search

JuliaDynamics / Associations.jl

Algorithms for quantifying associations, independence testing and causal inference from data.
https://juliadynamics.github.io/Associations.jl/stable/
Other
147 stars 12 forks source link

Add convergent cross sorting #370

Open rafaqz opened 3 months ago

rafaqz commented 3 months ago

Another one....

https://www.nature.com/articles/s41598-021-98864-2 https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10336384/#RSOS221590C29

rafaqz commented 3 months ago

Maybe useful, but not licensed: https://github.com/lbreston/CCS

kahaaga commented 3 months ago

Looks useful, @rafaqz! From a brief glance at their supplementary information, this looks pretty straight forward to implement.

One parameter in their method is T, the fraction of pairwise distances considered. They say "Rougher signals require a larger fraction of pairwise distances to be considered because their ranks are less tightly coupled". To determine roughness, they use a measure involving the standard deviation. We should be maximally flexible, so we should implement a dispatch-based method for allowing not only standard deviation but other measures of "data spread" when calculating T.