"Concurrence topology" is a new nonparametric method for describing high-order
statistical dependence among up to dozens of binary variables.
This website provides supplementary material for the accepted article:
"Describing high-order statistical dependence using 'Concurrence Topology',
with application to functional MRI brain data". 2014. Steven P. Ellis and Arno Klein.
A 2012 preprint exists on arXiv:1212.1642
Software (in R):
Posted on StatLib under the name "ConcurrenceTopology": http://lib.stat.cmu.edu/
and on Github: https://github.com/binarybottle/concurrencetopology
Documents:
Guide to use of the software: SoftwareHowTo.txt (fig1, fig2)
Some mathematical theory underlying the software: ComputationalHomologyNotes.pdf
Some topics not included in the article: Background.pdf
Data:
Supplemental examples in an R file: TestPatterns.RData
fMRI demographic (+diagnosis) and BOLD data plus documentation: fmri.tar.gz
Some results: results.tar.gz
statistical dependence among up to dozens of binary variables.
This website provides supplementary material for the accepted article:
"Describing high-order statistical dependence using 'Concurrence Topology',
with application to functional MRI brain data". 2014. Steven P. Ellis and Arno Klein.
A 2012 preprint exists on arXiv:1212.1642
Software (in R):
Posted on StatLib under the name "ConcurrenceTopology": http://lib.stat.cmu.edu/
and on Github: https://github.com/binarybottle/concurrencetopology
Documents:
Guide to use of the software: SoftwareHowTo.txt (fig1, fig2)
Some mathematical theory underlying the software: ComputationalHomologyNotes.pdf
Some topics not included in the article: Background.pdf
Data:
Supplemental examples in an R file: TestPatterns.RData
fMRI demographic (+diagnosis) and BOLD data plus documentation: fmri.tar.gz
Some results: results.tar.gz