Variable descriptions are presented in Tables 1 and 2, and construction of variables is described in the Methods section, below. Spatial regression methods and the rationale for using the spatial spillovers model are presented in the Methods section, below, with a discussion of what spatial spillovers are and why they might manifest themselves and cause problems in regression. Regression results are presented in Table 4, where both heteroskedasticity-consistent OLS and spatial lag regression models are presented. Table 3 presents sample statistics, including the mean, median, standard deviation, minimum, and maximum for each variable. Variable descriptions (Tables 1 and 2) reveal that there are many different units of measurement in the analysis – rates.
