PROC CLUSTER with METHOD=AVERAGE (average linkage) computes the distance between two clusters being merged. How is this distance defined under average linkage?
Select an answer to reveal the explanation.
Short Explanation and Infographic
Here's the deal — c is correct because average linkage (METHOD=AVERAGE in PROC CLUSTER) defines the between-cluster distance as the arithmetic mean of all pairwise distances between every member of cluster A and every member of cluster B. This intermediate criterion avoids the chaining problem of single linkage and the compactness bias of complete linkage.
Full explanation below image
Full Explanation
C is correct because average linkage (METHOD=AVERAGE in PROC CLUSTER) defines the between-cluster distance as the arithmetic mean of all pairwise distances between every member of cluster A and every member of cluster B. This intermediate criterion avoids the chaining problem of single linkage and the compactness bias of complete linkage. A is single linkage (METHOD=SINGLE). B is complete linkage (METHOD=COMPLETE). D is centroid linkage (METHOD=CENTROID), which uses cluster centroids, not all pairwise member distances.