Spatial Econometrics in an Age of CyberGIScience

• Activity Number: 212
• Type: Invited
• Date/Time: Monday, July 30, 2012 : 2:00 PM to 3:50 PM
• Sponsor: Business and Economic Statistics Section
• Author(s): Luc Anselin*+ and Sergio Rey
• Companies: Arizona State University and Arizona State University
• Keywords: cyberinfrastructure ; spatial econometrics ; spatial statistics ; spatial analysis ; open source software

Abstract

We focus on the evolution of the technology behind implementing spatial econometric methods into software tools. We review the changing methodological emphases and their implications for data structures and computational infrastructure required for estimation and inference. We review the evolution of software solutions, starting with SpaceStat and GeoDa and moving on to the PySAL open source library of spatial analytical functions (Rey and Anselin 2010). We also compare these approaches to other software solutions. We follow the review with a discussion of requirements and challenges encountered when moving these software tools into a CyberGIScience framework. We discuss efficient data structures, the need for metadata and provenance tracking, as well as high performance computing requirements. We illustrate this discussion with examples from the evolving parallel PySAL library and its implementation in HPC environments such as clusters, cloud computing and the Teragrid. We close with the outline of a vision for a "spatial econometrics workbench" as a core component of cyberinfrastructure for GIScience.