Unmixing Aggregate Data: Estimating the Social Composition of Enumeration Districts

  title={Unmixing Aggregate Data: Estimating the Social Composition of Enumeration Districts},
  author={Ryan Mitchell and D. J. Martin and Glles M. Foody},
  journal={Environment and Planning A},
  pages={1929 - 1941}
In this paper the authors address the problem of interpreting and classifying aggregate data sources and draw parallels between tasks commonly encountered in image processing and census analysis. Both of these fields already have a range of standard classification tools which are applied in such situations, but these are hindered by the aggregate nature of the input data. An approach to ‘unmixing’ aggregate data, and thus to revealing the nature of the subunit variation masked by aggregation… 

Figures and Tables from this paper

Threshold Analysis Approach to the Objectification of Social Space: The Structure of Household Types in Sydney
Limited research has been undertaken into the geographical structure of familism within urban areas in recent decades despite significant changes in the nature of family living arrangements. A major
The Application of Zone-Design Methodology in the 2001 UK Census
The authors identify the advantages of using an intra-area correlation measure for the maximization of social homogeneity within output areas, and explore the differences between the 1991 and 2001 approaches to output geography.
Is there an 'i' in gdis? the problem of representation in geodemographic and lifestyle systems
The paper considers the potential pitfalls of transforming and synthesising social-economic and behavioural-attitudinal datasets across multiple levels of aggregation, with respect to Geodemographic
Creating Small Area Measures of Urban Deprivation
In recent years, the scale and pace of urban change have been associated with fine-scale fragmentation of the lifestyles of urban populations. One manifestation of this is that households of diverse
The Spatial Targeting of Urban Policy Initiatives: A Geodemographic Assessment Tool
Government frequently adopts an area-based approach to the targeting of urban policy initiatives as an indirect way of reaching the individuals that the initiatives are intended to help. The paper
New Data and Approaches for Urban Analysis: Modelling Residential Densities
It is argued that closer RS-GIS integration will create new opportunities for modelling and understanding urban systems and take some steps towards that end-goal by considering the contribution that four different datasets make to generating improved models of residential densities for a study region of Bristol, England.
An Applied Microsimulation Model: Exploring Alternative Domestic Water Consumption Scenarios
Microsimulation is now a long-established tool for the evaluation, projection and retrospective analysis of a diverse range of subjects including kinship networks (Zhao, 1996), income redistribution
Clarifying and re-conceptualising density


The Mapping of Small-Area Census Data—A Consideration of the Role of Enumeration District Boundaries
A study of Newcastle upon Tyne EDs shows that ED boundaries do not, in fact, mark the boundaries of distinct areas, and the presumption against the use of ED boundaries for cartographic representation is reinforced.
Approaches for the production and evaluation of fuzzy land cover classifications from remotely-sensed data
  • G. Foody
  • Environmental Science, Mathematics
  • 1996
Remote sensing is an attractive source of data for land cover mapping applications, and when pixels may have multiple and partial class membership measures of the strength of class membership may be output and, if strongly related to the land cover composition, mapped to represent such fuzzy land cover.
The sample of anonymised records.
  • C. Marsh
  • Art
    ESRC Data Archive bulletin
  • 1991
The author describes the purchase of two samples of anonymized records from the 1991 United Kingdom census and the creation of a center at the University of Manchester to act both as distributor of
Classification of remotely sensed data by an artificial neural network: issues related to training data characteristics
In this paper a feed-forward artificial neural network using a variant of the back-propagation learning algorithm was used to classify agricultural crops from synthetic aperture radar data, demonstrating the dependency of the two classification techniques on representative training samples and normally distributed data.
Introductory Digital Image Processing: A Remote Sensing Perspective
Introductory Digital Image Processing: A Remote Sensing Perspective focuses on digital image processing of aircraft- and satellite-derived, remotely sensed data for Earth resource management applications.
Class and Stratification. An Introduction to Current Debates
Introduction to the Second Edition. Introduction to the First Edition. Part I: Explaining Inequality: Introduction. Social Order and Theories of Social Differentiation. Stratification and the Debate
Introduction to remote sensing
This popular text introduces students to widely used forms of remote sensing imagery and their applications in plant sciences, hydrology, earth sciences, and land use analysis. Providing
Generalization Performance of Overtrained Back-Propagation Networks
The performance of the back-propagation (BP) algorithm is investigated under overtraining for three different tasks, finding that interpolation performance is shown to decrease with overtraining and size of the sample space.
Multi-Source Image Classification II: An Empirical Comparison of Evidential Reasoning and Neural Network Approaches
RESUMELes methodes classiques reconnues pour la classification d'images, comme la classification par maximum de vraisemblance, ne sont pas toujours appropriees pour traiter, de nos jours, les donnees
Backpropagation neural nets with one and two hidden layers
Experimental results indicate that four-layered networks are more prone to fall into bad local minima, but that three- and four-Layered networks perform similarly in all other respects.