'Proportion' analysis is a technique for comparing the relative incidence of concentrated deprivation between regions. It is applied when population or household data is available down to the level of small areal units or cells. The technique involves calculating the proportion of households in each cell possessing a given attribute: identifying those cells with extreme proportions: and then drawing inferences based on the incidence of these selected cells. This technique is shown to be sensitive to bias in the presence of variations in size of the basic cells. A general formula is derived for calculating the extent of the bias, under simplifying assumptions. Tables are given, illustrating the extent of the bias in particular cases.
Get full access to this article
View all access options for this article.
References
1.
Clarke, J.I., Dewdney, J.C., Evans, I.S., Rhino, D.W. and Visvalingam, M. (1980). People in Britain: A Census AtlasCensus Research Unit, University of Durham, (in collaboration with Office of Population Censuses and Surveys , and General Register Office, Scotland).
2.
Department Of Environment. (1974). Census Indicators of Urban Deprivation: Great Britain. Working Note No. 6 . London.
3.
Visvalingam, M. (1976). Chi-square as an alternative to ratios for statistical mapping and analysis. University of Durham: Census Research Unit. Durham.
4.
Visvalingam, M. and Dewdney, J.C. (1977). The effects of the size of areal units on ratio and chi-square mapping. University of Durham: Census Research Unit. Durham.
