I am running a hierarchical clustering exercise and trying to evaluate it with different measures like Calinski-Harbasz score and Silhuette score. Could anyone tell or point to any document comparing different clustering evaluation measures, and their pros and cons?

Also, could anyone please tell under what condition, a clustering evaluation measure (like Calinski-Harbasz) would provide misleading results (e.g. presence of excessive outliers) ?

More Ashutosh Karna's questions See All
Similar questions and discussions