Statistical disclosure limitation in the presence of edit rules

We compare two general strategies for performing statistical disclosure limitation (SDL) for continuous micro data subject to edit rules. In the first, existing SDL methods are applied, and any constraint-violating values they produce are replaced using a constraint-preserving imputation procedure. In the second, the SDL methods are modified to prevent them from generating violations. We present a simulation study, based on data from the Colombian Annual Manufacturing Survey, that evaluates the performance of the two strategies as applied to several SDL methods. The results suggest that differences in risk-utility profiles across SDL methods dwarf differences between the two general strategies. Among the SDL strategies, variants of micro aggregation and partially synthetic data offer the most attractive risk-utility profiles.

Duke Scholars

Author Jerome P. Reiter Statistical Science