2006 Census: Census Data Enhancement
 

The ABS is undertaking a new project called Census Data Enhancement. The primary objective of this project is to enhance the value of the Census by combining it with future censuses and other datasets held by the ABS. This project aims to increase the amount of relevant information available about Australian society to support decision making. This project has three main features:

  • the Statistical Longitudinal Census Dataset;
  • use of the Statistical Longitudinal Census dataset with specified non-ABS datasets; and
  • quality studies.

These main features are explained below in more detail.


Statistical Longitudinal Census Dataset


The central feature of this project is the creation of a Statistical Longitudinal Census Dataset (SLCD). The SLCD will be:

  • created by combining data from the 2006 Census with data from future censuses;
  • created by bringing together the data through statistical techniques rather than matching based on name and address; and
  • based on a 5% random sample of the population.

Patterns in individual experiences over time and factors that might influence these experiences, would be those where the SLCD would provide most insight. Examples include studies of the impact of parents' education and labour force participation on their children's subsequent participation, and the impact of factors such as family structures and household income on these outcomes.

The value of the SLCD will grow as data are brought together from future censuses. The SLCD by its nature is an investment in the future, and its value will be in answering research questions of the future.


Use of the Statistical Longitudinal Census Dataset with Specified Non-ABS Datasets


The SLCD will be used further by bringing it together with specified non-ABS datasets using statistical techniques. The
Census Data Enhancement - Statement of Intention indicated that the use of the 5% SLCD with specified non-ABS datasets will proceed for particular datasets, only with the agreement of the custodians of the non-ABS datasets and only for statistical purposes. The specified non-ABS datasets are:
  • birth and death register data, including cause of death data;
  • Department of Immigration and Citizenship Settlement database (containing information about long-term migrants); and
  • national disease registers.

All statistical studies will be contingent on the quality studies described below. The outcomes of the quality studies will indicate if valid statistical analyses can be performed, and the types of statistical study for which the SLCD in combination with the above datasets, is most useful.


Quality Studies


During the period of Census processing, name and address information will be used to bring together Census data and other specified datasets (listed in the Census Data Enhancement Project: An Update) for ABS quality studies. Once Census processing is completed, all name and address information collected in the Census of Population and Housing is destroyed. These quality studies will allow the ABS to make improvements to the current collections, for example expected outcomes of the Indigenous mortality quality study include: gaining an understanding of differences in Indigenous status recording between death registration and census data; identifying factors contributing to undercoverage of Indigenous deaths; and investigating the feasibility of calculating and applying adjustment factors for Indigenous deaths output data.

Findings from Census Data Enhancement - Quality Studies

The following papers include findings from quality studies undertaken as part of the Census Data Enhancement project:


Australian Labour Market Statistics: Underenumeration in the Labour Force Survey (cat no. 6105.0, pp. 22-27) - released 07/2008

Discussion Paper: Assessment of Methods for Developing Life Tables for Aboriginal and Torres Strait Islander Australians, 2006 (cat. no. 3302.0.55.002) - released 11/2008

Generalised Linear Models with Probabilistically linked data: Application to the Simulated Statistical Longitudinal Census Dataset (cat. no. 1352.0.55.098) - released 02/2009

Information paper: Census Data Enhancement - Indigenous Mortality Quality Study, 2006 - 07 (cat. no. 4723.0) - released 11/2008

Research paper: Methodology of Evaluating the Quality of Probabilistic Linking (cat. no. 1351.0.55.018) - released 04/2007


Privacy


The confidentiality of data will be fully protected by the secrecy provisions of the Census and Statistics Act and the secure environment the ABS maintains to ensure public trust. Further detail is available through the following links:


Census Data Enhancement Project: An Update (cat. no. 2062.0).
Frequently Asked Questions


Background to the Project


For more information including the Privacy Impact Assessment, the ABS response to the Privacy Impact Assessment and public submissions see
Census of Population and Housing - Enhancing the Population Census - Privacy Impact Assessment and Public Submissions. The original proposal is available as a Discussion Paper Enhancing the Population Census: Developing a Longitudinal View (cat. no. 2060.0)