A spatial obesity risk score for describing the obesogenic environment using kernel density estimation: development and parameter variation

Table 3 ANOVA F statistics for Augsburg and Meitingen

BC Base case, BW Bandwidth, EC Edge correction, GP Grid points, INT Interpolation, WT Weighting
^a bandwidth, edge correction, and number of grid points presented in ascending order, i.e., with the first scenario describing the least amount of bandwidth, edge correction, and number of grid points respectively
^b The F statistic refers to the ANOVA F statistic between the groups of estimated data points at the 50 evaluation points for a given area (1000 data points at each evaluation point), calculated as follows: F = between-group variability/within-group variability; higher values of the F statistic reflect more preferable parameter values for a given scenario. The groups are generated based on the POI bootstrap replications

ISSN: 1471-2288