Additivity is the property of a set of summary statistics which respect the arithmetic relationships implicit in their construction. The standard example is in tables of counts where row and column totals should equal the sum of the cells in those rows and columns.
Some perturbative disclosure control methods such as random rounding may give results that are non-additive. Non-additivity may be seen as problematic by users; it may also reveal information about the pre-disclosure-controlled data, as the plausible real values may be constrained by the intersection of non-additive values.
Further reading:
See also: PERTURBATION, TABULAR DATA
Shlomo, N., 2007. Statistical disclosure control methods for census frequency tables. International Statistical Review, 75(2), 199–217, https://doi.org/10.1111/j.1751-5823.2007.00010.x.
-
Shlomo, N., 2007. Statistical disclosure control methods for census frequency tables. International Statistical Review, 75(2), 199–217, https://doi.org/10.1111/j.1751-5823.2007.00010.x.
