1352.0.55.108 - Research Paper: Sample Design Frameworks for ABS Household Surveys (Methodology Advisory Committee), Jun 2010  
ARCHIVED ISSUE Released at 11:30 AM (CANBERRA TIME) 23/11/2010  First Issue
   Page tools: Print Print Page Print all pages in this productPrint All
  • About this Release

For many years the sampling framework used for ABS household surveys has been based around a single master sample of geographic areas selected after the five-yearly Population Census. The areas in the master sample are divided into finer blocks, with one block providing sample for the Monthly Population Survey (MPS), and a 'parallel' block used for a diverse range of large-scale social surveys, collectively referred to as Special Social Surveys (SSSs). Although the sample design parameters for the master sample have been tailored to the key MPS objectives, there is sufficient flexibility in parallel block sample designs that nearly all SSSs have used the parallel blocks. Growing demand for SSSs to meet a more diverse range of objectives may mean that there will be more surveys for which the parallel block will be less suitable. In addition, changes to the ABS geography standard and new methods and systems for sample preparation and maintenance reduce the cost advantage of tightly coupled samples for the MPS and SSSs. Considering these changes, alternative frameworks may be clearly superior for the future SSS program. This paper compares some alternative sampling frameworks for ABS household surveys, describing key sample design issues which need to be considered.