Using Hierarchical Clustering to Explore Patterns of Deprivation Among English Local Authorities

Abstract

ABSTRACTBackgroundThe English Indices of Multiple Deprivation (IMD) is widely used as a measure of deprivation of geographic areas in analyses of health inequalities between places. However, similarly ranked areas can differ substantially in the underlying domains and indicators that are used to calculate the IMD score. These domains and indicators contain a richer set of data that might be useful for classifying local authorities. Clustering methods offer a set of techniques to identify groups of areas with similar patterns of deprivation. This could offer insights into areas that face similar challenges.MethodsHierarchical agglomerative (i.e. bottom-up) clustering methods were applied to sub-domain scores for 152 upper-tier local authorities. Recent advances in statistical testing allow clusters to be identified that are unlikely to have arisen from random partitioning of a homogeneous group. The resulting clusters are described in terms of their subdomain scores and basic geographic and demographic characteristics.ResultsFive statistically significant clusters of local authorities were identified. These clusters represented local authorities that were:Most deprived, predominantly urban;Least deprived, predominantly rural;Less deprived, rural;Deprived, high crime, high barriers to housing; andDeprived, low education, poor employment, poor health.ConclusionHierarchical clustering methods identify five distinct clusters that do not correspond closely to quintiles of deprivation. These methods can be used to draw on the richer set of information contained in the IMD domains and may help to identify places that face similar challenges, and places that appear similar in terms of IMD scores, but that face different challenges.