-regression planning

SKILL.md

.github/skills/heterogeneity-source-analysisView on GitHub ↗
---
name: heterogeneity-source-analysis
description: Identify and classify sources of between-study heterogeneity (clinical, methodological, statistical)
execution: subagent
prompt: ./prompt.md
input: study_characteristics, effect_sizes, moderator_candidates
used-by: meta-analysis
---

# Heterogeneity Source Analysis SOP

Systematically identify, classify, and prioritize potential sources of between-study heterogeneity for investigation via subgroup analysis and meta-regression.

## When to Use

- When meta-analysis reveals substantial heterogeneity (I2 > 50%)
- During planning of subgroup analyses and meta-regression
- When assessing the transitivity assumption in network meta-analysis

## Input

- `study_characteristics`: Study-level characteristics and covariates
- `effect_sizes`: Extracted effect sizes showing variation
- `moderator_candidates`: Pre-specified candidate moderator variables

## Output

Classified sources of heterogeneity with investigation priority and statistical analysis plan.

More from yogsoth-ai/de-anthropocentric-research-engine

SkillDescription
abductive-hypothesis-generationStrategy: 面对异常的最佳解释推理
ablation-brainstormRemove components one by one, observe system changes to reveal hidden dependencies and generate ideas from structural gaps.
ablation-component-mappingMap system architecture to ablatable units for ablation studies
ablation-designDesign ablation studies to isolate component contributions in ML systems
ablation-executionRemove components one by one from a system, record the response/impact of each removal.
abp-vulnerability-classificationClassify assumptions on 2 axes — load-bearing (how much conclusion depends on it) × vulnerable (how likely to be false). Focuses attention on High-Load × High-Vulnerable quadrant.
abstraction-extractionExtract abstract principles from concrete domain cases. Strips domain-specific details to reveal transferable mechanisms.
abstraction-ladderPerform bisociation at multiple abstraction levels
abstraction-ladderingMove between concrete and abstract framings — 3 levels up (Why?) and 3 levels down (How?) to find the most productive research level.
abstraction-to-designAbstract biological principle to design principle. Bridge from biology to engineering.