A data scientist applies PROC HPCLUS with k=5 to customer transaction data. After initial cluster assignment, the data scientist suspects cluster 3 contains outliers. Which SAS approach best identifies outlier observations within a cluster?
Select an answer to reveal the explanation.
Short Explanation and Infographic
Here's the deal — a is correct because within a k-means cluster, outliers are observations that are far from the centroid. Computing each observation's Euclidean distance to its assigned centroid and flagging those beyond a threshold (e.g., mean + 3*SD of distances within that cluster) is the standard cluster-based outlier detection approach.
Full explanation below image
Full Explanation
A is correct because within a k-means cluster, outliers are observations that are far from the centroid. Computing each observation's Euclidean distance to its assigned centroid and flagging those beyond a threshold (e.g., mean + 3*SD of distances within that cluster) is the standard cluster-based outlier detection approach. B (increasing k) may split cluster 3 but doesn't identify outliers systematically. C (PROC HPLOGISTIC) requires labeled outlier data, which is not available here. D (PROC UNIVARIATE) identifies variable-level extremes but ignores multivariate cluster membership context.