Title :
A Method of Using Cluster Analysis to Study Statistical Dependence in Multivariate Data
Author :
Borucki, William J. ; Card, Don H. ; Lyle, Gilbert C.
Author_Institution :
NASA Ames Research Center
Abstract :
A technique is presented that uses both cluster analysis and a Monte Carlo significance test of clusters to discover associations between variables in multidimensional data. The method is applied to an example of a noisy function in three-dimensional space, to a sample from a mixture of three bivariate normal distributions, and to the well-known Fisher´s Iris data.
Keywords :
Clustering algorithms, data analysis, multivariate analysis, nonlinear data structures, pattern recognition.; Algorithm design and analysis; Clustering algorithms; Data analysis; Fluctuations; Gaussian distribution; Iris; Monte Carlo methods; Multidimensional systems; Statistical distributions; Testing; Clustering algorithms, data analysis, multivariate analysis, nonlinear data structures, pattern recognition.;
Journal_Title :
Computers, IEEE Transactions on
DOI :
10.1109/T-C.1975.224162
