After running PROC HPCLUS with NCLUST=4, two clusters appear very similar. Which metric best quantifies the separation between these two specific clusters?
Select an answer to reveal the explanation.
Short Explanation
Here's the deal — when two clusters look alike, you need the Euclidean distance between their centroids to quantify how far apart they are in feature space. If that distance is small, those clusters are close and may be candidates for merging.
Full Explanation
The Euclidean distance between the two cluster centroids is correct because it directly quantifies how different those two specific clusters are in feature space. A small centroid distance indicates similar clusters that may be candidates for merging. The within-cluster sum of squares is wrong because it is a global compactness measure. The overall pseudo-F statistic is wrong because it measures global separation versus cohesion. The squared change from the 3-cluster to 4-cluster solution is wrong because it evaluates the overall benefit of adding another cluster globally.