This paper discusses the use of suppression to protect data in the Special Migration Statistics, a dataset produced from the 1991 Census, and argues that this procedure prevents accurate analysis of the data. A computer program is described that uses a series of methods to "recover' data which were suppressed, and to estimate those parts of the data which cannot be recovered. A process termed logical data patching is used to recover data, while a technique termed integer fitting is introduced to estimate the remaining suppressed parts of the dataset. The latter process uses a familiar iterative proportional fitting procedure, coupled with an innovative three-way controlled rounding procedure in order to generate integer-only tables which are consistent with all available totals. The program has been used to recover and estimate data successfully, and results include sample tables of migrants between types of districts by ethnicity.
No takes yet. Share an insight, caveat, or question.
Rees et al. (1997) studied this question.