AbstractAbstractSeveral polychotomous characteristics, when expressed in chi-score form, exhibit distributions in property space which deviate from the inherent assumptions of the more commonly used methods of cluster analysis. This paper suggests a novel approach to classification which exploits the observed and inferred characteristics of categorised data. The concepts and methods are applied to data on household composition to extract a demographic typology from the one-kilometre grid square population census data for 1971.
No takes yet. Share an insight, caveat, or question.
M. Visvalingam (1981) studied this question.
Synapse has enriched one closely related paper. Consider it for comparative context: