skills.rest
dengzhe-hou
dengzhe-houCOMMUNITY
Explore all skills by this author →
GitHub

eeg-stats

Run claim-driven EEG group statistics with cluster-based permutation tests.

Updated Aug 27, 2026
Search Tags:#multiple comparisons#mne-python#eeg statistics#cluster permutation#ANALYSIS_PLAN#roi channels#cohens d
One-click install
npx skills add https://github.com/dengzhe-hou/auto-eeg-analysis --skill eeg-stats
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: eeg-stats
Source: https://github.com/dengzhe-hou/auto-eeg-analysis/tree/main/skills/eeg-stats
Command: npx skills add https://github.com/dengzhe-hou/auto-eeg-analysis --skill eeg-stats

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires mne, scipy, numpy, python.

What problem does it solve?

This Skill turns pre-defined EEG claims into rigorous, reproducible group-level statistics so you can test hypotheses without ad-hoc choices.

Core Features & Use Cases

  • Claim-driven cluster permutation testing: Runs spatio-temporal cluster permutation tests (directional or two-sided) for ERP/TFR/connectivity contrasts specified in ANALYSIS_PLAN.
  • ROI + channel-mapping guardrails: Enforces planned time windows and ROI channels, using channel_mapping.json to resolve 10-20 names to numbered channels and stopping when mappings are missing.
  • COBIDAS-ready statistical outputs: Writes per-claim JSON verdicts plus reproducibility artifacts (arrays and backend resolution) and appends a structured FINDINGS.md entry.
  • Multiple-comparisons controls: Applies the multiple-comparisons strategy defined in ANALYSIS_PLAN (e.g., Bonferroni or hierarchical).

Quick Start

Use the eeg-stats Skill to compute cluster permutation group statistics for your frozen ANALYSIS_PLAN by running it on a prepared project directory (with stats prerequisites generated by earlier ERP/TFR stages).

Frequently Asked Questions about eeg-stats

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

FAQPage Schema
How do I run cluster-based permutation tests for EEG group statistics?▼

Cluster-based permutation tests for EEG group statistics can be run by applying a Skill to a prepared project directory containing a frozen ANALYSIS_PLAN.md and stage outputs to evaluate pre-registered directional or two-sided contrasts.

How do I enforce pre-registered ROI channels and time windows during EEG statistical analysis?▼

To enforce pre-registered ROI channels and time windows during EEG statistical analysis, the process uses a channel_mapping.json file to resolve 10-20 names to numbered channels, halting execution if any required mappings are missing.

Does MNE-Python support claim-driven multiple comparisons correction for ERP and time-frequency data?▼

MNE-Python supports claim-driven multiple comparisons correction by applying strategies like Bonferroni or hierarchical controls defined in a frozen ANALYSIS_PLAN.md to ERP, time-frequency, or connectivity stage outputs.

What is the best way to generate reproducible EEG statistical outputs for COBIDAS compliance?▼

The best way to generate reproducible EEG statistical outputs for COBIDAS compliance is running claim-driven group statistics that output per-claim JSON verdicts, arrays, and structured FINDINGS.md reproducibility artifacts.

Can I use cluster permutation testing for both paired and independent EEG study designs?▼

Cluster permutation testing can be applied to both paired and independent EEG study designs when pre-registered claims specify contrasts, regions of interest, time windows, and directional hypotheses in the analysis plan.

What prerequisites are needed before computing EEG group-level hypothesis tests?▼

Prerequisites for computing EEG group-level hypothesis tests include a frozen ANALYSIS_PLAN.md, ERP or time-frequency stage outputs, an ENVIRONMENT.json for MNE resolution, and channel_mapping.json for ROI channel alignment.

Related Skills

Explore More Education & Research Skills→
ovachieverovachiever
52

thesys-generative-ui

Stream interactive React UI components from LLM responses.

Community
Advanced
joshua3403joshua3403

pdca

Automate PDCA cycle management and generate Plan, Design, Analysis, and Report artifacts.

Community
Basic
Victory-HugoVictory-Hugo
1

pydeseq2

Perform differential expression analysis on bulk RNA-seq data with PyDESeq2.

Community
Intermediate
NeuroAIHubNeuroAIHub
34

Neural Population Decoding Analysis

Design and validate multivariate neural decoding analyses for EEG, MEG, or fMRI population data.

Official
Advanced