In the first five sections of this chapter, we provide separate motivations for regression models that include spatial autoregressive processes. These motivations are explored in more detail in later chapters of the text, with the presentation here being less formal. Section 2.1 shows how cross-sectional model relations involving spatial lags of the dependent variable (the SAR model) come from economic agents considering past period behavior of neighboring agents. Section 2.2 provides a second situation where omitted variables that exhibit spatial dependence lead to a model that includes spatial lags of both the dependent as well as independent variables. Sections 2.3 to 2.5 provide additional motivations based on spatial heterogeneity, externalities, and model uncertainty. Taken together, the motivations in Sections 2.1 to 2.5 show how a host of alternative spatial regression structures arise when dependence enters into a combination of the explanatory variables, dependent variables, or disturbances.