First page Back Continue Last page Overview Graphics

2001 Census interaction data issues: Adjustment for Disclosure Control


Notes:

Various methods of adjustment for disclosure control were used by ONS with the results of the 2001 Census. The methods are known as ‘pre-tabulation’ and ‘post-tabulation’ adjustments.

Pre-tabulation modifications that come from edit and imputation involving, for example, record level imputation for a single person or household and item imputation for an individual field/variable. One of the most important imputations for the migration and commuting counts was the imputation of migrants whose origin was missing/unstated and of commuters with unstated workplace. Some of these counts can be quite substantial in number. Thus there are no separate counts of these in 2001 as there were in 1991 and no way of distinguishing these in the 2001 SMS/SWS .

One number census adjustments are also pre-tabulation

Thresholding and record swapping also occur pre-tabulation, i.e. before the SMS and SWS are generated,

SCAM (Small Cell Adjustment Method), however, is applied post-tabulation to every SMS/ SWS table (excluding flows with migration destinations and commuting origins in Scotland)