search

SystemsGenetics / KINC

Knowledge Independent Network Construction
MIT License
11 stars 4 forks source link

Dynamic correlation analysis #113

Closed spficklin closed 4 years ago

spficklin commented 4 years ago

When small sample sizes are used, Pearson correlation performs better than Spearman. But for large samples Spearman is preferred. When using GMMs some clusters are small and some are large, but KINC requires a blanket correlation method for all clusters. Perhaps we should consider dynamically choosing the best correlation method given the sample size.

This will probably affect the cmx output file as we should probably keep track of which correlation method was used.

spficklin commented 4 years ago

This would be great! But to not keep issues open forever, I'm tagging as enhancement and "For the Future" so we can pull it up again in the future.