The Effect of Cluster Size, Dimensionality, and the Number of Clusters on Recovery of True Cluster Structure

Authors:
Glenn W. Milligan;S. C. Soon;Lisa M. Sokol
Affiliations:
Faculty of Management Sciences, Ohio State University, Columbus, OH 43210.;College of Administrative Sciences, Ohio State University, Columbus, OH 43210.;Flight Systems, Inc., Arlington, VA 22209.
Venue:
IEEE Transactions on Pattern Analysis and Machine Intelligence
Year:
1983

Citing 0
Cited 4

Minimum spanning tree based split-and-merge: A hierarchical clustering method

Information Sciences: an International Journal
RSQRT: An heuristic for estimating the number of clusters to report

Electronic Commerce Research and Applications
A fuzzy multistage evolutionary (FUME) clustering technique

Pattern Recognition Letters
Enhancing minimum spanning tree-based clustering by removing density-based outliers

Digital Signal Processing

Quantified Score

Hi-index	0.14

Visualization

Abstract

An evaluation of four clustering methods and four external criterion measures was conducted with respect to the effect of the number of clusters, dimensionality, and relative cluster sizes on the recovery of true cluster structure. The four methods were the single link, complete link, group average (UPGMA), and Ward's minimum variance algorithms. The results indicated that the four criterion measures were generally consistent with each other, of which two highly similar pairs were identified. The tirst pair consisted of the Rand and corrected Rand statistics, and the second pair was the Jaccard and the Fowlkes and Mallows indexes. With respect to the methods, recovery was found to improve as the number of clusters increased and as the number of dimensions increased. The relative cluster size factor produced differential performance effects, with Ward's procedure providing the best recovery when the clusters were of equal size. The group average method gave equivalent or better recovery when the clusters were of unequal size.