Summary
The experience of NSIs in the field of correction of errors has led to assume that only a small subset of observations is affected by influential errors, i.e., errors with a high impact on the estimates, while the rest of the observations are not contaminated or contain errors having small impact on the estimates. Selective editing is a general approach to the detection of errors, and it is based on the idea of looking for important errors in order to focus the treatment on the corresponding subset of units to reduce the cost of the editing phase, while maintaining the desired level of quality of estimates. In this section a general description of the framework and the main elements of selective editing is given.
To read the entire document, please access the pdf file (link under "Related Documents" on the right-hand-side of this page).
Your feedback is appreciated. Please send your remarks, suggestions for improvement, etc. to memobust@cbs.nl.