3101.0 - Australian Demographic Statistics, Sep 2006  
ARCHIVED ISSUE Released at 11:30 AM (CANBERRA TIME) 22/03/2007   
   Page tools: Print Print Page Print all pages in this productPrint All

FEATURE ARTICLE: REBASING AUSTRALIA'S POPULATION ESTIMATES USING THE 2006 CENSUS OF POPULATION AND HOUSING


WHAT IS REBASING?

Rebasing refers to the process by which the Australian Bureau of Statistics (ABS) uses the most recent Census results to revise all estimates back to 30 June in the year of the previous Census. Rebasing ensures that the ERP time series for the previous intercensal period are comparable with the latest estimates. Rebasing is applied to the population estimates for national, states/territories and Statistical Local Areas (SLAs) and Local Government Areas (LGAs).



THE REBASING PROCESS

After each Census, the ABS uses Census counts by place of usual residence to construct a new base population figure for 30 June of the Census year, from which to estimate quarterly ERP forward. Because this new population estimate uses the Census as its main data source, it is said to be 'based' on that Census and is referred to as a population base.


Constructing a new base figure

After obtaining population counts from the most recent Census, the ABS firstly adjusts this figure to show population counts by place of usual residence. This involves:

  • adding in those residents who were absent interstate on Census night; and
  • subtracting those who were visiting from interstate or overseas on Census night.

The ABS then uses these Census counts by place of usual residence to construct a new base figure for 30 June of the Census year. This involves:
  • adjusting for net undercount using the results from the Post Enumeration Survey (PES);
  • adding in the number of Australian residents who were temporarily overseas (RTOs) on Census night using data on international travellers obtained from the Department of Immigration and Citizenship;
  • applying a range of demographic adjustments designed to resolve any anomalies in the Census counts (adjusted for undercount and RTOs); and
  • back-dating this figure from Census night to 30 June of that year.


REBASED ERP

During the rebasing process, the most recent 20 quarterly estimates (i.e. September of the previous Census year (September 2001) to June of the most recent Census year (June 2006)) become what is referred to as final estimates. This means that no subsequent revisions will be made to these estimates. However, for 2006 Census rebased estimates, there are two releases of data - 'preliminary rebased' estimates with national and state/territory estimates being available in June 2007, and 'final rebased' estimates with national and state/territory estimates being available in June 2008. Preliminary rebased estimates for SLAs and LGAs will be compiled and released in July 2007 with final rebased estimates released in July/August 2008.



INTERCENSAL ERROR AND INTERCENSAL DISCREPANCY

The new Census allows the ABS to compare the latest Census based ERP with ERPs based on the previous Census which have been carried forward using data on births, deaths and migration. The difference between these two population figures as at 30 June in the latest Census year is referred to as the 'intercensal error'.


There are two areas that can contribute to the intercensal error:

  • errors in the Census based estimates of the population at the current or previous Census date; and/or
  • errors in the estimates of any of the components of population change since the previous Census.

Information collected in the Census allows an assessment of how much of the intercensal error will be due to inaccuracies in estimates of interstate migration, using data from the two Census questions on usual residence one year ago and five years ago.


After the intercensal error is adjusted for revisions to the components of population change (i.e. births, deaths and migration), the remaining (unattributable) portion is known as the intercensal discrepancy. Thus the intercensal discrepancy acts as a balancing item, that when combined with intercensal births, deaths and migration equals the difference between the two Census population estimates. Like intercensal error, intercensal discrepancy is caused by measurement errors in the start and/or finish population estimates and/or in estimates of births, deaths or migration in the intervening period which cannot be attributed to a particular source.



CHANGES FOR THE 2006 CYCLE

The methods used to rebase the population are described in Demographic Estimates and Projections: Concepts, Sources and Methods (cat. no. 3228.0). Further information on rebasing for the 2006 cycle is outlined below.


Expanding the scope of the PES

The PES has been undertaken in remote areas and discrete Indigenous communities for the first time. Previously, the PES did not go to such areas which meant that persons living in these areas and communities did not have a chance of selection in the survey. Rather it was assumed that undercount in these areas were represented by survey responses for the rest of each state and territory.


New method for RTOs

The move to a 12/16 method for Net Overseas Migration (NOM) means that residents temporarily overseas on Census night will be calculated using a consistent methodology. For further information on the improved NOM method see: Information Paper: Improved Methods for Estimating Net Overseas Migration, 2006 (cat. no. 3107.0.55.003).



PLANS FOR OUTPUT

Australian Demographic Statistics, December quarter 2006 (cat. no. 3101.0) to be released on 5 June 2007 will contain preliminary ERP for Australia, states and territories based on the results of the 2006 Census. Previously published estimates dating back to 30 September 2001 will be revised to take account of this new Census based population estimate for 30 June 2006. Final ERP for the quarters September 2001 to June 2006 will be published in Australian Demographic Statistics, December quarter 2007 (cat. no. 3101.0) to be released on 5 June 2008.


Preliminary rebased estimates for SLAs and LGAs will be published in late July 2007 in Regional Population Growth, Australia, 1996-2006 (cat. no. 3218.0) with final rebased estimates published in July/August 2008.


Preliminary rebased estimates of the Australian Aboriginal and Torres Strait Islander population at 30 June 2006 will be published in Population Distribution Aboriginal and Torres Strait Islander Australians, 2006 (cat. no. 4705.0) in August 2007. Final rebased estimates for 30 June 2006 will be published in July/August 2008.


An update of the Information Paper: Measuring Net Undercount in the 2006 Population Census (cat. no. 2940.0.55.001) will be released on 7 May 2007. The Information Paper: Census of Population and Housing, Data Quality - Undercount (cat. no. 2940.0) will be released on 5 June 2007.


Further updates on upcoming releases of rebased population estimates will be announced in future issues of the publication .


For further information please contact Phil Browning on 02 6252 6639.