Full Citation
Title: Data Formats, Coordinate Reference Systems, and Differential Privacy Frameworks
Citation Type: Book, Section
Publication Year: 2023
ISBN:
ISSN:
DOI: 10.1007/978-3-031-24857-3_3
NSFID:
PMCID:
PMID:
Abstract: This is our last conceptual chapter. In this chapter we formally discuss three topics with important practical implications for SSEM: spatial data formats (vector and raster), coordinate reference systems (projected and unprojected), and data privacy or projection frameworks (data swapping, differential privacy, and jittering). Accordingly, the purpose of this chapter is to provide readers with the set of practical elements and understandings required to start reading spatial data files and building, visualizing, and analyzing splace datasets while being aware of the relevance of protecting our participants’ privacy. From this perspective, we begin the chapter with a presentation of spatial data formats that include: (a) raster or grid data files which represent units in space based on a matrix or grid, and (b) vector data format which stores and represents geographical features (or geometries) as points, lines, or polygons. As part of this presentation, we illustrate how to move from raster to vector data and vice versa, along with the implications of these transformations for SSEM. Subsequently, we introduce coordinate reference systems (CRSs) and discuss similarities and differences between projected (flattened) and unprojected (spherical) spatial data representations, once again while highlighting similarities, differences, and the implications of each CRS form for SSEM. Finally, we close this chapter with a discussion of Differential Privacy Frameworks implemented by the United States Census Bureau as a response to the conundrum of presenting as accurate counts of inhabitants as possible, while protecting the identity and privacy of the respondents. From this view, although differential protection was developed and implemented with the goal of protecting participants’ place-based anonymities based on their personal attributes, this framework may pose challenges with respect to modeling accuracy. Our presentation will discuss the implications of these data protections for SSEM and will also illustrate instances where the preservation of accurate spatial mapping and analyses is paramount.
Url: https://link.springer.com/chapter/10.1007/978-3-031-24857-3_3
User Submitted?: No
Authors: González Canché, Manuel S.
Editors:
Pages: 55-94
Volume Title: Spatial Socio-econometric Modeling (SSEM)
Publisher: Springer, Cham
Publisher Location:
Volume:
Edition:
Data Collections: IPUMS USA
Topics: Methodology and Data Collection, Population Mobility and Spatial Demography
Countries: