Stats NZ has a new website.

For new releases go to

www.stats.govt.nz

As we transition to our new site, you'll still find some Stats NZ information here on this archive site.

  • Share this page to Facebook
  • Share this page to Twitter
  • Share this page to Google+
Subnational Population Estimates: At 30 June 2012
Embargoed until 10:45am  –  23 October 2012
Data quality

Period-specific information
This section contains information about data that has changed since the last release.

General information
This section contains information that does not change between releases.

Period-specific information

Data sources used to estimate subnational migration

For subnational areas, net migration includes international migration (flows into and out of New Zealand) and internal migration (flows between areas in New Zealand). Multiple data sources are traditionally used to derive estimates of subnational migration because:

  • there is no direct measure of internal migration in New Zealand other than the periodic Census of Population and Dwellings
  • while New Zealand does have a direct measure of international migration (via the arrival and departure cards completed by passengers), vague, incomplete, and temporary addresses affect the quality of geographic information.

Since 2006, Statistics NZ has implemented a number of changes to its estimation methods aimed at improving the accuracy of subnational population estimates. This has included the use of new data sources and refined methods for using existing data sources. These initiatives have been given greater impetus due to:

  • the estimation challenges raised by the 2010/11 Canterbury earthquakes
  • the cancellation of the 2011 Census of Population and Dwellings, which means that population estimates have to be extended further out than usual from the 2006 base (starting point).

While producing subnational population estimates at 30 June 2012, three data sources were primarily used to estimate subnational migration by age and sex:

  • international (permanent and long-term) migration statistics
  • address change information from primary health organisation enrolment data
  • address change information from the Linked Employer-Employee Dataset (LEED).

These three datasets were selected because they have high rates of population coverage, include the key demographic variables of age and sex, and capture information on address changes.

In using these three data sources, efforts were made to identify and make use of their respective strengths. With regards to estimating subnational migration by age:

  • international migration data were used to estimate international migration for all ages
  • primary health organisation enrolment data were used to estimate internal migration for the population aged 0–14 years and 45 years and over
  • taxation data from LEED were used to estimate internal migration for the population aged 25–44 years.

There are particular challenges associated with estimating subnational migration for the 15–24 year age group. Not only is this group highly mobile, it has low coverage in many data sets (including primary health organisation enrolment data and LEED). As a result, subnational migration for this age group was estimated using the information sources mentioned above, as well as historical estimates and age-sex net migration patterns derived from population projections.

Once preliminary estimates of subnational migration had been created, several additional data sources were used to evaluate and refine the estimates. This additional process was considered necessary as no information source perfectly measures movements of the resident population. The information sources used to evaluate and refine the estimates included:

  • school enrolment data
  • electoral enrolment data
  • residential building consents 
  • information provided by territorial authorities during the annual consultation
  • data on specific population sub-groups, namely defence force personnel, prison populations, and tertiary students.

For additional information on the data sources mentioned in this section see Evaluation of alternative data sources for population estimates.

Effect of the 2010/11 Canterbury earthquakes

The 2010/11 Canterbury earthquakes triggered large migration flows as people were displaced from earthquake-affected areas. Consequently, some additional uncertainties apply to subnational population estimates at 30 June 2011 and 30 June 2012. These uncertainties concern whether population movements:

  • are short-term (ie temporary) or long-term in nature
  • occurred before or after the 30 June reference dates.

With regards to Christchurch city, a number of data sources have been used to assess subnational migration during the 2011 and 2012 June years (see Data sources used to estimate subnational migration section). These data sources yield different measures of subnational migration for Christchurch city. However, collectively the different data sources provide confidence about the general robustness of population estimates.

Geographic boundaries

The population estimates in this release are based on boundaries at 1 January 2013. They take into account recent boundary changes involving Christchurch city and Selwyn district (which came into effect on 21 March 2012), and Manawatu district and Palmerston North city (which came into effect on 1 July 2012). These boundaries align with those used in the latest subnational population projections (released 8 October 2012), and the boundaries that will be in place for the 2013 Census of Population and Dwellings.

Provisional and final estimates

The population estimates contained in this release are provisional. They incorporate provisional estimates of births, deaths, and migration that occurred in the June 2012 year. Final estimates will be released on 19 December 2012, along with area unit population estimates. In addition, all population estimates after 30 June 2006 will be revised following results from the 2013 Census of Population and Dwellings.

General information

Base population

The estimated resident population at 30 June 2006 forms the base population for deriving post-censal population estimates.

The estimated resident population of each area at 30 June 2006 is based on the census usually resident population count from the 2006 Census (held 7 March 2006), with adjustments for:

  • people missed or counted more than once by the census (net census undercount)
  • residents temporarily overseas on census night
  • births, deaths, and net migration between census night and 30 June 2006
  • reconciliation with demographic estimates at ages 0–4 years. 

Deriving subnational population estimates

Subnational population estimates for dates after 30 June 2006 were derived by updating the estimated resident population of each area at 30 June 2006 for births, deaths, and net migration (international and internal migration combined).

Birth and death registrations are used to estimate the number of births and deaths that occurred during each June year. There is often a delay between when a birth or death occurs and when it is registered, and this delay is taken into account when estimating birth and death occurrences.

Multiple data sources are used to derive estimates of subnational migration (see Data sources used to estimate subnational migration).

Subnational population estimates are consistent with national population estimates for a given reference date.

2006-base population estimates extended

Statistics NZ planned to produce 2006-base post-censal estimates until mid-2012. Following the cancellation of the 2011 Census of Population and Dwellings, 2006-base post-censal estimates will now be produced until mid-2014.

2013-base population estimates

The 2013 Census of Population and Dwellings will be held on Tuesday 5 March 2013. The 2013 Census website (www.census.govt.nz) provides information about the census.

Population estimates based on the 2013 Census are scheduled for release from August 2014.

Nature of estimates

Population estimates give the best available measure of the size and age-sex composition of the population usually living in an area. However, uncertainty is inherent in the estimation process. Statistics NZ produces subnational population estimates using a component methodology, where the components of population change (births, deaths, and net migration) are used to update a base population. There is some uncertainty associated with component data, particularly the estimation of net migration (international and internal migration combined) for subnational areas. Generally speaking, the uncertainty associated with population estimates increases as the estimates move further away from the base (starting point). Uncertainty also increases as population estimates are broken down by age, sex, and geographic area.

In reality, there is no data source that perfectly measures the resident population of New Zealand or of subnational areas. Furthermore, there is no data source that perfectly measures changes in the resident population, or even movements of the resident population within New Zealand. The periodic Census of Population and Dwellings remains the cornerstone of population statistics in New Zealand. Following the 2013 Census it will be possible to derive updated estimates of the population, to assess the accuracy of estimates since 2006, and to revise estimates where necessary.

Data accuracy

An evaluation of subnational population estimates produced during the 2002–06 period identified that, five years out from the 2001 base population, absolute relative errors were less than 5 percent for 60 out of 73 territorial authority areas (based on boundaries at 30 June 2006). For the 10 territorial authority areas with a population greater than 100,000, relative errors ranged from an underestimate of 2.2 percent (Manukau city) to an overestimate of 0.5 percent (Auckland city).

It is not possible to ascertain the accuracy of current population estimates as no independent authoritative measure of the resident population exists. Since 2006, Statistics NZ has implemented a number of changes to its estimation methods aimed at improving the accuracy of population estimates. This has included the use of new data sources and refined methods for using existing data sources (see Data sources used to estimate subnational migration).

Rounding

All figures in this release were rounded independently. All derived figures in this release were calculated using data of greater precision than published.

The rounding of estimates of the total population, and broad age groups, has been determined by the total population size of the geographic area. Estimates for areas with a population less than 10,000 are rounded to the nearest 10. For areas with a population between 10,000 and 20,000, estimates are rounded to the nearest 50. Estimates for areas with a population of 20,000 or more are rounded to the nearest 100.

The rounding of estimates of natural increase, net migration, and population change has been determined by the absolute value of the estimate. Estimates less than 1,000 have been rounded to the nearest 10. Estimates greater than 1,000 have been rounded to the nearest 100.

More information

Information about the population estimates contains detailed information about the methods used to derive population estimates.

Liability 

While all care and diligence has been used in processing, analysing, and extracting data and information in this publication, Statistics NZ gives no warranty it is error-free and will not be liable for any loss or damage suffered by the use directly, or indirectly, of the information in this publication.

Timing of published data

Our information releases are delivered electronically by third parties. Delivery may be delayed by circumstances outside our control. Statistics NZ does not accept responsibility for any such delay.

Crown copyright©

Creative Commons logo.
This work is licensed under the Creative Commons Attribution 3.0 New Zealand licence. You are free to copy, distribute, and adapt the work, as long as you attribute the work to Statistics NZ and abide by the other licence terms. Please note you may not use any departmental or governmental emblem, logo, or coat of arms in any way that infringes any provision of the Flags, Emblems, and Names Protection Act 1981. Use the wording 'Statistics New Zealand' in your attribution, not the Statistics NZ logo.

  • Share this page to Facebook
  • Share this page to Twitter
  • Share this page to Google+
Top
  • Share this page to Facebook
  • Share this page to Twitter
  • Share this page to Google+