ABSTRACT
As a data scientist, there is always a need to uncover and understand complex relationships among variables. Although traditional statistical books offer a variety of techniques for this purpose, special consideration is required to account for variables that have a spatial dimension. Specifically, statistical measures that are used to establish the strength, direction, and significance of observed relationships between variables offer an objective assessment of these associations, but they can become even better when the element of spatiality is included. The measures that are typically used to infer about statistical relationships are drawn from correlation and regression analyses. In this chapter, we explore these approaches, observe the underlying assumptions behind each technique, and work through a few examples to illustrate the applications.
