Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Robust group analysis using outlier inference.

Mark Woolrich1

  • 1Oxford Centre for Functional Magnetic Resonance Imaging of the Brain, University of Oxford, John Radcliffe Hospital, Oxford OX3 9DU, UK. woolrich@fmrib.ox.ac.uk

Neuroimage
|April 15, 2008
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Modelling variability in functional brain networks using embeddings.

Imaging neuroscience (Cambridge, Mass.)·2026
Same author

Alzheimer's disease and its progression reduce pyramidal cell gain and connectivity.

Alzheimer's & dementia : the journal of the Alzheimer's Association·2025
Same author

Alzheimer's disease and memantine effects on NMDA-receptor blockade: non-invasive in vivo insights from magnetoencephalography.

Molecular psychiatry·2025
Same author

Reduced beta bursting underpins loss of corticomuscular coherence in amyotrophic lateral sclerosis.

Brain communications·2025
Same author

Divergent Brain Network Activity in Asymptomatic C9orf72 and SOD1 Variant Carriers Compared With Established Amyotrophic Lateral Sclerosis.

Human brain mapping·2025
Same author

<i>Imaging Neuroscience</i> opening editorial.

Imaging neuroscience (Cambridge, Mass.)·2025
Same journal

Investigating the Neural Origins of Ear-EEG: A Correlation Study Using Scalp EEG Source Reconstruction.

NeuroImage·2026
Same journal

Hysteresis effects in visual and auditory perception and the comparison of underlying neural mechanisms - an EEG study.

NeuroImage·2026
Same journal

Short-term audio-tactile training affects cortical auditory speech-envelope tracking for incongruent but not congruent stimuli.

NeuroImage·2026
Same journal

Dissociable Neurocognitive Mechanisms of State and Trait Anxiety in Working Memory: Threat-Induced Alterations in Decision Dynamics and Attenuation of Large-Scale Network Reconfiguration.

NeuroImage·2026
Same journal

Neuro-Ocular Amyloid Characterization in Alzheimer's Disease via Cross-Site PET-MRI and Hierarchical Cross-Attention Driven Multimodal Representation Learning.

NeuroImage·2026
Same journal

Whole-brain network dynamics underlying intolerance of uncertainty.

NeuroImage·2026
See all related articles

This study introduces a robust general linear model (GLM) approach for neuroimaging group studies to identify and handle outlier subjects. The method improves statistical inference by modeling errors as a mixture of Gaussian distributions, enhancing data analysis accuracy.

Area of Science:

  • Neuroimaging
  • Statistical Modeling
  • Brain Research

Background:

  • Neuroimaging group studies assume random subject sampling and Gaussian distributed effect sizes.
  • Outlier subjects can significantly skew results in group studies if not properly addressed.
  • Existing methods may not adequately handle outliers, impacting the reliability of neuroimaging findings.

Purpose of the Study:

  • To develop a robust group inference method for neuroimaging that effectively identifies and accounts for outlier subjects.
  • To enhance the accuracy and reliability of statistical inference in group-level neuroimaging analyses.
  • To integrate outlier detection within a hierarchical modeling framework for improved performance.

Main Methods:

  • Proposed a robust general linear model (GLM) approach modeling errors as a mixture of two Gaussian distributions.

Related Experiment Videos

  • Integrated the robust GLM into a hierarchical group model, utilizing GLMs at each hierarchical level.
  • Employed a Bayesian inference framework to infer on the robust GLM, incorporating lower-level variance information.

    • Main Results:

    • The proposed method demonstrated effective outlier inference and improved group inference accuracy.
    • Performance was validated using both simulated data and real functional magnetic resonance imaging (fMRI) data.
    • Comparison with iterative reweighted least squares and permutation testing showed competitive or superior performance.

    Conclusions:

    • The robust GLM approach offers a significant advancement for neuroimaging group studies by effectively managing outliers.
    • This method enhances the reliability of statistical inference in the presence of non-representative subjects.
    • The integration with hierarchical modeling and Bayesian inference provides a powerful tool for analyzing complex neuroimaging data.