1352.0.55.032 - Research Paper: Data Editing Design Principles in a CAI Environment (Methodology Advisory Committee), Jul 1999  
ARCHIVED ISSUE Released at 11:30 AM (CANBERRA TIME) 01/11/2000  First Issue
   Page tools: Print Print Page Print all pages in this productPrint All
  • About this Release

About this Release

Statistical data editing is redefined as one element of a total quality control strategy for CAI surveys, aimed primarily at preventing non-sampling error, with error mitigation playing an important but subordinate role. Prevention of non-sampling errors is achieved by improving survey processes. This relies on the collection and analysis of data relating to editing performance and to the sources, types and distribution of errors in the data. This type of information should also be used to assess data quality and to provide users with information that can assist them to understand the limitations of the data. In relation to error mitigation, this paper emphasises the need for the systematic and orderly specification of edits and that the amendment of data should occur only in response to important errors. A balance must be achieved between edits applied in the field and those applied in the office, between automated and clerical approaches to verification and amendment of errors, and also between the use of micro and macro-editing methods.