DIANA stands for DIvisive ANAlysis clustering. It is a hierarchical clustering technique that starts with one cluster and subsequently divides the clusters until each cluster is just a single element. At each step, we select the cluster with the most dissimilar elements. The most dissimilar element within that cluster is then used as a starting point in the creation of a new cluster, consequently splitting the original cluster into two. Divisive coefficient is a unit that measures the amount of clustering structures found.
For more information on DIANA, please refer to the work of Kaufman and Rousseeuw (1990), Finding groups in data. Rousseeuw, Peter J., and L. Kaufman. "Finding groups in data." Hoboken: Wiley Online Library (1990).
In the next exercise, we will be covering the concepts of hierarchical clustering using DIANA.
In this exercise, we will perform hierarchal clustering using DIANA. We will be using the...