|Page tools: Print Page Print All RSS Search this Product|
3.11 The regression models use an area's share of indicator data to estimate the share of the state or territory's population for that area. More correctly, the change in share of state/territory of the indicator data is used to estimate the change in share of state/territory population since the base year.
3.12 All population and indicator data need to be on the same boundaries, therefore adjustments are made to indicator data to account for changes to SLA boundaries over the regression or estimation periods.
3.13 The choice of indicators varies across the states and territories, depending on availability and indicative ability. The predominant indicator data sources currently used are dwelling approvals, Medicare enrolments and Electoral enrolments.
3.14 Dwelling approvals data are collected on an ongoing basis by the ABS, with summaries released frequently. Dwelling counts from the latest Census are used as the base number of dwellings by SLA. Updated estimates of dwellings are prepared by adding approvals to the Census base. Under the assumption that it takes several months for the dwelling to be constructed and people to move in after it has been approved, lags are incorporated into the approvals data - dwellings approved six to twelve months before the estimation reference period are incorporated in the regression models, with provision made for some longer lags, in particular for large approval jobs.
3.15 Medicare enrolments, by postcode, are provided to the ABS by Medicare Australia. Changes to the number of Medicare enrolments provide an indication of total population change, which can be incorporated into the regression models used to estimating population change. Under the assumption that it takes a few months for a person to change their address on the Medicare system, a lag is incorporated into the Medicare data used in the regression model. Because Medicare data are only available by postcode, it is converted to SLA using a postcode to SLA concordance. The quality of the Medicare data is therefore highly dependent on the quality of the postcode to SLA concordance. One issue with creating this concordance, is determining which SLA to concord unmappable postcodes with.
3.16 Counts of people on the Commonwealth electoral roll, are provided to the ABS by the AEC. These data are provided by Census collection district (CD), which are then aggregated to SLA. Under the assumption that it could take a few months for a person to change their address on the electoral roll, a lag is incorporated into the Australian Electoral Commission (AEC) data used in the regression model. One potential concern here, which needs to be accounted for when using AEC data for population estimation, is the annual variability of the size of the electoral roll, especially around election time when rolls tend to be updated more than at other times.
3.17 In areas where indicator data are unreliable and migration can be assumed to be insignificant, population change since the previous Census may be estimated by adding estimates of natural increase (births minus deaths) since the previous Census. In some very small areas population change since the previous Census may be assumed to be zero in the absence of any reliable indicator data for these areas.
3.18 All estimates are scrutinised and validated by population analysts. Local knowledge, including that advised by local governments, may be used to adjust the figures for particular SLAs.
3.19 All estimates at SLA level are constrained to sum to state/territory level population estimates.
Disaggregation of post-censal SLA population totals by age and sex
3.20 Post-censal estimates of the age and sex distributions of SLA populations are made by updating the population by age and sex for the Census year using annual births (by sex), deaths (by age and sex) and derived age and sex profiles of migration. SLA estimates by age and sex are released by five year age groups (0-4, 5-9, ... 80-84, and 85 and over), and are also available by single year of age (0,1,... 84, 85+).
3.21 While annual data on births and deaths by age and sex are available for each SLA, data on migration into and out of SLAs for post-censal years are not available and are derived indirectly. This is done as follows:
3.22 The estimate of total population growth for each SLA (see above) for the twelve months is split into natural increase and net migration components. Natural increase is derived for each SLA from birth and death registration statistics. Net migration is derived for each SLA as the difference between total population growth and natural increase. Net migration is then split into internal and overseas migration components. This is done by apportioning according to the relative contributions based on one-year migration data from the most recent Census, in conjunction with state/territory level estimates of interstate migration and overseas migration.
3.23 The SLA age/sex profiles of internal migration are derived from Census data on the SLA of usual residence one year ago. These profiles are produced for:
3.24 The SLA age/sex arrival and departure profiles are then constrained so that, for each age and sex, the net effect across all SLAs in a state/territory equals the finalised interstate migration estimate for the financial year prior to the Census.
3.25 The age/sex profile of overseas arrivals for a SLA is derived from Census counts for that SLA of people whose usual residence one year ago was overseas. The overseas departure profile for each SLA is assumed to be the same as the overseas arrival profile (in the absence of data on overseas departures at the SLA level from either the Census or outgoing passenger cards). For overseas arrivals, the total of all SLAs within a state/territory is constrained to sum to the age/sex profile of permanent and long-term arrivals for the financial year prior to the Census for the state/territory. For overseas departures, the total of all SLAs within a state/territory is constrained to sum to the age/sex profile of permanent and long-term departures for the financial year prior to the Census for the state/territory. Migration for those aged zero is assumed to be half that of one year olds.
3.26 For greater detail, see Appendix 3 - Estimating migration for SLAs.
3.27 Having established estimates of the migration component, the Census date population estimates for each SLA by age and sex are then updated in the normal way, (i.e. after converting to financial year of birth - by adding births, subtracting deaths and adding net migration). A more detailed account of this procedure at the national and state/territory level is given in Chapter 2 - Estimating national and state population.