An Examination of the Effect of Six Types of Error Perturbation on Fifteen Clustering Algorithms
- 1 September 1980
- journal article
- Published by Cambridge University Press (CUP) in Psychometrika
- Vol. 45 (3) , 325-342
- https://doi.org/10.1007/bf02293907
Abstract
An evaluation of several clustering methods was conducted. Artificial clusters which exhibited the properties of internal cohesion and external isolation were constructed. The true cluster structure was subsequently hidden by six types of error-perturbation. The results indicated that the hierarchical methods were differentially sensitive to the type of error perturbation. In addition, generally poor recovery performance was obtained when random seed points were used to start the K-means algorithms. However, two alternative starting procedures for the nonhierarchical methods produced greatly enhanced cluster recovery and were found to be robust with respect to all of the types of error examined.Keywords
This publication has 24 references indexed in Scilit:
- The validation of four ultrametric clustering algorithmsPattern Recognition, 1980
- Ultrametric Hierarchical Clustering AlgorithmsPsychometrika, 1979
- U-Statistic Hierarchical ClusteringPsychometrika, 1978
- Evaluating object set partitions: Free-sort analysis and some generalizationsJournal of Verbal Learning and Verbal Behavior, 1976
- Mixture model tests of cluster analysis: Accuracy of four agglomerative hierarchical methods.Psychological Bulletin, 1976
- Nonmetric Grouping: Clusters and CliquesPsychometrika, 1975
- Representation of Structure in Similarity Data: Problems and ProspectsPsychometrika, 1974
- Hierarchical clustering schemesPsychometrika, 1967
- Assessing similarity between profiles.Psychological Bulletin, 1953
- rp and other Coefficients of Pattern SimilarityPsychometrika, 1949