Spatial Thinking in Planning Practice: An Introduction to GIS

52 Figure 9.7 Viewshed Analysis depicting the areas within a park where a proposed radio antenna can be seen. Map courtesy of the National Park Service, Department of Interior, 2007. Source: GIS Commons. http://gis- commons.org/analysis/ CORRELATION AND REGRESSION Correlation and Regression are two ways to compute the degree of association between two (or sometimes more) layers. With correlation, you do not assume a causal relationship. In other words, one layer is not a#ecting the spatial pattern of the other layer. "e patterns may be similar, but no cause and e#ect is implied. Regression is di#erent; you make the assumption that one layer (and its variable) in'uences the other. You specify an inde- pendent variable layer (sometimes more than one) that a#ects the dependent variable layer (Figure 9.9). Chapter 9: Raster Data Models