Proximity and Areal Data
Content for Wednesday, October 25, 2023
Last class we started to explore ways to leverage spatial autocorrelation as a means of using interpolation to generate values at unobserved locations. We’ll continue that discussion using variograms and kriging. We then move to a discussion of areal data and the need to identify “neighbors” as a means of understanding how to weight observations when the actual point location of the observation may be unknown or impossible to assign.
Resources
Ch. 7: Spatial Neighborhood Matrices in from Paula Moraga’s new book Spatial Statistics for Data Science: Theory and Practice with
Rgives a little gentler introduction to spatial neighbors specifically in the context of statistical models.Chapter 14 Proximity and Areal Data in Spatial Data Science by Edzer Pebesma and Roger Bivand provides explanations of how the
spdeppackage can be used to construct neighborhood weights.
Objectives
By the end of today you should be able to:
Describe and implement statistical approaches to interpolation
Describe the case for identifying neighbors with areal data
Implement contiguity-based neighborhood detection approaches
Implement graph-based neighborhood detection approaches