Statistical inference and multiple testing correction in classification-based multi-voxel pattern analysis (MVPA): Random permutations and cluster size control

By Johannes Stelzer, Yi Chen, Robert Turner. NeuroImage, 2011

375 citations recorded by the source corpus.

Subfields: Cognitive Neuroscience, Geometry and Topology

View Paper: https://www.semanticscholar.org/paper/efaed8b0c78c0504dbe6901ed4a7686c0b3e8324

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Neuroscience

In Geometry and Topology

Citations in the corpus

Cross‐validation failure: Small sample sizes lead to large error bars (2017, methodology): “The distribution of number of successes is then given by a binomial law (Pereira and Botvinick, 2011; Stelzer et al., 2013).”
Searchlight analysis: Promise, pitfalls, and potential (2013, methodology): “Permutation-based tests have also been proposed (Kriegeskorte et al., 2006), with new techniques increasing their interpretability and computational tractability (Gaonkar and Davatzikos, 2012; Stelzer et al., 2013).”
The Decoding Toolbox (TDT): a versatile software package for multivariate analyses of functional imaging data (2015, background): “In addition, caution is warranted when using permutation approaches to make sure that these tests are not overly liberal (Stelzer et al., 2013), for example because they break up statistical dependencies at the wrong level (i.e., they violate the assumption of exchangeability, Nichols and Holmes,…”
On the distribution of cross-validated Mahalanobis distances (2016, background): “In sum, the normal approximation provides a simple and straightforward way of testing linear combinations of distances, freeing the user of the need to perform permutation statistics [21, 24].”
Prioritizing spatial accuracy in high-resolution fMRI data using multivariate feature weight mapping (2014, methodology): “Around every voxel (center voxel), we constructed a spherical searchlight that contained every neighbor voxel within a given radius r (Kriegeskorte et al., 2006; Stelzer et al., 2013).”
A Primer on Pattern-Based Approaches to fMRI: Principles, Pitfalls, and Perspectives. (2015, methodology): “For testing against chance, permutation tests have proven to be more valid than binomial tests or t tests (Nichols and Holmes, 2002; Noirhomme et al., 2014; Pereira and Botvinick, 2011; Schreiber and Krekelberg, 2013; Stelzer et al., 2013).”
CoSMoMVPA: Multi-Modal Multivariate Pattern Analysis of Neuroimaging Data in Matlab/GNU Octave (2016, methodology): “• focus on reproducibility and maintainability: Inspired by PyMVPA, CoSMoMVPA uses the git distributed version control system (Torvalds et al., 2005)), an extenstive test suite, and continuous integration testing.”
Decoding Dynamic Brain Patterns from Evoked Responses: A Tutorial on Multivariate Pattern Analysis Applied to Time Series Neuroimaging Data (2016, background): “Statistical evaluation of decoding analyses is a complex issue, and there is no consensus yet on the optimal approach (Allefeld, Görgen, & Haynes, 2016; Noirhomme et al., 2014; Schreiber & Krekelberg, 2013; Stelzer, Chen, & Turner, 2013; Nichols & Holmes, 2002).”
The representation of abstract goals in working memory is supported by task-congruent neural geometry (2024, unknown): “Then, the permuted maps were bootstrapped from each participant 10,000 times to create a null distribution of group-level mean [75].”