News for hackers. Stuff that matters.
Re:Visualising Correlations using Graphs by boombard on Friday December 05, 2014 @04:39AM (#8703616)
I agree, it's not perfect - just a useful abstraction. Just the same as arbitrary thresholds for correlation or a p<0.05 significance level - often you lose information but gain insight. From personal experience I've seen MST's map out underlying structures that validate classical chemical kinetics of a system in a logical path: something that would not have been apparent in ordinary thresh-holding approaches

Basically IMO it's good to use all of these techniques together to get a good picture of your system. In the end the greatest limitation is our human cognition to interpret the results, which frankly needs all the help it can get.

Re:Visualising Correlations using Graphs by jburroni on Friday December 05, 2014 @09:46AM (#8704738)
Thank you for the feedback. I prefer to use a graph instead of a tree because I want to spot clusters of relations.