Standard statistical methods often fail to account for the spatial patterns in brain maps
In short: Researchers who tested ten different statistical frameworks found that many current methods for comparing brain maps produce inaccurate results. By using controlled simulations and real neuroimaging data, the study showed that even advanced models designed to account for spatial patterns can still lead to an increased rate of false positives.
The researchers used simulations and empirical datasets to test how different null models perform when analyzing brain topography. They found that while models ignoring spatial patterns consistently overestimate significance, even more sophisticated spatially-constrained models can still produce unreliable, overly optimistic statistical estimates.
Why it matters: Neuroimaging researchers need more statistically rigorous methods to compare brain maps accurately.
Opens the Intellect+ feed with this card first. Swipe up for the next one.
Sources
- Source: Research: Markello and Misic (2021). Comparing spatial null models for brain maps. NeuroImage. · cc-by
To cite this card, link to https://intellectplus.co.uk/app/science-research-standard-statistical-methods-often-fail-to-account-for-the-s.
How we source, check and correct cards: Editorial standards.
General information, not professional advice. Spotted an error? Flag the card or see corrections and complaints.
Intellect Plus is a visual educational discovery platform for exploring fascinating facts and ideas. Brain Food, Not Brain Rot. What is Intellect Plus?
Related
More in Science · Latest · A–Z · All topics