Usual residence five years ago (information about this variable and its quality)

Priority level

Priority level 2

We assign a priority level to all census variables: Priority 1, 2, or 3 (with 1 being highest and 3 being the lowest priority).

Usual residence five years ago is a priority 2 variable. Priority 2 variables cover key subject populations that are important for policy development, evaluation, or monitoring. These variables are given second priority in terms of quality, time, and resources across all phases of a census.

The Census priority level for usual residence five years ago remains the same as 2013.

Quality Management Strategy and the Information by variable for usual residence five years ago (2013) have more information on the priority rating.

Overall quality rating for 2018 Census

Poor quality

Data quality processes section below has more detail on the rating for this variable.

Caution is advised when using this variable at small geographies. Please see Recommendations for use and further information section below.

The External Data Quality Panel has provided an independent assessment of the quality of this variable and has rated it as poor quality. 2018 Census External Data Quality Panel: Assessment of Variables has more information.

Subject population

Census usually resident population

‘Subject population’ means the people, families, households, or dwellings to whom the variable applies.

How this data is classified

Census Usual Residence 5 Years Ago Classification V1.0.0

Usual residence five years ago address is a flat classification showing the meshblock of a respondent’s usual residence five years ago.

The usual residence five years ago classification consists of a combination of classifications that are ordinarily stored independently of each other. There is a hierarchic relationship between the New Zealand geographic classifications of meshblock, statistical area 2 (SA2), territorial authority (TA) and regional council (RC). For example, SA2s aggregate to form both TAs and RCs. The categories of each of these ordinarily independent classifications sit alongside each other at the same level of this classification. The country classification also sits alongside the New Zealand statistical standard of geographic areas, at the same level of the usual residence 5 years ago classification.

The standard codes are:

Meshblock codes (7 digits)

SA2 codes (6 digits) prefixed by '9'

TA codes (3 digits) prefixed by '9999'

RC codes (2 digits) prefixed by '99999'

Country codes (4 digits) prefixed by '999'

9999977 Response unidentifiable

9999988 Response outside scope

9999994 Unable to match to 2013 census data

9999995 Not born 5 years ago

9999996 No fixed abode

9999997 Country not stated

9999998 New Zealand not further defined

9999999 Not stated

The 2018 classification differs from previous versions, due to 2013 Census data at meshblock level being used as a source for this variable rather than a question on the form.

Other differences from the 2013 Census are:

• area units were replaced by SA2s
• two residual categories ‘don't know’ and ‘refused to answer’ were removed
• a new residual category of ’unable to match to 2013 Census data’ was added
• SA2, TA, and RC categories were appended with 'not further defined (nfd)' to clarify their use in coding.

The Standards and Classifications page provides background information on classifications and standards.

Usual Residence 5 Years Ago Indicator Classification 2 V3.0.0

Usual residence five years ago indicator is a flat classification with the following categories:

1 Same as Usual Residence

2 Elsewhere in New Zealand

3 Not Born Five Years Ago

4 Overseas

5 No Fixed Abode Five Years Ago

9 Not elsewhere included

‘Not elsewhere included’ contains the residual categories:

77 Response unidentifiable

94 Unable to match to 2013 Census data

98 New Zealand not further defined

99 Not Stated

Census Usual Residence 5 Years Ago SummaryV3.2

01 Same Usual Residence as 5 Years Ago

02 Same Territorial Authority

03 Same Regional Council, Different Territorial Authority/Territorial Authority unknown

04 Different Regional Council , Same Island

05 Different Regional Council, Different Island

06 Area Outside Regional Council /Territorial Authority stated but Regional Council not further defined/Area Outside Territorial Authority

07 No Fixed Abode 5 Years Ago

08 Overseas 5 Years Ago

09 Not Born 5 Years Ago

94 Unable to match to 2013 Census data

97 Response Unidentifiable

98 New Zealand Not Further Defined

99 Not Stated

Code ‘06’ (Area Outside Regional Council/Territorial Authority stated but Regional Council not further defined/Area Outside Territorial Authority) was not used in 2018 because we coded records to more precise locations.

Question format

There is no question on the 2018 Census form for this variable. Instead, data for the Census 2018 usual residence subject population was sourced from the 2013 Census. This variable was collected as a question in previous censuses.

We applied coding rules to:

• respondents aged less than five year old, who were coded to ‘not born five years ago’
• respondents who arrived in New Zealand fewer than five years ago, who were coded to ‘overseas five years ago’.

We then matched the rest of the census usually resident population to 2013 Census data to extract their usual residence meshblock in 2013.

How this data is used

Outside Stats NZ

• Supporting long-term service planning (e.g. housing and transport planning, public health planning).
• Understanding population mobility within a region.

Within Stats NZ

• Improving Tier 1 statistics, eg population estimates.
• Measuring internal migration.
• Understanding regional population fluctuations.
• Contributing to the quality of population estimates and projections.

2018 data sources

We used responses from the 2013 Census to provide information for usual residence five years ago.

The table below shows the breakdown of the various data sources used for this variable.

We applied coding rules to the 2018 Census usually resident population born after the 2013 Census, and to people who were not in New Zealand during the 2013 Census. They were coded to ‘not born five years ago’ and ‘overseas five years ago’ respectively.

For the rest of the census usually resident population, there was only one data source for usual residence five years ago - usual residence at the 2013 Census.

‘No information’ is where we could not match respondents back to the 2013 Census dataset.

Please note that when examining Usual residence 5 years ago data for specific population groups within the subject population, the percentage with no information may differ from that for the overall subject population.

Missing and residual responses

No information in the data sources table above is the percentage of the subject population coded to ‘unable to match to 2013 Census data’. In previous censuses, non-response was the percentage of the subject population coded to ‘not stated.’

In 2018, the proportion of responses coded to ‘unable to match to 2013 Census data’ is high because there were no alternative data sources or imputation for the ‘usual residence five years ago’ variable.

No information:

• 2018: 14.6 percent
• 2013: 3.5 percent
• 2006: 2.9 percent.

The 'New Zealand not further defined' category included respondents who gave insufficient information to allow coding to area unit, territorial authority, or regional council. In 2018, we were able to code responses to more exact locations so very few responses were coded to this category.

NZ not further defined:

• 2018: < 0.01 percent
• 2013: 5.3 percent.

2013 Census data user guide provides more information about non-response in the 2013 Census.

Data quality processes

Overall quality rating: Poor quality

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

Three quality metrics contributed to the overall quality rating:

• data sources and coverage
• consistency and coherence
• data quality.

The lowest rated metric determines the overall quality rating.

Data quality assurance for 2018 Census provides more information on the quality rating scale.

Data sources and coverage: Poor quality

We have assessed the quality of all the data sources that contribute to the output for the variable. To calculate a 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 2013 Census match is defined as 1.00. Ratings for other sources are the best estimates available of their quality relative to a 2013 Census match. 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:

• 98–100 = very high
• 95–<98 = high
• 90–<95 = moderate
• 75–<90 = poor
• <75 = very poor.

For usual residence five years ago, 2013 Census data was the only data source. The proportion of data sourced from the 2013 Census along with the no information (unable to match to 2013 Census data) rate of 14.64% determined the overall poor quality rating of 0.85.

Consistency and coherence: High quality

The usual residence five years ago variable metric for consistency and coherence is high quality.

Variable data is consistent with expectations across nearly all consistency checks, with some minor variation from expectations that makes sense due to real-world change, incorporation of other sources of data, or a change in how the variable has been collected.

Data quality: High quality

The data quality checks included edits for consistency within the dataset and cross-tabulations to regional council level. For the usual residence five years ago variable, there were no major issues with quality.

Recommendations for use and further information

As the 2013 census was the only source of data for this variable, with no admin data or imputation used to replace missing responses, the overall quality is poor. However, the quality of the matched responses is sound and comparable with 2013 and 2006 censuses.

We recommend that the use of this data can be similar to that produced in 2013, with some caution:

• when using 'usual residence five years ago indicator' at small geographies, there will be variability in the percentage of missing data for a given area. This means some small geography areas will have poorer quality data than the overall quality rating.
• when examining Usual residence 5 years ago data for specific population groups within the subject population, the percentage with no information (unable to match to 2013 Census data) may differ from that for the overall subject population.

Contact our Information Centre for further information about using this variable