In an h-Scattergram each head value zi is plotted against each tail value zj that is used to compute g(h). The formula to calculate the difference for any given pair of points at locations i and j is
h-Scattergram analysis is closely related to variance cloud analysis. Both analyses present pair-by-pair information on variances within lag classes arranged by separation distances.
Note that an h-Scattergram is specific to both direction (isotropic or a specific anisotropic direction) and to a particular lag class. In the variogram below, the cursor is on the point representing lag class 7 of the isotropic variogram, which one might suspect contains an outlier because it is so different from the other points:
Clicking on this variogram point brings up the h-Scattergram for lag class 7 below, and it becomes apparent that a number of pairs are very different from the others – placing the cursor over each point reveals that all of the points farthest from the 45-degree line contain record 4 as a member of the pair (the cursor below is over the point represented by records 4 and 92 with a separation distance of 52.28):
Clicking on this h-Scattergram point brings up the Sample Details window, which gives us the option to temporarily mask one of the data records that make up this pair:
Since record 4 is a member of all of these outlier pairs, we choose to mask record 4, which gives us a much more reasonable variogram:
Re-examination of the h-scattergram for lag class 7 reveals that the greatest differences between head and tail values of individual pairs are substantially lower than before (0.8 vs. 2.8) and, more importantly, all of the major outlier pairs are gone. This was accomplished by removing a single data record from the analysis:
The variogram lag class for which the variance cloud is created. The variance for every pair of points in the lag class is plotted against the distance interval separating that pair.
The right-click menu and other commands work here as they do for the Variograms Window.