Generation of Random Clusters with Specified Degree of Separation
Journal of ClassificationPublished 1 September 2006
Weiliang Qiu, Harry Joe
Citations118
SJR quartileQ1
SJR score0.71
SNIP1.33
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
A random cluster generation algorithm that has the desired features: the population degree of separation between clusters and the nearest neighboring clusters can be set to a specified value, based on a separation index.
Abstract
We propose a random cluster generation algorithm that has the desired features: (1) the population degree of separation between clusters and the nearest neighboring clusters can be set to a specified value, based on a separation index; (2) no constraint is imposed on the isolation among clusters in each dimension; (3) the covariance matrices correspond to different shapes, diameters and orientations; (4) the full cluster structures generally could not be detected simply from pair-wise scatterplots of variables; (5) noisy variables and outliers can be imposed to make the cluster structures harder to be recovered. This algorithm is an improvement on the method used in Milligan (1985).
Keywords
Computer ScienceMathematics
Using multivariate statistics
77,462 Citations1983Barbara G. Tabachnick, Linda S. Fidell
In this Section: 1. Multivariate Statistics: Why? and 2. A Guide to Statistical Techniques: Using the Book Research Questions and Associated Techniques.
CURE
1,909 Citations1998Sudipto Guha, Rajeev Rastogi +1 more
This work proposes a new clustering algorithm called CURE that is more robust to outliers, and identifies clusters having non-spherical shapes and wide variances in size, and demonstrates that random sampling and partitioning enable CURE to not only outperform existing algorithms but also to scale well for large databases without sacrificing clustering quality.
Journal of ClassificationA study of standardization of variables in cluster analysis
873 Citations1988Glenn W. Milligan, Martha C. Cooper
The present simulation study examined the standardization problem and found that those approaches which standardize by division by the range of the variable gave consistently superior recovery of the underlying cluster structure.
Psychological MethodsProperties of the Hubert-Arable Adjusted Rand Index.
740 Citations2004Douglas Steinley
An investigation of cluster validation indices that relates 4 of the indices to the L. Arabie (1985) adjusted Rand index is provided, which provides a method for testing the significance of observed adjusted Rand indices.
Multivariate Behavioral ResearchA Study of the Comparability of External Criteria for Hierarchical Cluster Analysis
488 Citations1986Glenn W. Milligan, Martha C. Cooper
The results of the study indicated that the Hubert and Arabie adjusted Rank index was best suited to the task of comparison across hierarchy levels.
Psychological MethodsLocal Optima in K-Means Clustering: What You Don't Know May Hurt You.
263 Citations2003Douglas Steinley
The results suggest the need for some strategy to study the local optima problem for a specific data set or to identify methods for finding "good" starting values that might lead to the best solutions possible.
Journal of Multivariate AnalysisGenerating random correlation matrices based on partial correlations
245 Citations2005Harry Joe
Journal of ClassificationWeighting and selection of variables for cluster analysis
164 Citations1995R. Gnanadesikan, J. R. Kettenring +1 more
This paper reports on the performance of nine methods on eight “leading case” simulated and real sets of data and demonstrates shortcomings of weighting based on the standard deviation or range as well as other more complex schemes in the literature.
PsychometrikaAn Algorithm for Generating Artificial Test Clusters
155 Citations1985Glenn W. Milligan
An algorithm for generating artificial data sets which contain distinct nonoverlapping clusters is presented, useful for generating test data sets for Monte Carlo validation research conducted on clustering methods or statistics.
PsychometrikaA Variable-Selection Heuristic for K-means Clustering
132 Citations2001Michael J. Brusco, J. Dennis Cradit
A cluster analysis of real-world financial services data revealed that using the variable-selection heuristic prior to the K-means algorithm resulted in greater cluster stability, indicating the heuristic is extremely effective at eliminating masking variables.
Journal of ClassificationA validation study of a variable weighting algorithm for cluster analysis
82 Citations1989Glenn W. Milligan
The results indicate that the De Soete procedure is effective in identifying extraneous variables which do not contribute information about the true cluster structure.
PsychometrikaA Comparison of the Classification Capabilities of the 1-Dimensional Kohonen Neural Network with Two Pratitioning and Three Hierarchical Cluster Analysis Algorithms
70 Citations1998Niels G. Waller, Heather A. Kaiser +2 more
A comparison of the classification capabilities of the 1-dimensional Kohonen neural network with two partitioning and three hierarchical cluster methods in 2,580 data sets with known cluster structure finds the performance of the Kohonen networks was similar to, or better than, the other methods.
Computational Statistics & Data AnalysisSeparation index and partial membership for clustering
52 Citations2004Weiliang Qiu, Harry Joe
A new separation index is proposed that measures the magnitude of gaps between any two clusters in a partition, by projecting the data in a pair of clusters into a one-dimensional space in which they have the maximum separation.
PsychometrikaComparative Evaluation of Two Superior Stopping Rules for Hierarchical Cluster Analysis
50 Citations1994Robert S. Atlas, John E. Overall
Multivariate Behavioral ResearchUnivariate Screening Measures for Cluster Analysis
17 Citations1995John R. Donoghue
Using moment-based statistics to screen variables; only variables which pass the screening are then used in clustering, and screening variables appears a viable alternative to both ultrametric weights and forward selection.