Quality Statement

Label
Usual residence one year ago - 2023 Census: Information by concept en-NZ
Definition

Usual residence one year ago address identifies an individual’s usual residence on 7 March 2022, which may be different to their current usual residence (7 March 2023). This variable reports an individual’s usual residence one year ago at the lowest possible geographic level.

Usual residence one year ago indicator determines if there is a difference between an individual’s usual residence and their usual residence one year ago. It provides information on the migration of people within New Zealand and of those who have either been born or arrived from overseas over the last year.

en-NZ
Overall quality rating

Usual residence one year ago address: High quality
Usual residence one year ago indicator: High quality
Data quality processes section below has more detail on the rating.

en-NZ
Priority level

Priority level 2
A priority level is assigned to all census concepts: priority 1, 2, or 3 (with 1 being highest and 3 being the lowest priority).
Usual residence one year ago is a priority 2 concept. Priority 2 concepts cover key subject populations that are important for policy development, evaluation, or monitoring. These concepts are given second priority in terms of quality, time, and resources across all phases of a census.
The census priority level for usual residence one year ago remains the same as 2018.
The 2023 Census: Final content report has more information on priority ratings for census concepts.

en-NZ
Subject population

Census usually resident population count
‘Subject population’ means the people, families, households, or dwellings that the variable applies to.

en-NZ
How this data is classified

Usual residence one year ago address
The usual residence one year ago classification consists of a combination of geographic classifications that are ordinarily stored independently of each other. There is a hierarchical relationship between the New Zealand geographic classifications of meshblock, statistical area 2, territorial authority, and regional council. They are combined for the purpose of providing as much detail as possible for usual residence one year ago. Ideally usual residence one year ago would be defined at the meshblock level. Where this is not possible, the next most detailed geography is used.

Usual residence one year ago is classified into the following categories:

Usual Residence 1 Year Ago Classification V3.1.0 – level 1 of 1

  • Meshblock codes (7 digits)
  • Statistical area 2 codes (6 digits) prefixed by '9' and appended with 'nfd'
  • Statistical area 3 codes (5 digits) prefixed by '99' and appended with 'nfd'
  • Territorial authority codes (3 digits) prefixed by '9999' and appended with 'nfd'
  • Regional council codes (2 digits) prefixed by '99999' and appended with 'nfd'
  • Country codes (4 digits) prefixed by '999'
  • 9999977 Response unidentifiable
  • 9999988 Response outside scope
  • 9999995 Not born 1 year ago
  • 9999996 No fixed abode
  • 9999997 Country not stated
  • 9999998 New Zealand not further defined
  • 9999999 Not stated

Follow the link above the table to examine the classification in more detail.

Address information (street number, name, and flat number; suburb or rural locality; city, town, or district; and country) is used to place a person into the classification. The detail of the response dictates what level this response can be coded to, with the most detailed level of meshblock being the ideal.

The 2023 classification used for usual residence one year ago address is similar to 2018 in structure, however area codes have been updated to reflect the 2023 geographic pattern, including the addition of statistical area 3 codes.

Usual residence 1 year ago indicator
Usual residence one year ago indicator is classified into the following categories:

Usual Residence 1 Year Ago Indicator Classification V2.0.0 – level 1 of 2

Code Category
1 Same as usual residence
2 Elsewhere in New Zealand
3 Not born one year ago
4 Overseas
5 No fixed abode one year ago
9 Not elsewhere included

Usual residence one year ago indicator uses a 2-level hierarchical classification with level 1 presented in the table below. The level 1 residual category ‘Not elsewhere included’ contains the residual categories ‘Response unidentifiable’, ‘New Zealand not further defined’, and ‘Not stated’.

Follow the link above the table to examine the classification in more detail.

The 2023 Census classification for usual residence one year ago indicator is consistent with that used in 2018 Census. Usual residence one year ago indicator can also be summarised by:

The summary variables are different than in the 2018 Census as they have been split into two variables to reflect the different geography levels.

Standards and classifications has more information on what classifications are, how they are reviewed, where they are stored, and how to provide feedback on them.

en-NZ
Question format

Usual residence one year ago address information is collected on the individual form (question 14 paper form).

The one year ago indicator is derived from the relationship between a respondent’s current usual residence and their usual residence one year ago.

There were differences in question layout, and the way a person could respond between the modes of collection (online and paper forms).

On the online form:

  • the individual form was automatically populated with the respondent’s usual address from the household set up form. The respondent was then asked to confirm if they lived there one year ago. If they did not live there and instead selected ‘at another New Zealand address’, they were required to then enter that address. If they selected ‘I lived overseas 1 year ago’, they were asked to enter the country name. The text boxes had as-you-type functionality.

On the paper form:

  • respondents could tick a box to indicate that one year ago, they were ‘not born one year ago’, ‘at their usual residence’, ‘at another address’, or ‘overseas’. If they chose ‘at another address’, they were asked to write in that address. If they selected ‘overseas’, they were asked to provide the name of the country where they usually lived one year ago. Non-response and responses outside the valid range were possible, such as multiple inconsistent responses. For example, respondents could:
    • tick multiple boxes and not write anything in the text fields
    • tick a box and write something in multiple text fields
    • not tick any boxes and write something in multiple text fields
    • tick multiple boxes and write something in multiple text fields.

Data from online forms may therefore be of higher overall quality than data from paper forms. However, processing checks and edits were in place to improve the quality of the paper forms.

Stats NZ Store House has samples for both the individual and dwelling paper forms.

en-NZ
Examples of how this data is used

Data-use outside Stats NZ:

  • to understand population mobility within New Zealand
  • to support long-term service planning (for example, housing and transport planning, public health planning).

Data-use by Stats NZ:

  • to measure and identify trends in internal migration
  • to contribute to the quality of subnational population estimates and projections
  • to construct matrices to examine inflows and outflows in more detail (for example, regional council area of usual residence one year ago (that is, 2022 address) by usual residence regional council area (that is, 2023 address)
  • for distinguishing movers and non-movers.
en-NZ
Data sources

Usual residence one year ago address
Alternative data sources were used for missing census responses and responses that could not be classified or did not provide the type of information asked for. The table below shows the distribution of data sources for usual residence one year ago address data.

Data sources for usual residence one year ago address data, as a percentage of census usually resident population count, 2023 Census
Source of usual residence one year ago address data Percent
2023 Census response 84.7
 2023 Census form 84.5
 2023 Census individual variable sources from dwelling/household set-up form 0.2
Historical census 0.0
Admin data 14.3
Deterministic imputation 0.2
Statistical imputation 0.1
 CANCEIS(1) donor’s response sourced from 2023 Census form 0.1
 CANCEIS donor’s response sourced from dwelling/household set-up form <0.1
 CANCEIS donor’s response sourced from admin data <0.1
No information 0.7
Total 100.0
1. CANCEIS = imputation based on CANadian Census Edit and Imputation System
Note: Due to rounding, individual figures may not always sum to the stated total(s).

When a respondent ticked the box to indicate that their usual residence one year ago address was the same as their current usual residence address, their usual residence one year ago address is sourced from the same data source as usual residence address. While this is usually a census form, at times the information on a census form cannot be coded so the information will have been alternatively sourced.

To replace missing or residual responses, the following admin data sources were used:

  • Accident Compensation Corporation
  • 2013 Census
  • 2018 Census
  • Department of Internal Affairs
  • Inland Revenue
  • Kāinga Ora
  • Ministry of Education
  • Ministry of Health
  • Ministry of Social Development
  • New Zealand Transport Agency.

2013 and 2018 Censuses addresses are used as inputs to the models for determining usual residence address from admin data, but are not split out as separate data sources.

Predicting usual residence address from admin data in the 2023 Census describes this process in more detail.
Data from New Zealand Customs Service was also used to identify people who were overseas 5 years ago.
Deterministic derivation from another variable is used to classify records as ‘not born one year ago’ if the person’s age is less than one year.
Statistical imputation was used for the remaining missing values.

Usual residence one year ago indicator
Usual residence address and usual residence one year ago address were used to derive the usual residence one year ago indicator. The data sources from each of the input variables can be found above and in the Usual residence address – 2023 Census Information by concept.

Editing, data sources, and imputation in the 2023 Census describes how data quality is improved by editing, and how missing and residual responses are filled with alternative data sources (admin data and historical census responses) or statistical imputation. The paper also describes the use of CANCEIS (the CANadian Census Editing and Imputation System), which is used to perform imputation. This webpage also contains a spreadsheet that provides additional detail on the admin data sources.

en-NZ
Missing and residual responses

Missing and residual responses represent data gaps where respondents either did not provide answers (missing responses) or provided answers that were not valid (residual responses).

Where possible, alternative data sources have been used to fill missing and residual responses in the 2023 and 2018 Censuses.

Usual residence one year ago address and usual residence one year ago indicator

Percentage of ‘Not stated’ for the census usually resident population count:

  • 2023: 0.7 percent
  • 2018: 15.2 percent

For usual residence one year ago address and usual residence one year ago indicator, the response unidentifiable and New Zealand not further defined responses are grouped with ‘Not stated’ and are classified as ‘Not elsewhere included’.

Percentage of ‘Not elsewhere included’ for the census usually resident population count:

  • 2023: 0.7 percent
  • 2018: 16.8 percent
en-NZ
Data quality processes

Overall quality rating:

  • Usual residence year ago address: High
  • Usual residence year ago indicator: High

Data has been evaluated to assess whether it meets quality standards and is suitable for use.

Three quality metrics contribute to the overall quality rating:

  • data sources and coverage
  • consistency and coherence
  • accuracy of responses.

The lowest rated metric determines the overall quality rating.

Data quality assurance in the 2023 Census provides more information on the quality rating scale.

In the 2023 Census, the address and indicator variables have been given separate data quality ratings. In the 2018 Census, one rating was given for usual residence one year ago.

Data sources and coverage:

  • Usual residence one year ago address: Very high quality
  • Usual residence one year ago indicator: Very high quality

The quality of all the data sources that contribute to the output for the variable were assessed. To calculate the data sources and coverage quality score for a variable, each data source is rated and multiplied by the proportion it contributes to the total output.

The rating for a valid census response is defined as 1.00. Ratings for other sources are the best estimates available of their quality relative to a census response. Each source that contributes to the output for that variable is then multiplied by the proportion it contributes to the total output. The total score then determines the metric rating according to the following range:

  • 0.98–1.00 = very high
  • 0.95–<0.98 = high
  • 0.90–<0.95 = moderate
  • 0.75–<0.90 = poor
  • <0.75 = very poor.

Usual residence one year ago address
The high proportion of data received from 2023 Census forms, alongside the high quality of the alternative data sources, resulted in a score of 0.98, leading to the quality rating of very high.

Data sources and coverage rating calculation for usual residence one year ago address data, census usually resident population count, 2023 Census
Source for usual residence one year ago address data Rating Percent Score contribution
2023 Census response 1.00 84.74 0.85
Admin data 0.89 14.28 0.13
Deterministic imputation 1.00 0.21 <0.01
CANCEIS(1) nearest neighbour imputation 0.60 0.07 <0.01
No information 0.00 0.71 0.00
Total 100.00 0.98
1. CANCEIS = imputation based on CANadian Census Edit and Imputation System.
Note: Due to rounding, individual figures may not always sum to the stated total(s) or score contributions.

Usual residence one year ago indicator
For the usual residence one year ago indicator variable, a score of 0.98 has determined the very high quality rating in 2023.

Data sources and coverage rating calculation for usual residence one year ago indicator data, census usually resident population count, 2023 Census
Source for usual residence one year ago data Source for usual residence data Rating Percent Score contribution
2023 Census response 2023 Census response 1.00 84.65 0.85
2023 Census response CANCEIS(1) nearest neighbour imputation 0.80 0.09 <0.01
Admin data 2023 Census response 0.95 4.40 0.04
Admin data Admin data 0.90 9.83 0.09
Admin data CANCEIS nearest neighbour imputation 0.75 0.05 <0.01
Deterministic derivation 2023 Census response 1.00 0.06 <0.01
Deterministic derivation Admin data 0.95 0.15 <0.01
Deterministic derivation CANCEIS nearest neighbour imputation 0.80 <0.01 <0.01
CANCEIS nearest neighbour imputation 2023 Census response 0.80 <0.01 <0.01
CANCEIS nearest neighbour imputation CANCEIS nearest neighbour imputation 0.60 0.07 <0.01
No information 2023 Census response 0.50 0.58 <0.01
No information Admin data 0.45 <0.01 <0.01
No information CANCEIS nearest neighbour imputation 0.30 0.13 <0.01
Total 100.00 0.98
1. CANCEIS = imputation based on CANadian Census Edit and Imputation System
Note: Due to rounding, individual figures may not always sum to stated total(s) or score contributions.

Consistency and coherence:

  • Usual residence one year ago address: Very high quality
  • Usual residence one year ago indicator: Very high quality

Usual residence one year ago address and usual residence one year ago indicator data are highly consistent with expectations across all consistency checks.

The introduction of alternative data sources for these variables significantly reduced missing data, compared with 2018, and has led to higher quality data which is more consistent with expectations.

Accuracy of responses:

  • Usual residence one year ago address: High quality
  • Usual residence one year ago indicator: High quality

The usual residence one year ago address and indicator data has only minor data quality issues. The quality of coding and responses within classification categories is high. Any issues with the variables appear in a low number of cases.

Comparison of usual residence one year ago address with usual residence five years ago indicator, years since arrival in New Zealand, and years at usual residence highlight that some respondents did not answer all of these questions in a consistent manner.

As usual residence one year ago indicator is derived from high quality variables (usual residence address and usual residence one year ago address), it is also rated as high quality.

en-NZ
Recommendations for use and further information

Usual residence one year ago data can be used in a comparable manner to the 2018 Census.

There has been a change in methodology for usual residence one year ago in the 2023 Census, where admin data sources have been used to fill in missing or residual responses where possible. When comparing time series for usual residence one year ago, it is recommended to use proportion of total stated (excluding residuals), due to the decrease in missing and residual responses in the 2023 Census compared with the 2018 Census.

It is recommended that data users familiarise themselves with the changes in methodology between each census.

Data users should be aware that:

  • usual residence one year ago was reintroduced as a question in the 2018 Census for the first time since 1981, so there is no time series for this variable
  • new classifications for the summary variables, regional council and territorial authority and local board (usual residence one year ago summary RC and usual residence one year ago summary TALB), were introduced in 2023. These summary variables are therefore unable to be compared to the 2018 summary variable.
en-NZ
Information by variables from previous censuses

To assess how this concept aligns with the variables from the previous census, use the link:

Contact our Information centre for further information about using this concept.

en-NZ

Information

History

View Full History
Revision Date Responsibility Rationale
66 26/09/2024 11:33:55 AM
65 26/09/2024 10:00:58 AM