Understanding data quality

The dwelling response rate measures the number of private dwellings that returned a completed Census form as a proportion of all private dwellings believed to be occupied on Census Night.

The private dwelling response rate for the 2021 Census was 96.1%. In the 2016 Census this response rate was 95.1%, and in 2011 it was 96.5%.

The increased response rate between 2016 and 2021 is thought to be positively influenced by, but not limited to, the implementation of a ‘window of time’ enumeration period which gave respondents flexibility about when they completed their Census form. The ‘no log in code’ pathway accessible on the Census website allowed respondents to participate in the Census when they had not received or misplaced the log in code sent in the mail. The impact of COVID-19 lockdowns and various border restrictions also meant there were simply more people at home.

The table below provides a breakdown of dwelling response by state and territory across the last three censuses.

The person response rate measures how many people are included on a returned Census form as a proportion of all people (responding and non-responding) in Australia on Census Night.

Private dwellings that were occupied but did not return a Census form contribute to the number of people who are considered non-responding. Similarly, people present in non-private dwellings (hotels, hospitals, boarding houses, etc.) but who did not complete a Census form also contribute to the number of non-responding people.

There are several reasons why person non-response occurs in the Census. People may indicate a desire to mail back a Census form or to complete the form online but may forget to do so, while some people may refuse to complete a Census form altogether.

The dwelling response rate is only calculated for private dwellings, while the person response rate includes all people regardless of whether they are in a private or non-private dwelling.

The person response rate was 95.8% in the 2021 Census. In the 2016 Census it was 94.8% and in the 2011 Census it was 96.3%.

Where people have not responded to the Census, some data items are imputed for those that were missed. This includes key demographic characteristics such as age, sex, marital status, usual address and place of work. Imputation occurs to ensures a full and accurate dataset is produced for the Census (see Imputation).

The majority of item non-response is attributable to the people who did not respond to the Census at all. These people have records created for them and while key demographic data items are imputed for them, the remaining data items are left as ‘not stated’.

The second and smaller contributor to item non-response is when people return a Census form but may not answer a particular question or questions. This is referred to as item non-response.

Item non-response rates measure the number of people or dwellings that did not respond to a particular question on the Census as a proportion of the total number of people the question was applicable to. In this instance the response is left as ‘not stated’.

It is calculated by dividing the number of persons or dwellings who did not provide a response to a particular question (item) by the number of persons or dwellings for whom the question (item) would have been applicable and is expressed as a percentage.

Item non response rate (%) = Number of persons or dwellings who did not provide a response to a Census question / Total of all persons or dwellings for whom the Census question item was applicable × 100

Depending on the type of question, item non-response is categorised into Person variables and Dwelling variables.

Person item non-response rates only apply to variables that directly reflect responses to individual questions on the Census form, including imputed persons (those that did not respond to the question because they did not return a Census form).

For example, responses to the question, ‘What is the highest year of primary or secondary school the person has completed?’, were directly coded to the Highest year of school completed (HSCP) variable. Comparatively, the variable, Level of highest educational attainment (HEAP), does not have a non-response rate as it was not coded from an individual question on the Census form. It was derived from the variables HSCP and Non-school qualification: level of education (QALLP).

Person item non-response rates (that are not the key demographic imputed variables) exclude overseas visitors. Only key demographic variables are processed for overseas visitors.

The table below compares the 2021 item non-response rates for person variables to 2016 rates.

Item non-response for dwelling data items can only be calculated based on place of enumeration. Dwelling item non-response rates are only applicable to occupied private dwellings, except for Dwelling structure. The non-response rate for Dwelling structure includes both occupied and unoccupied private dwellings and is primarily sourced from the ABS Address Register. A field officer may also provide a response but a person completing their Census form is not able to.

The table below compares the 2021 item non-response rates for dwelling variables to 2016 rates.

Response rates, for both dwellings and people, and item non-response rates are internationally recognised measures that indicate the quality of Census data. Response rates give an overall indication of the number responses to the Census while item non-response rates are an indicator of a response to specific questions. The Post Enumeration Survey provides an additional, independent measure of Census coverage through its estimate of overcount and undercount.

The key indicators for the 2021 Census of Population and Housing support that the Census data is fit for purpose, with a high private dwelling response rate (96.1%) and the lowest recorded net undercount rate for an Australian Census (0.7%).

Data on this page was updated on 12 October 2022.