Christy et al. propose cluster-based approach to outlier detection as part of the preprocessing step. However, I don't think the plots are very interpretable. The authors use the R mclustbic function to determine BIC at different cluster sizes using GMMs - what is this supposed to show?
I would think the plots are designed to illustrate effectiveness of their outlier detection methods, but this fact is not obvious to me.
Thoughts on this?