Correlations of correlations are not reliable statistics: implications for multivariate pattern analysis. - Archive ouverte HAL Access content directly
Conference Papers Year : 2015

Correlations of correlations are not reliable statistics: implications for multivariate pattern analysis.

(1, 2) , (3, 2) , (2, 1) , (2, 1)
1
2
3

Abstract

Representational Similarity Analysis is a popular framework to flexibly represent the statistical dependencies between multi-voxel patterns on the one hand, and sensory or cognitive stimuli on the other hand. It has been used in an inferen-tial framework, whereby significance is given by a permutation test on the samples. In this paper , we outline an issue with this statistical procedure: namely that the so-called pattern similarity used can be influenced by various effects, such as noise variance, which can lead to inflated type I error rates. What we propose is to rely instead on proper linear models.
Fichier principal
Vignette du fichier
paper_stamlins.pdf (319.83 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01187297 , version 1 (26-08-2015)

Identifiers

  • HAL Id : hal-01187297 , version 1

Cite

Bertrand Thirion, Fabian Pedregosa, Michael Eickenberg, Gaël Varoquaux. Correlations of correlations are not reliable statistics: implications for multivariate pattern analysis.. ICML Workshop on Statistics, Machine Learning and Neuroscience (Stamlins 2015), Bertrand Thirion, Lars Kai Hansen, Sanmi Koyejo, Jul 2015, Lille, France. ⟨hal-01187297⟩
756 View
1334 Download

Share

Gmail Facebook Twitter LinkedIn More