2940.0.55.002 - Information Paper: Measuring Overcount and Undercount in the 2016 Population Census, Jul 2016  
ARCHIVED ISSUE Released at 11:30 AM (CANBERRA TIME) 01/07/2016  First Issue
   Page tools: Print Print Page Print all pages in this productPrint All


Address Text Matching
The process whereby an address is matched to a specific entry on an existing address index such as the ABS Address Register.

Automated Data Linking (ADL)
Automated linking processes used to determine possible links between Census and PES data, before any clerical matching process has begun. It employs a probabilistic linking method that uses a range of personal and address characteristics to evaluate the chance that a PES and Census record are the same individual.

Collect, Analyse, Reduce, De-duplicate and Systematise (CARDS)
A series of processes which prioritises and organises ADL output for use by the MSS system.

Computer Assisted Interviewing (CAI)
A method of data collection whereby responses are recorded directly into an electronic questionnaire on a notebook computer.

Correlation bias
A bias arising when people who were not counted in the Census are more likely to be missed in the PES than people with similar characteristics such as age, sex and Indigenous status who were counted in the Census.

The coverage is the actual population of persons within the scope of a survey about which data can actually be collected. As it is not always possible to collect data from all persons, some persons may be in scope but not in coverage. For the quality of the survey estimates, it is desirable that the survey coverage matches as closely as possible the survey scope. Coverage rules are generally applied in all surveys to ensure that each person is associated with only one dwelling, and hence has only one chance of selection.

Contact Sector
The set of all dwellings for which a Census form was received before the commencement of the PES enumeration. PES uses Census records from these dwellings during weight adjustment to improve the accuracy of estimates.

Discrete Community
A geographic location, bounded by physical or legal boundaries, and inhabited or intended to be inhabited predominantly by Aboriginal and Torres Strait Islander people, with housing or infrastructure that is either owned or managed on a community basis.

Dwelling Link Rating (DLR)
A system of classifying the quality of links for a dwelling of PES respondents to determine what level of clerical review is required. The three link ratings are Platinum, Silver and Tin.

Estimated Resident Population (ERP)
The official measure of the population of Australia based on the concept of residence. It refers to all people, regardless of nationality or citizenship, who usually live in Australia, with the exception of foreign diplomatic personnel and their families. It includes usual residents who are overseas for less than 12 months of the preceding 16 months. It excludes overseas visitors who are in Australia for less than 12 months of the preceding 16 months.

ERP rebasing
Following each Census of Population and Housing, ABS rebases its official estimates of population - the Estimated Resident Population (ERP) series. This provides the basis for population estimates until the next Census. The rebased Census-year ERP together with other Census information and data on intercensal components of population change allows ERP revisions to be made back to, but not including, the previous Census.

Freely Extensible Biomedical Record Linking (FEBRL)
Probabilistic linking software developed at the Australian National University used for PES automated data linking activities.

The process whereby an address is assigned a geographic classification.

General Population sample
All PES private dwelling sample selections other than those from discrete communities.

A household comprises either a single person, a family unit or a group of people within a dwelling who know each other and are able to provide information about each other. Usually there is only one household in each private dwelling, but separate households may be created if certain conditions apply.

A statistical process for predicting values where no response was provided to a question and a response could not be derived.

Imputed dwelling (in Census)
A dwelling which is determined to be occupied in the Census and where Census data is imputed because no Census form was received.

Intercensal Difference
The net revision (upward or downward) of the Estimated Resident Population as a result of rebasing.

Late return
A Census form which was returned after the start of PES enumeration.

Match and Search System (MSS)
The main PES clerical review facility, which allows processors to search, view, compare, and record matches between PES and Census data.

Non-contact sector
The set of all dwellings where no Census form was received, or a Census form was received after the start of the PES enumeration and is classified as a 'late return'. To preserve statistical independence, PES cannot use information from either 'late returns' or imputed dwellings from the Census when adjusting weights, but they do contribute to the undercount and overcount equations during tabulation.

Non-private dwelling
An establishment which provides a communal type of accommodation, such as a hotel, motel, hospital or other institution.

Non-sampling error
Error arising from inaccuracies in collecting, recording and processing the data. Every effort is made to minimise non-sampling error by the careful design of questionnaires, intensive training and supervision of interviewers, and efficient data processing procedures. Non-sampling error also arises because information cannot be obtained from all persons selected in the survey and data are imputed based on assumption about the non-respondents.

A discrete community that has a population of fewer than 50 people AND is administered by, or linked to, an organisation such as a Resource Agency or larger parent discrete community for the provision and maintenance of services.

Private dwelling
A residential structure which is self-contained, owned or rented by the occupants, and intended solely for residential use. A private dwelling may be a flat, part of a house, or even a room, but can also be a house attached to, or rooms above, shops or offices.

Sampling error
Sampling error occurs because data were obtained from a sample rather than the entire population. One measure of the likely difference resulting from not including all dwellings in the survey is given by the standard error. There are about two chances in three that a sample estimate will differ by less than one standard error from the figure that would have been obtained if all dwellings had been included in the survey, and about nineteen chances in twenty that the difference will be less than two standard errors.

The scope of a survey is the population about which information is to be collected.

Search address
An address where a person was reported to be staying on Census night or where a person may have been included on a Census form. PES processing attempts to locate all Census forms for each search address, in order to determine the number of times (if any) a person enumerated in the PES was included on a Census form.

Standard error
A measure of the sampling error.

Statistical Independence
A mathematical assumption that underlies PES estimation. Statistical independence requires both population independence (that people who were not counted in the Census are no more likely to be missed by the PES than people who were counted) and operational independence (that that Census operations do not influence PES operations and vice versa).

Systematic Equal Probability Sampling
A method of sampling from an ordered list by choosing one element, skipping past several others, choosing the next element and so on. The skip determines how many to take, for example a skip of 10 means take 1 in 10. For selecting dwellings from a block, this means compiling a list of dwellings, choosing at random the first dwelling to select, then applying the skip repeatedly to the end of the list.

Unoccupied dwelling (in Census)
A structure built specifically for living purposes which is habitable but the Census Collector was certain was unoccupied on Census night.