A neighbourhood Output Area Classification from the 2021 and 2022 UK censuses

Abstract

UK‐wide multivariate neighbourhood classifications have been built using small area population data following every census since 1971, and have been built using Output Area geographies since 2001. Policy makers in both the public and private sectors find such taxonomies, typically arranged into hierarchies of Supergroups, Groups and Subgroups, useful across a wide range of applications in business and service planning. Recent and forthcoming releases of small area census statistics pose new methodological challenges. For example, the 2022 Scottish Census was carried out a year after those in other UK nations, and some of the variables now collected across different jurisdictions do not bear direct comparison with one another. Here we develop a methodology to accommodate these issues alongside the more established procedures of variable selection, standardisation, transformation, class definition and labelling.

Classifying and mapping residential structure through the London Output Area Classification

“…The methodology employed for the creation of the LOAC 2021 closely aligns with the established framework used in the development of the national 2021 Output Area Classification (OAC), developed in partnership with the Office for National Statistics (ONS) (Wyszomierski et al, 2023). LOAC was developed through a partnership with the Greater London Authority (GLA) and supported by the insightful contributions of the LOAC 2021 Advisory Group.…”

“…Consistent with previous Output Area classifications, our intention was to create a general purpose classification, representing the full reach of the Census. The 68 selected variables are chosen to represent the domains of demography, ethnicity and origins, living arrangements, usual residence, health and education and employment, as justified in Wyszomierski et al (2023) and set out in Table 1 of the supplementary materials. The data spanned multiple domains, each representing crucial aspects or influences on residential differentiation.…”

“…Clustergrams are therefore interpreted by looking for a cluster value that offers a good separation of the cluster means (indicated by red dots) on the y-axis. Other diagnostic tests conducted followed those reported in Wyszomierski et al (2023). In this instance, following detailed consultation with the Advisory Group, a seven-cluster Supergroup solution was selected.…”

“…Geodemographic classifications have been developed in the UK over the past 50 years (Harris et al, 2005;Webber and Burrows, 2018), with the first model being created for the city of Liverpool in the 1970s from newly digitised census records (Webber, 1975). This model was then later expanded to the national extent (Webber, 1977;Webber and Craig, 1978), and subsequently other census-based geodemographic classifications have been created after each decennial census of the population, in 1981 (Charlton et al, 1985), 1991 (Brown and Batey, 1994), 2001 Rees, 2006, 2007), 2011 (Gale et al, 2016), and most recently 2021 (Wyszomierski et al, 2023). These are all general purpose classifications, but more specialised variants have been developed for particular policy domains, such as higher education (Singleton and Longley, 2009) and the adoption of new information and communications technology (Longley et al, 2008;Singleton et al, 2016a), As such, geodemographics are frequently seen as part of evolving digital infrastructure for modelling and policy analysis (Longley and Harris, 1999).…”

“…Second, if some attributes have extreme distributions, this can adversely affect the efficacy of the clustering process and can compromise the quality of the geodemographic classification. The OACs for 2001–2021 (Gale et al, 2016; Vickers and Rees, 2007; Wyszomierski et al, 2023) all applied a single model to every small area across the study area, to the detriment of representing the widely acknowledged distinctiveness of Greater London, which is represented using a narrow range of clusters as a consequence. As discussed elsewhere (Singleton and Longley, 2015), such issues are linked to the uniqueness of London relative to the rest of the UK.…”