Developing an Individual-level Geodemographic Classification
Developing an Individual-level Geodemographic Classification
复制标题
DOI：
10.1007/s12061-017-9233-7
复制
发表时间：
2018-09-01
影响因子：
1.9
通讯作者：
Birkin, Mark
中科院分区：
文献类型：
--
作者：
Burns, Luke;See, Linda;Birkin, Mark
地理人口统计学是对社会经济数据在空间上的明确分类，可用于按居住地对个人进行描述和分析。地理人口信息由公共部门用于规划和资源分配，但在商业部门的应用中也有相当大的用途。早期的地理人口统计系统，如英国的ACORN(居住社区分类)，只使用以地区为基础的人口普查数据，但较新的系统增加了补充信息层，例如信用详细信息和调查数据，以提供更好的阶级区分。虽然现在已经有了更多的数据，但地理人口统计系统基本上仍然是基于基于地区的人口普查信息。这在一定程度上是因为隐私法要求在总体水平上公布人口普查数据，但主要是因为许多研究仍然是专有的。家庭一级的分类确实存在，但它们往往基于地区和家庭数据集之间的回归。本文提出了一种仅使用人口普查数据在个人一级创建地理人口分类的不同方法。提出了一个通用的框架，它对来自英国人口普查小区域微数据的数据进行分类，然后将产生的簇分配给通过微模拟创建的合成种群。然后将该框架应用于为利兹市建立一个以个人为基础的系统，使用2001年人口普查的数据进行了演示，并使用英国家庭小组调查的个人和家庭调查数据进一步进行了验证。
Geodemographics is a spatially explicit classification of socio-economic data, which can be used to describe and analyse individuals by where they live. Geodemographic information is used by the public sector for planning and resource allocation but it also has considerable use within commercial sector applications. Early geodemographic systems, such as the UK's ACORN (A Classification of Residential Neighbourhoods), used only area-based census data, but more recent systems have added supplementary layers of information, e.g. credit details and survey data, to provide better discrimination between classes. Although much more data has now become available, geodemographic systems are still fundamentally built from area-based census information. This is partly because privacy laws require release of census data at an aggregate level but mostly because much of the research remains proprietary. Household level classifications do exist but they are often based on regressions between area and household data sets. This paper presents a different approach for creating a geodemographic classification at the individual level using only census data. A generic framework is presented, which classifies data from the UK Census Small Area Microdata and then allocates the resulting clusters to a synthetic population created via microsimulation. The framework is then applied to the creation of an individual-based system for the city of Leeds, demonstrated using data from the 2001 census, and is further validated using individual and household survey data from the British Household Panel Survey.