PATTERN CLUSTERING BY MULTIVARIATE MIXTURE ANALYSIS
Abstract
Cluster analysis is reformulated as a problem of estimating the parameters of a mixture of multivariate distributions. The maximum-likelihood theory and numerical solution techniques are developed for a fairly general class of distrubitions. The theory is applied to mixtures of multivariate normals ('NORMIX') and mixtures of multivariate Bernoulli distributions ('Latent Classes'). The feasibility of the procedures is demonstrated by two examples of computer solutions for normal mixture models of the Fisher Iris data and of artificially generated clusters with unequal covariance matrices.
Document Details
- Document Type
- Technical Report
- Publication Date
- Mar 01, 1969
- Accession Number
- AD0684087
Entities
People
- John H. Wolfe