This portion of the guide is divided into multiple sections covering basic principles of clustering analyses, hierarchical clustering, and K-means clustering in Prism.

The primary concepts of clustering

Distance methods

Linkage methods in hierarchical clustering

K-means++ initialization

K-means algorithms

Selecting the optimal number of clusters

Elbow plot and within cluster sum of squares (WCSS)

Silhouette score and the silhouette plot

Gap statistic and gap plot

Ball-Hall index

C index

Calinski-Harabasz index

Davies-Bouldin index

Dunn index

Frey index

Gamma index

GPlus index

Hartigan index

Krzanowski-Lai index

McClain and Rao index

Point-Biserial index

Ratkowsky index

Tau index

TraceW index

Hierarchical clustering

How to: Hierarchical clustering analysis

Entering data for hierarchical clustering

Specifying the clustering variables and clustering direction

Analysis options for hierarchical clustering

Choosing the preferred (tabular) outputs

Selecting visual (graph) outputs

Results of hierarchical clustering

Analysis Checklist: hierarchical clustering

K-means clustering

How to: K-means clustering

Entering data for K-means clustering

Specify variables to use for calculating distances

Analysis options for K-means clustering

Choosing the preferred (tabular) outputs

Selecting visual (graph) outputs

Results of K-means clustering

Primary results

Tabular results

Clustered data

Optional results

Clusters details

Distance of each row to its cluster center

Initial centroids

Scaled data

Analysis Checklist: K-means clustering