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

An improved theoretical P value for SPMs based on discrete local maxima.

K J Worsley1

  • 1Department of Mathematics and Statistics, McGill University, Montreal, Québec, Canada. worsley@math.mcgill.ca

Neuroimage
|August 30, 2005
PubMed
Summary

A novel continuity correction improves P value accuracy for statistical parametric maps, especially with larger spatial smoothing (FWHM). This new method offers a more precise statistical threshold in neuroimaging analyses like fMRI.

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

Assessing the significance of focal activations using their spatial extent.

Human brain mapping·2014
Same author

A unified statistical approach for determining significant signals in images of cerebral activation.

Human brain mapping·2010
Same author

Searching scale space for activation in PET images.

Human brain mapping·2010
Same author

An overview and some new developments in the statistical analysis of PET and fMRI data.

Human brain mapping·2010
Same author

Longitudinal and cross-sectional analysis of atrophy in pharmacoresistant temporal lobe epilepsy.

Neurology·2009
Same author

Episodic memory impairment in patients with Alzheimer's disease is correlated with entorhinal cortex atrophy. A voxel-based morphometry study.

Journal of neurology·2007

Area of Science:

  • Neuroimaging analysis
  • Statistical inference
  • Brain mapping

Background:

  • Accurate statistical inference is crucial in neuroimaging.
  • Current P value correction methods (Bonferroni, Random Field Theory) have limitations depending on spatial smoothing (FWHM).
  • A gap exists in correction accuracy for intermediate FWHM values.

Purpose of the Study:

  • To introduce a new continuity correction for P values in statistical parametric mapping.
  • To bridge the accuracy gap between Bonferroni and Random Field Theory corrections.
  • To provide a more accurate statistical threshold for neuroimaging data.

Main Methods:

  • Developed a novel continuity correction method for P values.
  • The method is based on discrete local maxima.

Related Experiment Videos

  • Evaluated the method's performance against Bonferroni and Random Field Theory.

    • Main Results:

    • The new method provides an accurate upper bound for P values, similar to Bonferroni.
    • It yields lower and more accurate P values for larger FWHM compared to existing methods.
    • Demonstrated approximately 43% lower P values on a typical fMRI dataset compared to the best of Bonferroni or RFT.

    Conclusions:

    • The proposed continuity correction offers improved P value accuracy in statistical parametric mapping.
    • This method enhances statistical power without increasing false positives, particularly for data with larger spatial smoothing.
    • The new approach provides a more reliable statistical threshold for neuroimaging research.