skills.rest
CUHK-AIM-Group
CUHK-AIM-GroupOFFICIAL
Explore all skills by this author →
WebsiteGitHub

glm

Runs classical General Linear Model analysis for task-evoked fMRI activation and group-level inference.

89|5|Updated Mar 25, 2026
Search Tags:#glm#neuroimaging#statistical inference#fmri#nilearn#task activation#contrast maps
One-click install
npx skills add https://github.com/CUHK-AIM-Group/NeuroDiscovery --skill glm-cuhk-aim-group
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: glm
Source: https://github.com/CUHK-AIM-Group/NeuroDiscovery/tree/main/skills/glm
Command: npx skills add https://github.com/CUHK-AIM-Group/NeuroDiscovery --skill glm-cuhk-aim-group

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires nilearn.

What problem does it solve? Researchers analyzing task-based fMRI need a rigorous statistical route to detect brain activation, but building design matrices, fitting first-level and second-level GLMs, and generating contrast maps requires coordinating multiple neuroimaging tools. This Skill provides model-level guidance for running classical GLM workflows on preprocessed task fMRI data. ## Core Features & Use Cases - First-Level GLM: Builds design matrices from events and confounds, fits subject/session-level models, and computes named contrasts such as task > baseline. - Second-Level GLM: Performs group-level inference across subjects using one-sample, two-sample, or covariate-adjusted design matrices, producing group z maps and statistical summaries. - Use Case: A neuroimaging researcher with preprocessed BOLD data and event timing files for 30 subjects uses this Skill to compute per-subject contrast maps, then runs a second-level analysis to identify group-level activation differences between conditions. ## Quick Start Ask the assistant to run a first-level GLM on your preprocessed task fMRI data with your events file and TR, producing contrast and z maps in the output directory.

Frequently Asked Questions about glm

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

FAQPage Schema
How do I run a first-level GLM on task fMRI data?▼

Provide a preprocessed BOLD image, an events file with onset, duration, and trial type, and the repetition time. The workflow builds a design matrix, fits the GLM per subject or session, and exports contrast and z maps via nilearn.

How do I perform second-level group analysis in fMRI?▼

Collect first-level contrast maps from all subjects and supply a group design matrix for one-sample, two-sample, or covariate models. The second-level GLM fits across subjects and produces group z maps, thresholded figures, and statistical summaries.

When should I use GLM instead of deep learning for fMRI analysis?▼

Use GLM when the goal is statistical inference on task conditions or contrasts rather than phenotype prediction. It suits limited sample sizes, group-level inference, and studies requiring interpretable contrast maps or cluster-level reports.

What inputs are required for task fMRI GLM analysis?▼

Required inputs are a preprocessed task BOLD image, an events table with onset, duration, and condition labels, and the repetition time. Optional inputs include confounds tables, brain masks, and group design matrices for second-level analysis.

What are the limitations of GLM for fMRI analysis?▼

GLM is designed for task-fMRI, not resting-state phenotype modeling. Results are sensitive to event timing quality, motion confounds, and preprocessing choices, and group inference requires consistent first-level contrast definitions across subjects.

Related Skills

Explore More Education & Research Skills→
NeuroAIHubNeuroAIHub
269

fmriprep

Execute containerized BIDS-App fMRI preprocessing with motion correction and anatomical registration.

Official
Advanced
CUHK-AIM-GroupCUHK-AIM-Group
78

brain-visualization

Translate neuroimaging outputs into publication-ready figures and 3D meshes.

Official
Intermediate
HaoxuanLiTHUAIHaoxuanLiTHUAI
34

fMRI GLM Analysis Guide

...

Community
Advanced
jkitchinjkitchin
34

python-regression-statistics

Guide regression analysis and outlier detection in Python using statsmodels, scikit-learn, scipy, and PyOD.

Community
Advanced