is given to samples within a distance band, while the weight of zero is
given to those outside the distance band (Zhang et al., 2008).
The results of local Moran's I index can be standardized, so its significance
level can be tested. When using local Moran's I index to analyze
in Geoda software the results were affected by the definition of weight
function, data transformation and existence of extremevalues (Zhang et
al., 2008). Its values are from −1 to 1.When I N 0 indicates positive spatial
autocorrelation, while I b 0 suggests negative spatial autocorrelation.
When there is positive local spatial autocorrelation, LISA has two
kinds of spatial clusters: high-high cluster (high values in a high value
neighborhood) and low-low clusters (low values in a low value neighborhood).
Meanwhile, a high negative local Moran's I value implies a
potential spatial outlier, which may be high-low (a high value in a low
value neighborhood) or low-high (a low value in a high value neighborhood)
outlier (Lalor and Zhang, 2001; Fu et al., 2016).