As a self-described, spatial demographer, and with a formative background in geography and planning, I am interested in substantive questions at the nexus of demography, geography, quantitative methods, and public policy. I believe that addressing contemporary substantive demographic and public policy-related questions increasingly requires an understanding of spatial concepts, data, and methods. Spatial concepts are seemingly simultaneously both well-known yet ironically ignored; for example, the concept of spatial dependence. However, levels of ignorance surrounding fundamental spatial concepts are waning (Logan, 2012; Matthews, 2016). Indeed, the increased familiarity with spatial concepts in academia and among policy makers (and also among the lay public) is a product of technological and computational developments that enhance the ability to collect, store, integrate, analyze, visualize, and interpret complex data, including spatial data. Researchers and policy makers are paying attention to old (and now digitized), new, and emerging forms of spatial data, and they recognize the need to be clear regarding a series of interrelated analytical choices, as these choices are not benign. The most relevant “spatial” choices relate to the definitions of place, geographic levels and scales of analysis, spatial interactions and any interdependencies between places, and to basic spatial concepts (for example, distance and relative location) and those that are more complex (for example, spatial heterogeneity and spatial nonstationarity). Related, in many areas of basic and applied demographic research the array of questions that are asked are often constrained by the availability of data, including the availability of spatial data. As stated above, technological changes in computational capacity coupled with the design and adoption of sophisticated data structures (relational databases) and information systems (geographic information systems) has opened up opportunities in data linkage. These opportunities in data linkage have facilitated the transition from single-level to multi-level analysis, from cross-sectional to longitudinal analysis, and from aspatial to spatial analysis. Geography has emerged as one of the main organizing frameworks for both hierarchical and complex nonhierarchical data structures. Leveraging geography, specifically location and relative location data, enables the

中文翻译：

---

空间人口学中的方法和应用：2

作为一名自我描述的空间人口学家，并具有地理和规划方面的形成背景，我对人口学、地理、定量方法和公共政策之间的联系的实质性问题感兴趣。我相信，解决当代实质性的人口和公共政策相关问题越来越需要对空间概念、数据和方法的理解。空间概念似乎同时既广为人知又讽刺地被忽视；例如，空间依赖的概念。然而，对基本空间概念的无知程度正在减弱（Logan，2012；Matthews，2016）。确实，学术界和政策制定者（以及非专业人士）对空间概念的日益熟悉是技术和计算发展的产物，这些发展增强了收集、存储、整合、分析、可视化和解释复杂数据的能力，包括空间数据。研究人员和政策制定者正在关注旧的（现在是数字化的）、新的和新兴的空间数据形式，他们认识到需要明确一系列相互关联的分析选择，因为这些选择不是良性的。最相关的“空间”选择涉及地点的定义、地理层次和分析尺度、空间相互作用和地点之间的任何相互依存关系，以及基本的空间概念（例如，距离和相对位置）和那些更复杂的（例如，空间异质性和空间非平稳性）。与此相关的是，在基础和应用人口研究的许多领域中，所提出的一系列问题通常受到数据可用性的限制，包括空间数据的可用性。如上所述，计算能力的技术变革以及复杂数据结构（关系数据库）和信息系统（地理信息系统）的设计和采用为数据链接开辟了机会。这些数据链接的机会促进了从单级分析到多级分析、从横截面分析到纵向分析以及从非空间分析到空间分析的转变。地理已成为分层和复杂的非分层数据结构的主要组织框架之一。借助地理，