Abstract

Rapid advances in the availability of spatial data, new measures, and methods of analysis have generated interest in spatial analysis beyond the traditional academic boundaries of geography and statistics. This uptick in interest is in part driven by a recognition that many contemporary problems are multifaceted and inherently spatial. This entry begins with a focus on fundamental spatial concepts such as location, distance, scale, and dependence to introduce the complexities of working with spatial data. Spatial data are special, most notably that observations in spatial data sets are rarely random and independent of each other, and as such conventional statistical approaches may be inappropriate. Two broad classes of spatial effects—spatial dependence and nonstationarity—have motivated key developments in spatial analysis and the focus here is on methods that promote a better understanding of these effects, spatial econometric and geographically weighted regression models, respectively. Selected emerging methods and themes relating to spatial data and methods are briefly discussed.