“…Nevertheless, because they lack a coherent theme of region, spatial and temporal scales, or even etiology, and are unrepresentative and not exhaustive of disease types (contents) and locality (space), analysis of these specimen data sets falls under the heading of exploratory, with subsequent additional such studies needed to establish a firm global epidemiology or public health assessment claim. Griffith (2006b) illustratively documents a rather long tradition recognizing why PSA is relevant to assessments of diseases and their diffusion in his spatial statistical analysis of the original John Snow cholera data; publications by Koch (2017Koch ( , 2022, among others, bolsters this viewpoint. Not only is PSA conspicuous in the geographic distribution of cholera deaths (e.g., a Moran Coefficient [MC] index of 0.88 [close to its maximum of 1.01, and far from its randomness value of −0.01], and a Geary ratio [GR] index of 0.25 [close to its minimum of 0.03, and far from its randomness value of one]), for example, but it also accounts for roughly 60% or more of the geographic variation exhibited by a Poisson/negative binomial (NB) probability model description of Snow's density of death counts data, based on Moran eigenvector spatial filtering (MESF 1 ; see Griffith et al, 2019) methodology.…”