A data scientist applies hierarchical clustering using PROC CLUSTER with METHOD=WARD. What does Ward's linkage criterion minimize at each merge step?
Select an answer to reveal the explanation.
Short Explanation and Infographic
Here's the deal — c is correct because Ward's linkage minimizes the increase in total within-cluster sum of squares (WCSS) when two clusters are merged, which tends to produce compact, similarly-sized clusters. A describes complete linkage (maximum distance).
Full explanation below image
Full Explanation
C is correct because Ward's linkage minimizes the increase in total within-cluster sum of squares (WCSS) when two clusters are merged, which tends to produce compact, similarly-sized clusters. A describes complete linkage (maximum distance). B describes average linkage (UPGMA). D describes centroid linkage.