liveBook · Manning

Complete linkage

As explained in Statistics Slam Dunk

The complete linkage method measures the separation between two clusters by the maximum distance between points in the different clusters.

Complete linkage measures the separation between two clusters using the maximum Euclidean distance between points in different clusters. In hierarchical clustering, it repeatedly merges the closest clusters according to this rule. section 3.9

NBA draft clustering

To group first-round NBA draft selections by pick number and average win shares, calculate a Euclidean distance matrix and pass it to base R's hclust() with method = "complete". Plot the result as a dendrogram and use rect.hclust(hc, k = 2) to mark two clusters.

How Statistics Slam Dunk covers it

How deep it goes
Defines the merge rule and demonstrates its R implementation, then stops at dendrogram visualization and cluster delineation.
Examples
Demonstrates clustering first-round NBA draft selections by pick number and average win shares.
What it assumes
Assumes Euclidean distances and a distance matrix before demonstrating hierarchical clustering from individual records.
What you can do after
Apply it via base R's hclust() to construct and visualize hierarchical clusters.
How it connects
Connects hierarchical clustering with Euclidean distance, distance matrices, dendrograms, and cluster segmentation.

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Statistics Slam Dunk. The section links point to the parts of the book it draws on.