Exercise

Comparing clustering methods: stability measures

As mentioned before, stability measures are a particular kind of internal measures that gauge the consistency of a clustering result by comparing it with the clusters obtained after each column is removed, one at a time. clValid implements four stability measures: APN, AD, ADM and FOM. More details can be found by typing help(clValid) in the console.

Let's compare the same three clustering methods according to these four stability measures on your mall_scaled data.

Instructions 1/4

undefined XP

1
2
3
4

Create a character vector named methods with the entries "hierarchical", "kmeans" and "pam". These are the three clustering algorithms we are going to focus our analysis on.