Workplace address (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).

Workplace address 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.

In 2013, workplace address was a priority 3 variable (supplementary).

Quality Management Strategy and the Information by variable for workplace address (2013) have more information on the priority rating.

Overall quality rating for 2018 Census

Moderate quality

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

Subject population

Employed census usually resident population aged 15 years and over.

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

How this data is classified

Workplace or Educational Institution AddressV1.0.0

Workplace address is a flat classification where all responses are coded to the most detailed level possible from the following categories:

Meshblock codes (7 digits)

Statistical Area 2 (SA2) codes (6 digits) prefixed by '9'

Territorial authority codes (3 digits) prefixed by '9999'

Regional council codes (2 digits) prefixed by '99999'

Urban rural codes (4 digits) prefixed by ‘URB’

to

9999996 No fixed address

9999998 New Zealand nfd

9999999 Not stated

8888888 Overseas

The detail of the response dictates what level this response can be coded to, with the most detailed level of meshblock being the ideal. If a response can only be coded to a higher level of geography than meshblock, such as SA2, then the name of the code is appended with ‘not further defined’ (‘nfd’) to indicate that this is the lowest level of detail that response has, and it can’t be further defined.

Although there have been no conceptual changes to the variable, there have been minor changes in the classification of this variable from the 2013 Census. A new output category of ‘Overseas’ was added to the classification. In previous censuses, a response of ‘overseas’ was coded to ‘New Zealand nfd’.

The residual category ‘New Zealand nfd’ was not used in 2018 because we decided to replace it with a more specific geography to improve data at higher geographies. Where ‘workplace address’ was not answered, there was no admin data available, or only partial workplace address information was provided, we used business rules to derive the address:

• if there was no workplace information, the workplace address code was set to ‘regional council nfd’ of usual residence
• if some information existed (for example city, suburb, or name), the workplace address code was set to ‘territorial authority nfd’ of usual residence
• if the individual was working at home, the workplace address was coded to the meshblock of usual residence.

This resulted in the categories of ‘territorial authority nfd’ and ‘regional council nfd’ increasing in 2018.

Census workplace address indicator V1.0.0

The workplace address indicator classification describes whether the respondent works at home or away from home.

The workplace address indicator classification is a flat classification:

1 Worked at home

2 Worked away from home

9 Not stated

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

Question format

Workplace address information was collected on the individual form (question 43 on the paper form).

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

There were differences between the modes of collection (online and paper forms) which resulted in higher quality for online responses.

Online, respondents were able to use an as-you-type list of business names and an address list for businesses to find and code their workplace addresses.

Respondents using paper forms had a free text response field where they wrote in their workplace address. This could result in vague responses which couldn’t be automatically coded or responses that were difficult to scan and therefore required extra coding around ‘place’ via a lookup file. The place coding captured responses like hospitals, airports, etc.

How this data is used

Outside Stats NZ

• Measure traffic flows for those who are employed (together with main means of travel to work).
• Assess daytime population in specific areas for town and traffic planning and civil defence purposes.

Within Stats NZ

• Code industry and sector of ownership variables from Stats NZ's Business Frame.

2018 data sources

We used alternative data sources for missing census responses and responses that could not be classified or did not provide the type of information asked for. Where possible, we used responses from the 2013 Census, administrative data from the Integrated Data Infrastructure (IDI), or imputation.

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

Administrative data sources

Data from the following administrative sources was used to code workplace address:

1. Individual tax return data (IR3) and Employer monthly schedule (EMS) data (Inland Revenue)

This is tax information relating to individuals and businesses, which includes information on workplace location.

2. Address notification data from the IDI

Data from the range of sources available in the IDI was used to enumerate usual residence, which was then used to derive the workplace address of employed individuals. In these cases, responses were coded to the usual residence ‘regional council nfd’ as people tend to work and live within the same regional council area.

Address notifications came from the following sources in the IDI:

• Accident Compensation Corporation
• Inland Revenue
• Ministry of Education
• Ministry of Health
• Ministry of Social Development
• Household Economic Survey (Stats NZ)
• New Zealand Transport Authority
• Household Labour Force Survey (Stats NZ)
• Auckland City Mission.

Please note that when examining workplace address data for specific population groups within the subject population, the percentage that is from 2013 Census data, administrative data, and statistical imputation may differ from that for the overall subject population.

Missing and residual responses

Workplace address indicator

This variable has no non-response (‘not stated’) in 2018. Responses that could not be classified or did not provide the type of information asked for were replaced by data derived from admin sources or by statistical imputation.

In previous censuses, there was non-response because this variable was not imputed.

Percentage of ‘not stated’ for the employed census usually resident population aged 15 years and over:

• 2018: 0.0 percent
• 2013: 4.7 percent
• 2006: 5.9 percent.

Workplace address

In 2018, the following residual codes for ‘Workplace Address Meshblock’ were replaced by ‘territorial authority nfd’ or ‘regional council nfd’ responses:

• 9999996 No fixed workplace address
• 9999977 Response unidentifiable
• 9999988 Response outside scope
• 9999998 New Zealand nfd
• 9999999 Not stated.

In 2013, we coded 8.5 percent of responses to 'New Zealand nfd' when the following conditions were met:

• respondents were employed but did not state a workplace address
• respondents stated a workplace address that could not be coded.

No fixed workplace address:

• in 2013, 0.4 percent of responses were coded to 'No fixed workplace address'
• in 2018, this category was coded to a ‘not further defined’ geography.

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

Data quality processes

Overall quality rating: Moderate 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: Moderate 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 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:

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

Admin data was moderately comparable to census forms. The high proportion of data from admin data contributed to the score of 0.90, determining the moderate quality rating.

Consistency and coherence: Moderate quality

Workplace address data is mostly consistent with expectations across consistency checks. The overall difference in the data compared with expectations can be explained through a combination of real-world change and incorporation of other sources of data.

Data quality: Moderate quality

The data quality checks for workplace address included edits for consistency within the dataset and cross-tabulations to the level of territorial authority and Auckland local board, using data from previous census years. For the main centres, we also analysed data at meshblock level.

Based on data quality, the rating is moderate. Address questions tend to have high numbers of vague responses that are difficult to code. However, coding is high quality where responses were made online and the business name as-you-type list and/or the address list was used.

Recommendations for use and further information

The data for workplace address can be used in the same ways as in the 2013 and 2006 Censuses. However, in 2018 most responses were automatically coded, while in 2013, all workplace address responses were manually coded. This change in the method of coding from manual to automated may have resulted in differences in comparability with this data.

‘Not further defined’ geographies must be included at their geographic level of analysis. For example, when analysing commuting in Auckland, ‘Auckland region nfd’ data should be included.

Contact our Information Centre for further information about using this variable.