Summary Quality Report - Mid Year Population Estimates for Northern Ireland

1. Introduction

Context for the quality report

Population estimates for Northern Ireland and areas within Northern Ireland are published annually and approximately one year in arrears. The mid-year population estimates relate to the usually resident population, including long-term migrants (people who change their country of usual residence for a period of 12 months or more), on 30 June each year.

Population estimates at the Northern Ireland level are derived using the ‘cohort component’ method. This method uses the most recent Census of the population: Each year, the population is ‘aged-on’ by one year with the number of births in the year added and the number of deaths in the year subtracted. An adjustment is also made for migration. Subsequent mid-year population estimates then use the previous year’s figures as the base.

For the Local Government Districts, the ‘cohort component’ method is also used. Further information can be found in the Methodology Report.

A number of data sources are used to compile the population estimates, including:

Census outputs;
General Register Office (GRO) Registers of Births and Deaths
Medical Card Register (NHAIS);
Higher Education Statistics Authority (HESA) – Enrolments at Higher Education and;
Ministry of Defence – Armed Forces data.

Quality assurance of these data sources for the production of population estimates has been undertaken and details of such can be found within the population statistics administrative data quality document.

The mid-year population estimates are essential building blocks for a wide range of Accredited Official Statistics. They are used as a base for other secondary population statistics such as population projections and population estimates for small geographic areas. They are also used in the weighting of survey estimates, such as the Labour Force Survey and other social surveys to ensure that they are representative of the total population. Population estimates are also widely used as denominators for rates or ratios, for example, in health and economic indicators. In addition, population estimates are used to allocate public funds to the Northern Ireland Executive through the Barnett formula.

The mid-year population estimates are the official set of population estimates for Northern Ireland. These estimates are comparable to official estimates produced by the three other UK constituent countries, the regions of England, Scotland and Wales.

2. Relevance

The degree to which the statistical product meets the user needs in both coverage and content.

As stated, the mid-year population estimates are the official set of population estimates for Northern Ireland. These estimates meet the known needs of our users as described in this section.

In terms of coverage, the mid-year population estimates are usually produced for an array of administrative and statistical geographies in Northern Ireland to meet the needs of our broad range of users. This release includes estimates at the Northern Ireland and Local Government Districts level (current) only. For both of these geographies a sufficient time series of data is supplied to allow users to examine population change; details of which are outlined on the mid-year population estimates main page. Estimates for smaller geographies will also be made available at a later date.

In relation to content, the mid-year population estimates are available unrounded by single year of age and sex to allow users to conduct their own analysis.

Additional supporting data published with the population estimates comprises components of population change which provide information on population events such as births, deaths, internal migration, international migration and other changes between the reference year and previous years. Furthermore, data tables detailing population densities and median ages provide an extra element to aid user analysis of mid-year estimates.

Mid-year population estimates have a wide variety of users within central government as well as being used by local authorities, health bodies, other public bodies, commercial companies and individuals in the private and academic sectors. These users can be categorised into two broad groups:

Users for which the absolute numbers are important – this may be in terms of allocating funds from central government under the Barnett formula, planning services, health services and providing a base for population and housing projections.
Users for which the population figures are used as denominators, for example, calculating weights for survey data, birth and death rates for population projections and the calculation of social and economic indicators.

3. Accuracy and Reliability

The proximity between an estimate and the unknown true value.

Population estimates are produced using information from several data sources including the previous census and administrative registers. The data sources used are deemed to be the best that are available nationally, however, the estimates are therefore subject to the coverage and error associated with these data sources. A full quality assurance of the data sources which contribute to the mid-year population estimates is available from the administrative data quality document.

Migration is the most difficult component of population change to measure and therefore a source of potential inaccuracy in the estimates. Migration inflows are estimated from the Medical Card Register, which is a list of patients registered with a family doctor. It is recognised that the Medical Card Register is deficient in recording young adult males; therefore, the age distribution of young adult males is adjusted to be similar to the young adult female distribution.

Similarly, migration outflows are measured from the Medical Card Register. Previous research has shown that not all outflows are measured fully by the Medical Card Register and therefore de-registrations (outflows) are scaled up by an additional 67 per cent (i.e. the assumption is that only 3 out of 5 persons who leave Northern Ireland to go abroad deregister with their family GP). As with inflows, it is recognised that the administrative data is deficient in recording young adult males, therefore the age distribution of young adult males is adjusted to be similar to the young adult female distribution.

The decennial census population estimates form the baseline for mid-year population estimates going forward. As each year from the baseline passes the accuracy of the population estimates slightly diminishes. However, the release of the census every 10 years offers the best opportunity to review the population estimates and revise their accuracy. The last review and rebasing of the population estimates was undertaken after the release of the 2021 census results. Details on the accuracy of the population estimates between 2011 and 2021 have been outlined in the Rebased 2011-2021 Mid-year Population Estimates statistical bulletin.

Consideration should be given to the constraining practices used in the production of mid-year estimates. Although estimates for Local Government Districts within Northern Ireland are produced from the cohort component method, the overall population totals for these areas are constrained to the established Northern Ireland total. As a result, this constraining process inherently means that any inaccuracies in the Northern Ireland population estimate will affect the sub national geographies. Additionally, although mid-year population estimates are available unrounded, estimates should not be taken with this level of accuracy. At best, the precision of the population estimates could be considered to be no better than to the nearest 100.

4. Timeliness and Punctuality

Timeliness refers to the time gap between publication and the reference period. Punctuality refers to the gap between planned and actual publication dates.

Mid-year population estimates for Northern Ireland are usually published annually in June each year. For a particular mid-year (30 June) they are usually available roughly 12 months after the reference date. This time lag reflects the availability of the data sources that measure the components of population change over the year and the time required to process data and calculate estimates. In a census year, publication is dependent on census figures being published and so publication will be later than June of the following year.

The publication schedule for the Population and Migration statistics branch of NISRA is available online and details all planned publication dates 12 months in advance. This schedule can be found on the population statistics section of the NISRA website.

In addition, a preannouncement on all statistics is made on Gov.uk detailing the exact date of publication four weeks in advance.

All statistical publications have been released to the planned publication schedule set out at the beginning of the year.

In the unlikely event of a change to the preannounced release schedule, public attention would be drawn to the change and the reasons for the change explained fully, as set out in the Code of Practice for Official Statistics.

5. Accessibility and Clarity

Accessibility is the ease with which users are able to access the data, also reflecting the format in which the data are available and the availability of supporting information. Clarity refers to the quality and sufficiency of the metadata, illustrations and accompanying advice.

Mid-year Population Estimates are available, free of charge, online from the Mid-Year Population Estimates section of the NISRA website. Links from the GOV.UK release calendar also provide the release date and location of each new set of population estimates four weeks in advance of publication.

The main statistical bulletin is available on the Mid-Year Population Estimates section of the NISRA website. Likewise, supporting tables and figures throughout the report are available to download.

As well as the main statistical bulletin the NISRA website hosts a number of data files in Excel format for each of the Northern Ireland geographies which can be downloaded. In addition, detailed data are now published in usable formats (.CSV) as part of the open data initiative on the NISRA Data Portal. Associated metadata accompanies the data files which details information in relation to variables, timeframes, coverage and methodology.

Users with any further queries can contact the responsible statistician by phone (028 9025 5156) or email (census.nisra@.gov.uk).

6. Coherence and Comparability

Coherence is the degree to which data that are derived from different sources or methods, but refer to the same topic, are similar. Comparability is the degree to which data can be compared over time and domain.

Population estimates for Northern Ireland are compiled and published by the Northern Ireland Statistics and Research Agency. The Office for National Statistics (ONS) are responsible for producing population estimates for England and Wales, with estimates for Scotland being produced by National Records of Scotland (NRS). Population estimates for each of the UK constituent countries are compiled using a common methodological approach and aim to be as consistent as possible.

Further information on the comparisons between UK population estimates can be found in the report: Consistency of methods used for population statistics across the UK countries.

The mid-year population estimates are consistent across all outputs in their reference period, running from mid-year to mid-year. However, depending on the geography in question the time series available may begin in mid-1971, mid-1991, mid-2001 or mid-2021. Therefore, not all geographies are comparable across the same number of years; details of the time series available for each geography are detailed within the accompanying metadata.

The mid-year population estimates provide data on components of population change which may overlap with other NISRA outputs. The coherence of these data can be affected by both reporting periods and context.

Firstly, the Long Term International Migration publication which is usually published in August each year also reports on migration figures for Northern Ireland. However, the focus of the Long-Term International Migration publication is to present alternative administrative data sources which assist with the measurement and quality assurance of international migration inflows to, and outflows from, Northern Ireland. These data are derived from the medical card register and other sources, however, comparisons with the official migration figures should not be made. This is because the migration data used in the Long-Term International Migration estimates refer to a specific subset of the medical card register only.

In addition, the adjustments made to the mid-year estimates migration figures to account for an underrepresentation of males and international outflows (see accuracy and reliability) have not been made to the Long-Term International Migration estimates. In relation to reporting period, Long-Term International Migration estimates are reported on quarterly and by calendar year rather than the mid-year to mid-year reporting period for population estimates.

Estimates of births and deaths used to calculate population estimates and reported on in the components of population change refer to those births and deaths which occur from mid-year to mid-year, irrespective of when registered. These estimates differ to those reported by NISRA Vital Statistics in terms of reporting period, with Vital Statistics reporting births and deaths both quarterly and annually.

Mid-year population estimates are usually produced in June by single year of age from 0 to 89 and 90+. The 90 and over age group are aggregated into a collective. The Estimates of the Population Aged 85 and over, have been incorporated in the Mid-Year Estimates rather than produced as a separate publication since mid-2023. This provides users with estimates of the population aged 90 to 104 by single year of age and sex. To produce these estimates NISRA has adopted the Kannisto-Thatcher Survivor Ratio Method, a completely separate methodology than the cohort component and ratio change methods used for mid-year estimates. Users should take note of the different methods used to produce these two population estimates when conducting any further analysis. Some overlap does exist between the two outputs as the estimates for those aged 85 to 89 in the Estimates of the Population Aged 85 and over publication are taken directly from the published mid-year estimates.

Useful links:

7. Trade-offs between output quality components

Trade-offs are the extent to which different aspects of quality are balanced against each other.

The mid-year estimates are published unrounded, by sex and single year of age, to enable users to carry out further analysis. However, in general the precision of the estimates could be considered to be no better than to the nearest 100.

Further information on the methodology used to create population estimates is available within the methodology report.

8. Assessment of user needs and perceptions

The process for finding out about users and uses, and their views on the statistical products.

Information on users’ needs for, and perceptions of, the population estimates are collected by:

User surveys, for example, the latest population and migration statistics user feedback survey was undertaken for 2018/19. The user feedback survey allows our users to comment on existing outputs and put forward changes in their requirements. The results of the latest user feedback survey have been published.
Contact with individual users – drawing on the evidence provided by the many users who contact the Population and Migration Statistics team with requests for, or queries on, the estimates and projections.
User groups, such as the Demographic Statistics Advisory Group, which allows the Population and Migration Statistics team to consult with personnel who represent the interests of the main user communities.
User engagement event – our most recent user engagement event was held in February 2020 and details of this event can be found on the stakeholder engagement section of the NISRA website.

Enquiries and suggestions

Accessibility contact

Please contact Dissemination Branch for assistance with accessibility requirements or alternative formats. Contact details are:

Email: info@nisra.gov.uk

Telephone: +44 (0)300 200 7836

Dissemination Branch
NISRA
Colby House
Stranmillis Court
BELFAST
BT9 5RR