Validating cluster size inference: random field and permutation methods

Hayasaka, Satoru; Nichols, Thomas E.

doi:10.1016/j.neuroimage.2003.08.003

Cited by 463 publications

(387 citation statements)

References 26 publications

Supporting

Mentioning

379

Contrasting

Order By: Relevance

“…Those values may well fall outside the validity domain of the RFT approximations underlying SPM [Worsley et al, 1996]. This confirms the wider applicability of permutation approaches to both family-wise error control [Holmes et al, 1996;Nichols and Holmes, 2002] and cluster-size inference [Bullmore et al, 1999;Hayasaka and Nichols, 2003].…”

Section: Discussionsupporting

confidence: 61%

“…The test also tabulates the distribution of the maximum suprathreshold cluster size [Bullmore et al, 1999;Hayasaka and Nichols, 2003], hence producing cluster-level P values for each FPRsurviving cluster. This second stage is typically more timeconsuming.…”

Section: Single Threshold Testmentioning

confidence: 99%

“…Permutation testing methods [Brammer et al, 1997;Bullmore et al, 1999;Hayasaka and Nichols, 2003;Holmes et al, 1996;Nichols and Holmes, 2002] have the potential to correct for specificity bias, as they can calibrate any test based on mild, nonparametric distributional assumptions. In addition, because they circumvent the classical approximations underlying random field theory (RFT), they offer a robust solution to the multiple comparison problem.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Combined permutation test and mixed‐effect model for group average analysis in fMRI

Mériaux¹,

Roche²,

Dehaene‐Lambertz³

et al. 2006

Human Brain Mapping

View full text Add to dashboard Cite

Abstract:In group average analyses, we generalize the classical one-sample t test to account for heterogeneous within-subject uncertainties associated with the estimated effects. Our test statistic is defined as the maximum likelihood ratio corresponding to a Gaussian mixed-effect model. The test's significance level is calibrated using the same sign permutation framework as in Holmes et al., allowing for exact specificity control under a mild symmetry assumption about the subjects' distribution. Because our likelihood ratio test does not rely on homoscedasticity, it is potentially more sensitive than both the standard t test and its permutation-based version. We present results from the Functional Imaging Analysis Contest 2005 dataset to support this claim. Hum Brain Mapp 27:402-410, 2006.

show abstract

Section: Discussionsupporting

confidence: 61%

Section: Single Threshold Testmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Combined permutation test and mixed‐effect model for group average analysis in fMRI

Mériaux¹,

Roche²,

Dehaene‐Lambertz³

et al. 2006

Human Brain Mapping

View full text Add to dashboard Cite

show abstract

“…For each permutation test, 1000 permutations were carried out. Since the accuracy of P value estimates does not improve dramatically by running more permutations (e.g., standard error (SE) = 0.007 for 1000 permutations compared to SE = 0.004 for 3000 permutations, for a cluster with corrected P = 0.05 (Hayasaka and Nichols, 2003)), we limited the test to 1000 permutations in order to conserve time and disk space.…”

Section: Discussionmentioning

confidence: 99%

“…Such statistic -local maximum, cluster size, or some other statistics -is used in the subsequent test as a test statistic, rather than each voxel value W(v). Only the largest of such test statistics is recorded in each permutation, in order to control the family-wise error (FWE) rate to correct for multiple comparisons (Hayasaka and Nichols, 2003;Holmes et al, 1996). The entire process is repeated for a sufficient number of times, typically between 1000 and 3000 permutations for sufficient confidence in the permutation distribution, each with a different permutation of As and Bs.…”

Section: Permutation Test Frameworkmentioning

confidence: 99%

A non-parametric approach for co-analysis of multi-modal brain imaging data: Application to Alzheimer's disease

Hayasaka

Duarte

et al. 2006

NeuroImage

View full text Add to dashboard Cite

We developed a new flexible approach for a co-analysis of multimodal brain imaging data using a non-parametric framework. In this approach, results from separate analyses on different modalities are combined using a combining function and assessed with a permutation test. This approach identifies several cross-modality relationships, such as concordance and dissociation, without explicitly modeling the correlation between modalities. We applied our approach to structural and perfusion MRI data from an Alzheimer's disease (AD) study. Our approach identified areas of concordance, where both gray matter (GM) density and perfusion decreased together, and areas of dissociation, where GM density and perfusion did not decrease together. In conclusion, these results demonstrate the utility of this new non-parametric method to quantitatively assess the relationships between multiple modalities. D

show abstract

The Neurobiological Role of the Dorsolateral Prefrontal Cortex in Recovery From Trauma

Lyoo

Kim

Yoon

et al. 2011

Arch Gen Psychiatry

125

View full text Add to dashboard Cite

show abstract

Validating cluster size inference: random field and permutation methods

Cited by 463 publications

References 26 publications

Combined permutation test and mixed‐effect model for group average analysis in fMRI

Combined permutation test and mixed‐effect model for group average analysis in fMRI

A non-parametric approach for co-analysis of multi-modal brain imaging data: Application to Alzheimer's disease

The Neurobiological Role of the Dorsolateral Prefrontal Cortex in Recovery From Trauma

Contact Info

Product

Resources

About