This paper explores the use of multilevel modelling to provide a statistical framework for geodemographic analysis. It argues that combining a neighbourhood classification with a modelling approach to analysis allows the levels of the geodemographic hierarchy to be considered simultaneously, identifying those which are most appropriate to the analysis and allowing the apparent differences between neighbourhood types to be considered in regard to their statistical significance, and to the uncertainty of the estimates. The paper shows how the model can be extended to create a cross-classified multiscale model that makes better use of the locational information available and uses it to improve the efficiency of the neighbourhood targeting. The ideas are illustrated with a case study using a sample of data and the freely available London Output Area Classification to predict which neighbourhoods in London have the highest percentages of Asian school pupils. The multiscale model is shown to outperform the predictions made using geodemographics alone.
Bibliographical notePublication date July 2016.
- multilevel modelling
- neighbourhood targeting
- London Output Area Classification