Estimates of Aboriginal and Torres Strait Islander Australians methodology

This publication contains preliminary estimates of the Aboriginal and Torres Strait Islander, non-Indigenous and total populations of Australia at 30 June 2021, based on results of the 2021 Census of Population and Housing.

Australia’s preliminary estimates of the Aboriginal and Torres Strait Islander, non-Indigenous and total populations includes all usual residents in Australia (regardless of nationality, citizenship, or visa status), except for people present for foreign military, consular or diplomatic reasons.

These data cover Australia and its states and territories, as defined by the Australian Statistical Geography Standard, Edition 3.

The category, ‘Other Territories’ is included in the Australia total, and includes Christmas Island, the Cocos (Keeling) Islands, Jervis Bay Territory and Norfolk Island.

Preliminary estimates of Aboriginal and Torres Strait islander population are based on the Census, Post Enumeration Survey (PES) and other demographic information. Further information on each component can be found in the Technical note – Methodology used in preliminary Aboriginal and Torres Strait Islander population estimates, below.

The preliminary estimate of the Aboriginal and Torres Strait Islander population at 30 June 2021 was 984,000 people. This estimate comprises 812,500 people counted on Census night, plus the 170,800 people measured as net undercount and the inclusion of an additional adjustment of 500 people. This technical note outlines the method used to compile the preliminary 2021 rebased estimate of the Aboriginal and Torres Strait islander population.

The preliminary Aboriginal and Torres Strait Islander population estimate is based on the 2021 Census of Population and Housing and is calculated using a similar process to that used for the total Australian population.

We calculate the preliminary rebased Australian population estimate at 30 June in a Census year by:

1. Adjusting Census counts of Australian usual residents to account for people missed, counted more than once, or counted in error in the Census (based on PES results)
2. Demographically adjusting Census counts or net undercount estimates based on coherence with other data sources and to remove implausible demographic features
3. Adding usual residents temporarily overseas on Census night
4. Adjusting for births, deaths and migration from 30 June to Census night.

The steps are illustrated in the following diagram. For further information, refer to Methodology used in rebased population estimates, June 2021.

Additional steps are taken when calculating the Aboriginal and Torres Strait Islander population, including smoothing of net undercount estimates and demographic treatment for age heaping for the Northern Territory. These are described in more detail in later sections of this technical note.

The ABS used the results of the 2021 Census as the main data source to produce the rebased population estimates for Aboriginal and Torres Strait islander Australians. The Census counted 812,500 Aboriginal and Torres Strait Islander people in Australia (excluding Other Territories) on Census night.

Asking a person’s Indigenous status may be considered personal and sensitive. As a result, some people choose not to answer this question in the Census. If no answer is provided to the question, the Census does not impute a value for the missing response. This is also true where person records are imputed for dwellings (either private or non-private) that were deemed occupied on Census night but for which no Census form was received. In the 2021 Census;

• there were 1,233,500 records (4.9% of the total Census count) where Indigenous status was not stated
• of these, 12.2% (or 0.6% of the total Census count) were set to not stated because the Indigenous status question was blank on returned Census forms
• the remaining, and majority (87.8%) of, records had a not stated Indigenous status because they were wholly imputed records for non-responding dwellings deemed occupied on Census night.

The Census Post Enumeration Survey (PES) is run shortly after each Census to independently measure Census coverage.

The 2021 PES included people from approximately 45,100 fully responding households across Australia. Information was collected for everyone present in the household. This included basic demographic information, the address where each person was on Census night, and any other addresses where each person may have been included on a Census form.

Results from the survey were used to determine the number of people who were counted in the Census and the number of people who should have been counted in the Census. The difference is referred to as net undercount.

Net undercount is used as one of the inputs for compiling the Aboriginal and Torres Strait Islander population estimates. In the PES, Indigenous status is collected from every person (i.e., there is no non-response). The PES is therefore able to estimate the net undercount of the Aboriginal and Torres Strait Islander population.

The not stated responses for Indigenous status in the Census drive the higher net undercount we see for Aboriginal and Torres Strait Islander population. This is because we don’t know the Indigenous status for these people (and don’t impute it).  Net undercount can only be calculated for known Indigenous status.

In the 2021 Census, the net undercount of the Aboriginal and Torres Strait Islander population was 170,800 people. This equates to a net undercount rate of 17.4%, which is similar to the rate for the 2016 Census (17.5%). This net undercount number is derived by calculating the difference between the PES Aboriginal and Torres Strait Islander population estimate (983,300) and the Aboriginal and Torres Strait Islander population Census count (812,500).

Some state and territory estimates of net undercount for the Aboriginal and Torres Strait Islander population have relatively high standard errors and therefore the raw PES estimates are not used in calculating the preliminary Aboriginal and Torres Strait Islander population estimates below the national level. Instead, the Empirical Bayes method (as used in 2016) is used to produce smoothed net undercount rates for 18 regions of Australia. Each of these regions was a customised geographic area designed to capture the varied collection issues in different parts of Australia, as an input into the Empirical Bayesian estimation method. Victoria, Tasmania, South Australia, and the Northern Territory were separated into two regions (split between capital city and balance of state), while New South Wales, Queensland and Western Australia were separated into three regions (with the balance of state split). The Australian Capital Territory was treated as a single region.

This method smooths the raw PES estimate of the net undercount based on the Census characteristics of the region (specifically the proportion of Aboriginal and Torres Strait Islander persons and the level of Census non-response in the region and the Census enumeration strategy).

The aim of smoothing is to provide stable estimates with lower standard errors. The overall amount of smoothing used in each region was determined by two factors: the standard error for each region and an overall smoothing constant.

Maximum likelihood estimation was chosen to calculate the smoothing constant. Maximum Likelihood is the preferred approach in contemporary literature and external application, and is considered more robust than Method of Moments. The Method of Moments was initially implemented in 2006 (and used in 2011 and 2016), and was based on statistical literature dating from the early 80’s.

The difference between Method of Moments and Maximum Likelihood is relatively small with respect to the large standard errors. Therefore, changing the estimation method to Maximum Likelihood is unlikely to make a statistically significant change to the estimates.

Regions with high standard errors required more smoothing. The outcome of this methodology, in relation to smaller standard errors and confidence intervals is presented in the table and the graph below.

Estimates of the Aboriginal and Torres Strait Islander population on Census night, which have been adjusted for net undercount (as noted above) were then further adjusted to compile population estimates at 30 June. This involved adding back Australians temporarily overseas at the time of the Census, and backdating to the 30 June using data on births, deaths and interstate and overseas migration, which occurred between the two dates. Minor demographic adjustments were then made to address anomalies in age and sex composition. All these additional adjustments added in 500 people at the national level.

When respondents are unsure of their age or the age of others they are reporting on behalf of, they may round their ages to those ending in 0 or 5. This produces systematic spikes for ages ending in 0 or 5, a phenomenon known as age heaping.

Age heaping is a relatively common demographic issue in developing countries and is generally not observed in the total Australian population, except in the Northern Territory, where it is evident in Census counts and population estimates for the Aboriginal and Torres Strait Islander population.

While we have not traditionally applied an adjustment for age heaping, the increasing demand for data by single year of age for key reporting purposes has necessitated a demographic treatment to ensure the best possible estimates are produced by age for the Northern Territory’s Aboriginal and Torres Strait Islander population.

The preliminary estimates of the Aboriginal and Torres Strait Islander population for the Northern Territory released in this publication are adjusted for age heaping using the Sprague method. For further information, please see Technical Note 2 in Estimates of Aboriginal and Torres Strait Islander Australians, June 2011.

Final resident population estimates by Indigenous status will be available in August 2023 in the publication Estimates of Aboriginal and Torres Strait Islander Australians. For more information regarding estimates of Aboriginal and Torres Strait Islander population please e-mail demography@abs.gov.au.