On classifying mixture components as clusters
N. T. Longford and J. Bartosova
Abstract
An index is defined for characterising the separation of two distributions
is introduced. It is applied to assessing whether mixture components are
clusters. A related property of being a satellite and a partial ordering
of the components are defined. A sequence of clustering structures is defined
for a finite mixture with a continuum of thresholds that qualify a cluster.
The approach is suitable for outcomes with arbitrary univariate or
multivariate distributions and their mixtures. The properties of the index
are explored by simulations and on examples.
Statistical Modelling 14, 229-255, 2014.
June 2014