mne-python-guide

Preprocessing raw EEG data using MNE-Python involves loading raw files, applying ICA for artifact removal, and filtering. This skill provides the exact methodological sequence and expert-recommended parameters to avoid common errors like incorrect filtering orders.

Cluster-based permutation tests on ERP data require constructing an adjacency matrix and executing the statistical test. This skill provides the exact sequence for adjacency matrix construction and statistical execution to ensure academic standards are met.

MNE-Python supports source localization and time-frequency decomposition for EEG and MEG data. This skill facilitates these complex workflows by providing domain-validated pipelines and methodological guardrails for accurate neurophysiological analysis.

Research literacy is required to use this skill effectively. It ensures you understand the methodological foundations for data preprocessing, statistical testing, and visualization required to analyze electrophysiology data accurately.

Data leakage in multivariate pattern analysis occurs due to incorrect cross-validation sequences. This skill provides methodological guardrails that warn against common pitfalls like data leakage in decoding, ensuring valid statistical results.

This MNE-Python guide supports intracranial EEG (iEEG) data analysis alongside standard EEG and MEG. It provides structured pipelines covering everything from raw data loading to advanced source localization and statistical testing.