a multivariate statistical technique which assesses the similarities between units or assemblages, based on the occurrence or non-occurrence of specific artifact types or other components within them.
A statistical technique that identifies groups of consumers whose characteristics are highly correlated within each cluster grouping and relatively uncorrelated between clusters. Cluster analysis is typically applied to lifestyle characteristics to facilitate the development of a 'bespoke' profile of a marketplace which offers a more 'human' visualisation of consumer groupings than is available via standard industry market research surveys. Links: This commercial American site gives some further information - Clustan.
Techniques that group objects (e.g., pixels) into clusters according to user-defined rules.