Income statistics provide policy makers and economic analysts with insights into a range of issues such as poverty, housing affordability, cost-of-living impacts, and the effects of taxes and government transfers on the population. Such insights are crucial for identifying where intervention may be needed and informing decisions that impact the economic wellbeing of all Australians.

The ABS Standard for Income Variables is used when preparing income statistics to help ensure that they are produced in a consistent and comparable manner. 

The conceptual definition used in the ABS standard is based on the one set out by the International Conference of Labour Statisticians and further explained in the Canberra Group Handbook on Household Income Statistics. It states that:

“Household income consists of all current receipts, whether monetary or in kind, that are received by the household or by individual members of the household, which are available for, or intended to support, current consumption by the household”.

The household unit is important to consider when analysing economic wellbeing. The ABS concept of a household defines it as one or more persons, at least one of whom is at least 15 years of age, usually resident in the same private dwelling.

While income is typically obtained at the individual level, it is often analysed at the household unit. This is because it is assumed that income is shared within a household to support consumption needs such as rent or mortgage payments and utility bills etc. 

The income standard defines six types of income. Together these determine total (gross) income. Each type is summarised below.

Income can be measured in different ways depending on the purpose it is used for. Two common measures of income produced by ABS are:

• ‘Annual income’ is the income from all types received over the period of a year. Often this relates to a financial year (July 1 to June 30).
• ‘Current income’ is the income that is available at a specific time point and aligns with the individual and household characteristics provided at this time. 

Compared to annual income, current income aligns more closely with the ABS conceptual definition of income. Analysing current income alongside other point-in-time circumstances is usually most appropriate for understanding the financial wellbeing of individuals or households. Current income may also be more appropriate for analysing groups with changing circumstances, income, or expenditure patterns throughout the year (e.g., new parents, first home buyers, seasonal workers, recently retired individuals).

Annual income statistics may be output as an annual amount or converted to a weekly amount. Current income is typically output as weekly or monthly amounts.

The admin data sources used for calculating admin income are presented below. Relevant aspects of data quality are discussed for each source. 

The Person Level Integrated Data Asset (PLIDA) is a secure data asset combining information on health, education, government payments, income and taxation, employment, and population demographics (including the Census and some ABS surveys) over time. 

Admin incomes are calculated using the PLIDA Modular Product, which consists of subsets of data (modules) that are supplied by data custodians, structured for analysis purposes. Further detail about the Modular Product’s datasets and modules can be found in the Data Item List.

The ABS is trusted as the accredited integrating authority for PLIDA. Linkage of datasets is performed using the Person Linkage Spine (Spine) which is separate from the main body of analytical data. Each spine entry is represented by a unique identifier, a ‘spine ID’, on which each person on PLIDA analysis files seeks a linkage to. The linkage of each analysis file via a common spine ID allows multiple datasets to be brought together for individuals.

PLIDA is overseen by a PLIDA Board. Access to PLIDA is provided to approved researchers working on approved projects. The PLIDA homepage provides more information on PLIDA and how it operates, including how it meets privacy and legislative requirements.

The following datasets are available in the PLIDA Modular Product and contain the income data used to calculate admin incomes.

The DOMINO database is a comprehensive, longitudinal resource developed by the Department of Social Services (DSS) to support research into the population’s interactions with government payments administered by Centrelink. It captures detailed information on: 

• Government pensions and allowances income.
• Income changes (to wages and other sources of non-government income) for recipients of Australian pensions and allowances. 

It also includes limited information about payments administered by the Department of Veterans’ Affairs. The DOMINO extract used includes data from 2000 onwards. 

Access to DOMINO data is strictly controlled and granted only to approved research projects through the Public Interest Certificate process. Access is available via PLIDA, where DSS ensures the provision of relevant and up-to-date metadata to support clarity around the features of data items. Metadata associated with the data is also maintained within the DOMINO metadata repository. DOMINO maintains a high level of consistency and comparability over time, although some changes to individual payment structures may occur. 

The data is typically made available six weeks after the end of each quarter.

Access to the tax data sources listed below is governed by a legislated arrangement under Section 355-65 of the Taxation Administration Act 1953. This authorises the ATO to share identifiable information with the ABS for the sole purpose of administering the Census and Statistics Act 1905. The ABS as an integrating authority is permitted to access and use this data for statistical and research purposes. This arrangement ensures that datasets are supplied securely and used exclusively for authorised analytical functions. 

All datasets are supplied with comprehensive metadata which is maintained within the PLIDA output files to support interpretation and analysis.

The STP dataset contains detailed employee-level payroll information submitted by employers to the ATO. This includes data on salaries, wages, tax withholdings, and superannuation contributions made through a payroll. STP data is available in PLIDA at a monthly frequency. These files include information from all active employing businesses and organisations across the Australian economy. Data is available from 2020 onwards.

The dataset used for developing admin incomes uses a version of the STP dataset as of July 2025. This dataset contains employee income that has undergone transformations so that data is presented in weekly episodes for all people. This improves its quality and utility for analysis for PLIDA researchers. These transformations mean that the data available for income calculation is limited. Specifically, breakdowns of payment categories and pay periods are not available, preventing the assessment of data at a finer level of granularity. The current STP data was superseded by an expanded set of information on 24 October 2025.

The Income Tax Return (ITR) dataset comprises annual information submitted by taxpayers to the ATO, including details on income, deductions, and tax liabilities of individuals. The data items currently available in PLIDA have a high degree of consistency over time. While providing a comprehensive range of data items for many in the population, the dataset may contain incomplete information due to unlodged tax returns. This includes people who have not yet lodged their return for the year, or those who are not required to lodge a return.

The ATO supplies data for a given financial year to the ABS for inclusion in PLIDA in two extracts. An extract of data at 12-months after the end of a financial year is followed by another file 16-months after the same financial year. The latter extract contains more complete data, including individuals who required an extension to lodge their tax returns for a given year. Financial year ITR datasets are available in PLIDA from 1999-2000 onwards. Data for a given year is available in PLIDA approximately 18 months following the reference financial year. 

The Payment Summary (PS) dataset contains detailed records of individuals’ financial year income, tax withheld, and other information typically required for completing an ITR. 

The PS dataset includes data for individuals who received an Income Statement—formerly known as a Pay As You Go (PAYG) payment summary—from their employer, which was subsequently submitted to the ATO. While comprehensive, for some individuals the dataset may only include employment records for part of a financial year and may lack context on the actual duration of employment during the year. Additionally, it may not capture certain types of income payments made to employees, such as tips or employee share schemes, which are not always reported through standard payroll systems. 

Data for a given financial year are supplied by the ATO to the ABS as two extracts, the first is an extract taken 12 months after the end of a financial year. This is followed by a 16-month extract file. Data files are included in PLIDA at the same time as the given period’s ITR data.

Data is available in PLIDA from 2001-02 onwards and has maintained a high degree of data item consistency over this period.

Superannuation Account Extract (SAE) data includes information sourced from the Member Account Attribute Service (MAAS), Member Account Transaction Service (MATS), and Self-Managed Superannuation Funds (SMSFs).

MAAS/MATS are reporting mechanisms which enhance the timeliness and accuracy of superannuation data reporting. These services replaced the Member Contributions Statement (MCS) from 1 July 2018 and are now the primary channels through which superannuation providers report member account information. 

MAAS is used to report changes to member account attributes, such as account openings, updates, closures, and lost member status, ensuring that member information remains current. MATS supports event-based reporting of financial transactions within superannuation accounts, including contributions and rollovers, allowing for frequent and detailed monitoring of superannuation activity. Both services are supported by technical documentation and validation protocols to ensure data quality. The use of these services is mandatory for APRA-regulated superannuation funds. 

SMSF data is primarily sourced from lodged annual returns. This data provides insights into the structure, performance, and demographics of the SMSF sector. 

While these datasets do not directly contain superannuation income data, they provide information including the balance of accounts, for modelling superannuation income.

Data for a given year is included in PLIDA at the same time as the given period’s ITR and PS data. Data is available in PLIDA from 2018-19 onwards. 

The following data sources provide official statistics on income. These sources are linked to PLIDA and are helpful when considering admin income comparisons. 

The Survey of Income and Housing (SIH) gathers detailed information on all types of current income, housing costs and household characteristics. It collects these from a sample of private dwellings across Australia (excluding very remote areas) over the course of the financial year. All usual residents of these dwellings aged 15 years and over participate in the survey.

SIH 2019-20 was collected using an online or in-person interview method between July 2019 and June 2020. It collected information from 15,011 households, which contained 29,123 people aged 15 years and over.

SIH imputes missing responses to questions (item non-response) using a suitable donor record. Results are also weighted to correct for sampling differences and non-response, using population benchmarks.  Further information about the SIH 2019-20 methodology and data quality can be found in the survey’s user guide.

The Census of Population and Housing, 2021 provides information on the Australian population as of 10 August 2021 (Census night). It aimed to count every person and dwelling in Australia on Census night, including people in private homes, hotels, hospitals, and other types of accommodation. 

The Census collected information about total ‘usual’ income from people aged 15 years and over in a single question. The question provided a selection of response categories featuring income ranges in weekly and annual amounts. The item does not clearly apply a current or annual income concept; however, it does reflect the income available at Census time.

Census also obtained information on other items including age, sex, housing, education, employment and cultural background. More information about the Census methodology is available in the Census methodology guide.

This section presents the approaches used to calculate admin income estimates. These approaches were developed with reference to the ABS income standard. This improves their comparability with SIH and Census incomes. There are two main steps in creating estimates:

The first step (1) describes, by PLIDA admin data source, how income estimates are created for each relevant income type. 

The second step (2) describes how the estimates produced in the first step are compiled into a total admin income estimate. Depending on whether an estimate is intended for comparison against SIH or Census, this compilation is achieved in different ways, owing to differences between these collections, such as data availability, reference periods, and how SIH alone applies treatments for missing data.

This step involves the calculation of admin incomes from:

• Data Over Multiple Individual Occurrences (DOMINO)
• Single Touch Payroll (STP)
• Payment Summary (PS)
• Income Tax Return (ITR)
• Superannuation Account Extract (SAE)

Some admin sources can be used to estimate multiple income types.

These calculations are performed on linked people aged 15 years and over for the SIH 2019-20 and Census 2021, considered separately. (That is, the sample may differ between SIH and Census.) Linked records refer to data available for people who are associated with a unique PLIDA spine ID. For both SIH and Census, there are a small number of instances where the spine ID is associated with more than one record. These people are not deemed as linked. 

The linkage rates for people aged 15 years and over are:

• 89% for SIH 2019-20 (weighted percentage).
• 93% for Census 2021 (excluding imputed people and overseas visitors).

Linkage rates are important to consider as there may be characteristics of people without linkage that affect how the data represents the total population. 

• Further details of the SIH sample linkage are discussed in the SIH estimate compilation summary.
• For Census, age and labour force information for people without a linkage are presented in Table 3 in the results summary.

For SIH, the reference period for both annual and current income estimates is 2019-20. The date of household interview is used as a reference date in estimating a person’s current income. 

For Census, the reference period for annual estimates is 2020-21, while current (weekly) income estimates relate to 10 August 2021.

For each data source, the specific PLIDA Modular Product tables and key data items used in calculating income types from each source are provided. Accompanying each data item is a description of its role in the income calculation. These descriptions are explained below:

• Determines selection interval. The item determines the interval of time used for the creation of an income estimate.
• Establishes income amounts. The item is used to identify or confirm relevant income amounts.
• Distinguishes instances. The item helps ensure that each instance of an event or item is measured e.g. each job for multiple job holders.
• Checks validity. The item checks the validity of a current income calculated from using another admin source.
• Determines income received. The item helps to determine the income amount received.

DOMINO is used to derive the contributions of government pensions and allowances to both current and annual income.

The PLIDA tables used in calculation are pyh_combined_age, pyh_combined_dis, pyh_combined_fam, pyh_combined_std, pyh_combined_wrk, pyh_combined_spl, and pyh_combined_pbb. Key data items used in calculation are presented in the table below.

The income calculation for a person considers their DOMINO records relating to income payments in the chosen reference period. Particular types of non-income payments, including reimbursements, loans, or capital transfers, are ignored.

Annual income measures income received within a financial year (1 July to 30 June). For any payment that is regularly paid and spans two financial years (e.g. fortnightly Age Pension), the calculation uses the payment dates and component daily payment amounts to determine how much of each payment falls within the year, summing these values. Less frequent payments (e.g., one-off, annual, or quarterly payments) received within the financial year are included without adjustment.

Current income relates to income received in a selection interval leading up to a point in time, typically the date at which other information about the person or household is collected e.g. an interview date or Census night.

The method first determines a frequency for specific payments:

• Regularly paid payments, such as the Age Pension, have a two-week selection interval: any payments received in the last two weeks are included.
• Less frequently paid payments are allocated a selection interval that best fits the frequency of payment (e.g. quarterly or annual). This allocation helps ensure that less frequently paid amounts that contribute to current consumption needs (e.g. pension supplements) are reflected in current income estimates.

A copy of the payments mapping the component type to payment frequency used is available in the Downloads.

The derived daily payment value for each of the relevant payment types received by a person are used to calculate their weekly income.

DOMINO provides information to inform an estimate of current employee income for some recipients of a government pension or allowance. This estimate was developed principally for the SIH 2019-20 comparison, as a complete year of Single Touch Payroll information (a more suitable source of employee income data) was not available. 

Amounts of employee income are self-reported by payment recipients. Data are available in two PLIDA tables:

• inc_emp_cont, which represent continuous employee earnings from ongoing employment during periods of payment receipt.
• inc_emp_var, which represent employee earnings which reflect one-off or irregular payments from employers.

The inc_emp_cont table was not used as estimates using this source did not show a sufficient statistical alignment with current employee income in SIH 2019-20.

The key data items used in calculating employee income from inc_emp_var are presented in the table below. 

For each job identified, the contribution to income (DOM_EMP_CUR) is calculated by multiplying the derived daily earnings by 7. If more than one entry from the same employer intersects with the reference date, the median income for the employer is used.

STP is used to derive both current and annual employee income amounts.

The PLIDA tables used reference the relevant month and year of the STP_BSLN_MADIP tables. Note that this version of data was superseded by a new version of STP data on 24 October 2025.

The key data items used in calculating employee income amounts are presented in the table below.

Employee income is the sum of WEEKLYCOMPENSATION and PYR_SPNTN_CNTRBTN_RPRTBL_AMT. 

WEEKLYCOMPENSATION is a derived item that includes all wages and salary payments (including bonuses and overtime) and allowances.

Annual estimates are the aggregate of the last 12 months of weekly income values. 

A person’s current estimate is derived from STP records that have:

• an income recorded for a weekly period, and
• that week’s ending date intersects with the period defined by the reference date and the four weeks prior.

Recall that the STP extract used in PLIDA transforms data into weekly episodes. This means that all employees have weekly entries regardless of how frequently they are paid. For each job worked in the four weeks prior to the reference date, if there are at least three of these intersecting weekly employee income amounts, the median of these is calculated. Such median values are added together to form a total weekly estimate. These reference, as appropriate, a data interval of duration:

• one month (STP_EMP_CUR_1M)
• three months (STP_EMP_CUR_3M)
• six months (STP_EMP_CUR_6M).

A one-month estimate therefore might not be available for an individual (e.g. as only two weekly incomes are available), but it may be possible to calculate a three-month or six-month estimate.

Additionally, a current income estimate based on twelve months of data is created (STP_EMP_12M). The initial focus is still on considering each current job separately. Instead of calculating the median income for each current job, the average income of each job is calculated. This involves, for each job, forming the total income received in the 12 months leading up to the reference date. A total is then divided by the total number of weeks between the first STP weekly income record for the job within that 12-month window and the reference date. The resulting weekly estimates for all current jobs are added together to produce a total weekly current income estimate.  

Note that STP_EMP_12M could not be produced for SIH 2019-20 as STP data are not available prior to 2020. STP also provides information about whether a person is an active employee (using ABN_HASH_TRUNC), which helps to establish the applicability of current income measures derived from PS and ITR sources when used for SIH comparisons (see below).

PS data is used to create current and annual employee income estimates.

The relevant PLIDA table is the instance of madipge-ato-d-pay-sum-fy that corresponds to the appropriate financial year period.

Key data items used in calculating employee income amounts are presented in the table below.

A person’s annual income is estimated from the aggregate of all their records of income over the financial year. 

ITR data is used to prepare estimates for all types of income.

The relevant PLIDA table is the atoitrincloss table.

Key data items used in preparing annual and current employee income are presented in the table below.

Annual income for a person is estimated from the aggregate of their relevant items within a financial year. 

Like annual estimates, current income is estimated from the aggregate of relevant items for a person within a financial year. However, additional checks are applied to screen out estimates likely to be invalid for the reference date. This primarily includes checking for employment income in more recent STP data.

Amounts from lump sum payment/s are included in current income using a cut-off at the equivalent of 3 months’ pay, based on the greater of AWE and ITR income (excluding lump sums). This helps ITR income measures represent amounts of a lump sum payment that are intended to support current living standards.

Key data items used in preparing annual and current government pensions and allowances are presented in the table below.

In the calculation, the values associated with these items are restricted to include only those amounts of a government pension or allowance that are not present in DOMINO for the same reference period. (That is, inclusions here are not in DOM_GOV_ANN,  as calculated for the same year as ITR data used). Inclusions reflect instances of government payments that cannot be found in DOMINO, such as overseas or state/territory administered government payments. 

Annual income for a person is estimated from the aggregate of their relevant items within a financial year. 

Current income uses the annual government pensions and allowance income (ITR_GOV_ANN). This is a proxy for current income, given more timely data is not available.

Key data items used in preparing current and annual own unincorporated business income are presented in the table below.

Annual income for a person is estimated from the aggregate of their relevant items within a financial year. 

Current income uses the annual own unincorporated business income (ITR_UBUS_ANN). This is a proxy for current income, given more timely data is not available.

Key data items used in preparing current and annual investment income are presented in the table below.

ITR excludes investment incomes for people not required to lodge a tax return. ITR also excludes notional income from offset accounts, which is the estimate of the amount households saved in interest on their loans.

Annual income for a person is estimated from the aggregate of their relevant items within a financial year. 

Current income uses the annual investment income (ITR_INV_ANN). This is a proxy for current income, given more timely data is not available.

Key data items used in preparing current and annual superannuation pensions and annuities income are presented in the table below.

ITR excludes superannuation pension and annuity income for individuals who are not required to lodge a tax return, e.g. due to tax reporting exemptions. For this reason, the data is particularly limited.

Annual income for a person is estimated from the aggregate of their relevant items within a financial year. 

Current income uses the annual superannuation pension and annuity income (ITR_SUP_ANN). This is a proxy for current income, given more timely data is not available.

Key data items used in preparing current and annual other regular transfer income are presented in the table below.

Annual income for a person is estimated from the aggregate of their relevant items within a financial year. 

Current income uses the annual other regular transfers income (ITR_OTH_ANN). This is a proxy for current income, given more timely data is not available.

The relevant PLIDA tables used for calculating estimates is the madip-anu-fv-maasmats table.

The data items used in calculating current and annual superannuation pensions and annuities income are presented in the table below.

Superannuation Account Extract data is used to model a ‘lower-bound’ estimate of current and annual superannuation income (SAE_SUP_CUR and SAE_SUP_ANN) by applying the minimum drawdown requirement (dependent on the person’s age) to the balance of superannuation account/s obtained from the superannuation data. This approach will only partially estimate superannuation incomes, as people may draw down more than the minimum drawdown requirement.

Only accounts in the retirement phase are used in this calculation. For non-SMSF accounts, this is indicated by a particular value of the account phase code. Where more than one account produces an income, these are added together to provide a total income amount. For SMSF records, retirement phase is inferred based on the person's age and earned income. That is, the persons age must be over the preservation age, and admin data shows that no employee or own unincorporated business incomes are received by the person.

Admin income sources have limitations that make them unable to measure income as required by the ABS income standard. The table below provides a summary of these limitations. 

This section will explain how the estimates of the previous section are used in compiling estimates of annual and current income for each person in SIH 2019-20 and Census 2021.

A comparison of raw PLIDA-based income amounts with SIH 2019-20 (available in the Appendix) guided derivation methods. Additionally, derivation methods considered for each source:

• its timeliness, with more timely sources given a greater priority.
• for current income, how the source supports measurement on a specific date.
• inclusion or exclusion of incomes, guided by the ABS income standard (see section 1.6).
• availability of data for the desired period. For instance, STP data was not available in PLIDA until 2020. Therefore, the method used for estimating employee income for SIH participants is more complex than it is for those of Census, where a full financial year of STP data is available.

Other differences between SIH and Census methods reflect considerations made for the unique features of each collection e.g. reference date selection.

All SIH 2019-20 admin income estimates that are sourced from PS, ITR and ATO Superannuation data refer to 2018-19 financial year and are adjusted to 2019-20 dollars using changes in the Consumer Price Index. This adjustment reflects changes in purchasing power and living standards between these periods. Data from 2018-19 was used as the only alternative, waiting for more recent data (available approximately 18 months after the reference period) limits the timeliness of results produced. Previous financial year data, likely to be the data available in future applications, is used to demonstrate the quality attributes of timelier results.

DOMINO and STP items reference data from the 2019-20 financial year, where available.

Annual employee income selects the greater of PS_EMP_ANN or ITR_EMP_ANN.

Current employee income derives income for current government pension and allowance recipients (based on DOM_GOV_CUR>0) differently to non-recipients (DOM_GOV_CUR=0). This is due to the underlying variability in employee income that is typical for government pension and allowance recipients.

For recipients of a government pension or allowance in 2020, the derivation preferences STP_EMP_CUR_1M. If not available, the next preferences (in order of decreasing preference) are:  STP_EMP_CUR_3M, STP_EMP_CUR_6M, and the maximum of either PS_EMP_CUR or ITR_EMP_CUR. 

As STP data was unavailable in 2019, DOM_EMP_CUR was potentially used for current employee income for people participating in SIH during 2019. If this was not available, then the preference was for selecting PS_EMP_CUR over ITR_EMP_CUR. (Note: it was not possible to subject these estimates to job or employment checks using STP data.) To reduce instances of income being incorrectly assigned to people with a 2019 reference date, PS and ITR amounts were excluded from a person’s calculation where: 

• current superannuation pensions and annuity income (SAE_SUP_CUR or ITR_SUP_CUR) were present.
• they were aged less than 60 years receiving current income from government paid parental leave pay (ITR only).
• They were receiving the Age Pension (ITR only).

A residual number of records with values not available for DOM_EMP_CUR, PS_EMP_CUR or ITR_EMP_CUR, but who had reported in SIH that they were an employee, had an admin employee income imputed using hot-deck donor imputation. This assigned these records employee income information from a similar person based on age, sex and state or territory of usual residence and section of state. Additionally, where possible, the donors record would have the same marital status, family type, relationship in household, interview quarter and ranged survey weight as the record requiring imputation).

People who did not receive a current government pension or allowance received the maximum of STP_EMP_CUR_1M, _3M or _6M variants, PS_EMP_CUR or ITR_EMP_CUR. Records with a 2019 reference date used PS_EMP_CUR and STP_EMP_CUR without STP employment checks.

Annual own unincorporated business income is ITR_UBUS_ANN. Current own unincorporated business income is ITR_UBUS_CUR.

Annual government pensions and allowances use DOM_GOV_ANN if available, otherwise ITR_GOV_ANN is used. Similarly, current government pensions and allowances use DOM_GOV_CUR if available, then ITR_GOV_CUR.

To improve comparability with SIH estimates of income, amounts of coronavirus payments were modelled for eligible people and assigned to their current and annual income in the same manner as SIH.

Annual investment income is ITR_INV_ANN. Current investment income is ITR_INV_CUR.

Annual superannuation pensions and annuities income uses ITR_SUP_ANN if available, otherwise SAE_SUP_ANN is used. Similarly, current superannuation uses ITR_SUP_CUR if available, then SAE_SUP_CUR.

Annual other regular transfers income is ITR_OTH_ANN. Current other regular transfers income is ITR_OTH_CUR.

For each person, their estimate of total annual income is calculated by summing all annual estimates for the admin income type. Similarly, a person’s total current income is the sum of all current income estimates across income types.

The admin items selected in this section are summarised in the table below in preferential order (unless otherwise specified, see employee income).

For all 2,934 ’unlinked’ people missing income information (due to lack of linkage to the PLIDA spine), it was deemed appropriate to impute their admin income values. This supports the validity of comparing admin income statistics with those derived from reported incomes in SIH. 

Imputation in this setting requires an understanding of which variables contribute to the state of being unlinked. A list of potentially influential characteristics was nominated:  household and family relationship, age, sex, location, level of income as reported in SIH, and associated survey weight.  For each member of the group requiring imputation, these characteristics were compared with those of people with PLIDA linkage. A summary of comparisons is presented in the Appendix.

Based on these results, it was considered that a standard ABS imputation method, 'Hot-deck imputation', may be appropriate. This method is used to impute data for an individual from a similar ('donor') record that has complete information. A potential donor record is drawn from a pool of eligible donors and deemed eligible for use if it shares certain key characteristics with the record requiring imputation.

The implementation of Hot-deck imputation was informed by results from a logistic regression intending to recognise those covariates which were significant in determining whether a person had PLIDA spine ID. Regression results suggested key characteristics for donor selection. Further criteria were also used to guide appropriate donor selection.  An exact match was required for:

• Age (grouped in 10-year age groups from 15 to 44 years, and then from 45 to 64 years, and 65 years and over).
• Family composition of household.
• Relationship in household.
• Sex of person.

Additionally, donors were selected to match on as many of the following characteristics as possible:

• Marital status.
• Survey weight (ranged).
• Quarter of SIH interview.
• State or territory of usual residence and section of state.

The imputation process was mostly able to find suitable donors. A small remainder of records that could not be associated with suitable donors received mean imputation from similar donors based on age, family composition, or relationship in household. A comparison of the reported an imputed incomes for unlinked and linked people is available in the Appendix.

Household income values are prepared by summing total income estimates (either derived from data or as imputed as per 2.1.2) using SIH household structures.

The dataset is reviewed and edited to resolve any detected inconsistencies between income type estimates. Towards this, DOMINO and STP data are used to help ensure coherence across the income profiles of individuals and their household members. For instance, all non-government incomes for an individual and their household members are reviewed alongside government pension and allowance incomes. This includes assessing against the maximum eligible amount for at which a person becomes ineligible for certain payments.

Statistics are weighted for output. The results from this study use the same sample and weights that are calculated for SIH 2019-20 population estimates. 

More information on weights is available in the Survey of Income and Housing User Guide. The user guide also provides information to assist the interpretation of weighted income measures presented in the results.

All Census 2021 admin income estimates sourced from ITR and ATO Superannuation data refer to the 2019-20 financial year. Estimates are adjusted to 2020-21 dollars using changes in the Consumer Price Index. This reflects changes in purchasing power and living standards between these periods. Data from 2019-20 was used as the only alternative, waiting for more recent data (available approximately 18 months after the reference period) limits the timeliness of results produced. Previous financial year data, likely to be the latest data available in future applications, is used to demonstrate the quality attributes of timelier results.

DOMINO and STP items reference data from the 2020-21 financial year, or the period following the end of the previous financial year to the reference date.

Annual estimates of employee income use STP_EMP_ANN.

Current employee income estimates are derived differently for current government pension and allowance recipients (indicated by DOM_GOV_CUR>0) compared to non-recipients (DOM_GOV_CUR=0). This is due to the underlying variability in employee income for government pension and allowance recipients.

For recipients of a government pension or allowance, STP_EMP_CUR_1M is used preferentially. If not available, then the preferences (in decreasing order) are STP_EMP_CUR_3M, followed by STP_EMP_CUR_6M and STP_EMP_12M.

People who did not receive a current government pension or allowance receive STP_EMP_12M as their current employee income.

Annual own unincorporated business income is ITR_UBUS_ANN. Current own unincorporated business is ITR_UBUS_CUR.

Annual government pensions and allowances use DOM_GOV_ANN if available, otherwise ITR_GOV_ANN is used. Similarly, current government pensions and allowances use DOM_GOV_CUR if available, then ITR_GOV_CUR.

Annual investment income is ITR_INV_ANN. Current investment income is ITR_INV_CUR.

Annual superannuation pensions and annuities use ITR_SUP_ANN if available. If this is not available SAE_SUP_ANN is used. Similarly, current superannuation uses ITR_SUP_CUR if available, then SAE_SUP_CUR.

Annual other regular transfers income is ITR_OTH_ANN. Current other regular transfers income is ITR_OTH_CUR.

For each person, their estimate of total annual income is calculated by summing all annual estimates for the admin income type. Similarly, a person’s total current income is the sum of all current income estimates across income types.

The admin items selected in this section are summarised in the table below in preferential order.

Household income values are prepared by summing total income estimates using Census household structures.

The dataset is reviewed and edited to resolve any detected logical inconsistencies. For example, specific age checks were applied to recipients of Youth Allowance and Age Pension amounts to ensure that amounts were not allocated to people not eligible for these payments.

Comparisons of administrative incomes and equivalent SIH 2019-20 reported incomes are presented below. 

Comparisons are for:

• the 26,189 people aged 15 years and above with PLIDA linkage (see section 1)
• each income type, by PLIDA data sources used
• current income, in weekly dollars
• government pensions and allowances income excluding Commonwealth Rent Assistance.

Results are based on unweighted data and do not account for sample error. Additionally, comparisons do not adjust for specific measurement differences between survey and admin data (e.g. misalignment in how specific incomes are categorised to an income type). As such, results provide only a general indication of the alignment of a source with SIH income. These are helpful to consider when determining their use towards final estimates. 

Histograms below display the counts of people with an income value from administrative or SIH data, rounded to a multiple of some unit (e.g. 100 dollars). From each of these we can infer the relative proportions of individuals in the various income groups.

Employee income was reported by 16,141 people in SIH (62%). 

PLIDA produces employee income from four sources (STP, PS, ITR and DOMINO).

The use of STP in estimating employee income produces:

• 5,322 instances of STP_EMP_CUR_1M (20% of all people)
• 5,477 instances of STP_EMP_CUR_3M (21%)
• 5,479 instances of STP_EMP_CUR_6M (21%).

Note that STP data is not available for SIH people interviewed in 2019.

Of the people having a variant of STP_EMP_CUR as listed above, 94% also had SIH information on employee income available. Summary statistics for these distinct types of employee income estimate are summarised in the table below.

Those individuals having both STP_EMP_CUR_1M and SIH employee income, contribute to the distributions of these estimates, is displayed below. The distributions for STP_EMP_CUR_3M and STP_EMP_CUR_6M are similar.

There are 8,924 instances where PS_EMP_CUR (34% of all people) is associated with any employer recorded in STP data between January 1 and June 30, 2020.

Of these people, 94% (8,355 people) have a comparable reported value of employee income in SIH. The mean PS_EMP_CUR for this group is $1,546, while SIH employee income is $1,569. The respective medians were $1,323 and $1,292. There was a strong positive correlation between these items (r=0.77, p<0.0001).

There were 12,972 instances where ITR_EMP_CUR (50% of people) is associated with any employer recorded in STP data between January 1 and June 30, 2020. 

Of these people, 11,638 (90%) also have a reported value for SIH employee income. The mean ITR_EMP_CUR for these people is $1,464, while their SIH employee income is $1,516. The respective median employee income values are $1,253 and $1,247. There is a strong positive correlation between these items (r=0.76, p <0.0001).

There are 696 people with a positive DOM_EMP_CUR (3% of all people).

Of these people, 625 (90%) have SIH reported information on employee income also available. The mean DOM_CUR_EMP for this group is $488, while their SIH employee income is $560. The respective median employee incomes are $416 and $466. There is a moderate positive correlation between these items (r=0.61, p <0.0001).

1,497 people (6%) in SIH reported an instance of own unincorporated business income.

There were 3,025 instances of ITR_UBUS_CUR, where at least one of the contributing ITR income variables contain non-missing data (12% of people).

Of these instances, 30% (907 people) had both an admin and a reported SIH value for own unincorporated business income. The mean ITR_UBUS_CUR value is $926, while the SIH value is $1,034. The respective medians are $513 and $610. There was a strong positive correlation between these items (r=0.70, p<0.0001).

8,659 people (33%) reported an Australian government pension and allowance income in SIH.

There were 10,864 people with DOM_GOV_CUR (41% of all people).

Of these, 7,194 (66%) also have SIH reported information on government pensions and allowances available. The mean DOM_GOV_CUR for this group is $371 and the mean SIH amount was $370. The respective medians are $366 and $389. The correlation of DOM_GOV_CUR with SIH employee income is strong and positive (r=0.81, p <0.0001).

There were 144 people identified with ITR_GOV_CUR payments (1% of people). Of these, there were 103 people with ITR_GOV_CUR (72%) who also had a government pension and allowance amount reported in SIH. The mean ITR_GOV_CUR is $342, while the mean SIH value was $381. The respective medians are $224 and $298. These items are weakly positively correlated (r=0.13, p=0.15).

16,542 people in SIH (63%) reported investment income.

There were 13,351 people with a non-zero ITR_INV_CUR amount (51% of people). 

Of these, there were 8,784 people with a non-zero ITR_INV_CUR (66%) who also reported investment income in SIH. The mean ITR_INV_CUR value is $255, while the mean SIH value is $218. The respective medians are $13 and $9. There is a moderate positive correlation between these items (r=0.65, p<0.0001).

2,882 (11% of people) in SIH reported superannuation pensions and annuities income.

There are 656 people with non-zero ITR_SUP_CUR (3% of people).

Of these, there were 546 people (83%) with an ITR_SUP_CUR value who also had a SIH superannuation pension and annuity value. For these people, the mean ITR_SUP_CUR is $756, while the mean SIH value is $890. The respective medians are $628 and $798. There is a strong positive correlation between these items (r=0.74, p<0.0001).

There are 2,532 people with SAE_SUP_CUR (10% of people).

Of these, 1,761 (70%) reported a SIH value. For these people, the mean SAE_SUP_CUR value is $476 and the SIH mean is $609. The respective medians were $294 and $479. There is a moderate positive correlation between these items (r=0.53, p<0.0001).

2,445 (9% of people) reported instances of other regular transfer income in SIH.

There are 1,283 people with non-zero ITR_OTH_CUR (5% of people).

Of these, 73 people (6%) also had a reported value of other regular transfers in SIH. For these people, the mean ITR_OTH_CUR is $213 and the SIH mean is $575. The respective medians are $9 and $327. There is a moderate positive correlation between these items (r=0.43, p=0.0002).

The table below provides a summary of selected characteristics of people aged 15 years and over who participated in SIH, according to their linkage status. This has two distinct values:

• Unlinked - people are missing admin income information either due to unsuccessful linkage to a PLIDA spine ID, or because the people are associated with multiple spine IDs exist in at least one PLIDA source used.
• Linked – people with linkage to a PLIDA spine ID, and this spine ID is not replicated in any PLIDA source used.

Additionally, the total for all people is presented alongside linkage status for comparison.

All statistics are weighted using SIH 2019-20 survey weights.

Total incomes, as reported in SIH, for the Unlinked and Linked groups are displayed in the graph below in $100 ranges.

Mean SIH-reported incomes, of total income and for each income type, for unlinked and linked groups, and for the total population (linkage status ignored), are presented in the first table below. This is followed by a comparable table for income derived from admin sources.  

Compared to linked persons, unlinked people report lower average incomes across most income types. The exception is for other regular transfers, where the unlinked mean income is double the corresponding linked value.

In a similar manner to Table 17, the admin income results in Table 18 show that, for both annual and current income estimates, the mean total income imputed for unlinked people is lower than that for linked people. However, compared to Table 17, Table 18 shows some notable differences. One is that the unlinked group has a higher mean employee income than the linked group. Another is that, for both current and annual income estimates, the mean of other regular transfers income is similar across linked and unlinked groups. This indicates that donor information is more likely to reflect employee income rather than other regular transfers, likely due to limitations in how the latter is captured in admin data sources.