Clustering from ordination
From MaRDI portal
Extensions to principal coordinate clustering are described. Motivated by the recognition that there is no reason for the internal properties of a subset of objects to be determined by those of any other, the objects are separated into two subsets based on the first principal coordinate, and the process repeated for each subset alone. Objects located in the vicinity of zero can be included in both subsets. Conditions are established for which this separation is equivalent to one based on the polarization decomposition.
Recommendations
Cites work
- Conditional clusters, musters, and probability
- Euclidean consensus dendrograms and other classification structures
- Hierarchical clustering from principal coordinates: An efficient method for small to very large numbers of objects
- scientific article; zbMATH DE number 3945948 (Why is no real title available?)
- scientific article; zbMATH DE number 3982318 (Why is no real title available?)
- scientific article; zbMATH DE number 3766841 (Why is no real title available?)
- scientific article; zbMATH DE number 3473132 (Why is no real title available?)
- Optimal attribute sets for identifications and diagnoses
- Some distance properties of latent root and vector methods used in multivariate analysis
- The Length of a Generation
- What is Projection Pursuit?
Cited in
(3)
This page was built for publication: Clustering from ordination
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1096286)