Linkage Methods (Clustering)

The following linkage methods are used in hierarchical clustering:

Ward Linkage (default) – Is based on the idea of minimizing the variance within each cluster. It calculates the distance between two clusters by measuring how much the sum of squared deviations from the mean changes when the two clusters are merged.
Single Linkage – Calculates the distance between two clusters by taking the minimum distance between any two points in the clusters, so it is based on the closest two points in each cluster.
Complete Linkage – Calculates the distance between two clusters by taking the maximum distance between any two points in the clusters, so it is based on the furthest two points in each cluster.
Average Linkage – Calculates the distance between two clusters by taking the average distance between all pairs of points in the clusters.
Weighted Linkage – Variation of average linkage that takes into account the size of each cluster when calculating the distance between them. Larger clusters have a greater influence on the distance calculation than smaller clusters.
Centroid Linkage – Calculates the distance between two clusters by taking the distance between their centroids, or the average position of all points in the cluster.