1351.0.55.037 - Research Paper: Education Performance Indicators and the Census: Accounting for 'Not Stated' Records, Dec 2011  
ARCHIVED ISSUE Released at 11:30 AM (CANBERRA TIME) 20/12/2011  First Issue
   Page tools: Print Print Page Print all pages in this productPrint All
  • About this Release

When calculating educational attainment indicators for national reporting purposes, decisions need to be made on how best to deal with those people for whom information on educational qualifications is not available, i.e. ‘Not stated’. This paper reviews the characteristics of people with ‘Stated’ and ‘Not stated’ levels of attainment by comparing 2006 Census data with corresponding survey data at the national and jurisdiction level, with a focus on the Aboriginal and Torres Strait Islander population. The impact of including and excluding the ‘Not stated’ records in the calculation of education indicators is examined, together with a third approach which explicitly examines the two components of the Census ‘Not stated’ group: imputed records and item non-responses. The paper concludes that, although there are some differences between the ‘Stated’ and ‘Not stated’ groups, it is nonetheless reasonable to claim that, overall and on average, they have similar characteristics. Consequently the paper proposes the continuation of the practical and transparent method of excluding ‘Not stated’ records in the calculation of the education indicators.