1. Methodology background


 National Statistic   
 Survey name  Population by country of birth and nationality QMI
 Frequency  Annually
 How compiled  Sample-based survey
 Geographic coverage  UK
 Sample size  300,000
 Last revised  30 November 2021

Back to table of contents

2. Important points

  • The Annual Population Survey (APS), which is the Labour Force Survey (LFS) plus various sample boosts, is a household survey and so does not cover most people living in communal establishments, some NHS accommodation, or students living in halls of residence who have non-UK resident parents.

  • As a result of this, the population totals used in APS and LFS estimates of the UK population by country of birth and nationality are not directly comparable with Office for National Statistics mid-year population estimates, which refer to the entire UK population.

  • All estimates produced are subject to sampling variability – confidence intervals are used as a measure of the precision of the estimate.

  • Estimates of the UK population by country of birth and nationality are not directly comparable with estimates of long-term international migration (measured using the International Passenger Survey (IPS)) because of the definitional differences between the two surveys; for example, the APS is a survey of residential addresses and does not include most communal establishments whereas the IPS does include people who may live in communal establishments.

Back to table of contents

3. Overview

Population by country of birth and nationality is an annual publication accompanied by a statistical report. The data are published five months after the end of the reference period.

The published tables are accompanied by datasets containing estimates by individual country of birth and nationality down to local authority level.

The population by country of birth and nationality tables are used by central and local government for planning and monitoring service delivery, policy development, resource allocation and managing the economy.

Back to table of contents

4. Output quality

This report provides a range of information that describes the quality of the output and details any points that should be noted when using the output.

We have developed Guidelines for Measuring Statistical Quality; these are based upon the five European Statistical System (ESS) Quality Dimensions. This report addresses these quality dimensions and other important quality characteristics, which are:

  • relevance
  • timeliness and punctuality
  • coherence and comparability
  • accuracy
  • output quality trade-offs
  • assessment of user needs and perceptions
  • accessibility and clarity

More information is provided about these quality dimensions in the following sections.

Back to table of contents

5. About the output

Relevance

(The degree to which the statistical outputs meet users’ needs.)

The estimates are produced using the Annual Population Survey (APS) (PDF, 839KB), which (other than the census and Census Coverage Survey) is the largest household survey in the UK. It is constructed from the Labour Force Survey (LFS) plus various boosts that increase the size of the sample. The main purpose of the LFS is to provide information on the UK labour market. However, the LFS also includes data on a variety of other variables such as country of birth and nationality.

The population by country of birth and nationality tables published are:

  • Table 1.1: Population in the UK, excluding some residents in communal establishments, by country of birth; UK by countries and, within England, London boroughs, metropolitan districts, unitary authorities and non-metropolitan districts; and unitary authorities within Wales
  • Table 1.2: Population in the UK, excluding some residents in communal establishments, aged 16 to 64 years, by country of birth; UK by countries and, within England, London boroughs, metropolitan districts, unitary authorities and non-metropolitan districts; and unitary authorities within Wales
  • Table 1.3: Overseas-born population in the UK, excluding some residents in communal establishments, by sex, by country of birth; 60 most common countries of birth
  • Table 1.4: Overseas-born population in the UK, excluding some residents in communal establishments, by country of birth; five most common countries of birth
  • Table 1.5: Overseas-born population in the UK, excluding some residents in communal establishments, by main reason for migration
  • Table 1.6: Overseas-born population in the UK, excluding some residents in communal establishments, by nationality held; 60 most common countries of birth
  • Table 2.1: Population in the UK, excluding some residents in communal establishments, by nationality; UK by countries and, within England, London boroughs, metropolitan districts, unitary authorities and non-metropolitan districts; and unitary authorities within Wales
  • Table 2.2: Population in the UK, excluding some residents in communal establishments, aged 16 to 64 years, by nationality; UK by countries and, within England, London boroughs, metropolitan districts, unitary authorities and non-metropolitan districts; and unitary authorities within Wales
  • Table 2.3: Non-British population in the UK, excluding some residents in communal establishments, by sex, by nationality; 60 most common nationalities
  • Table 2.4: Non-British population in the UK, excluding some residents in communal establishments, by nationality; five most common nationalities
  • Table 2.5: Non-British population in the UK, excluding some residents in communal establishments, by main reason for migration
  • Table 2.6: Non-British population in the UK, excluding some residents in communal establishments, by country of birth; 60 most common nationalities

The published tables are accompanied by datasets containing estimates by individual country of birth and nationality down to local authority level.

There is significant interest in statistics on the population of the UK and there is a need to understand how it impacts on society and the economy. The population by country of birth and nationality tables are used by central and local government for planning and monitoring service delivery, policy development, resource allocation and managing the economy. Users can contact migstatsunit@ons.gov.uk with further requests for data not supplied in the published tables.

This output is released with International Migration – terms, definitions and frequently asked questions, which provides background information on the data, as well as the limitations in comparing the data with other sources. It is also published alongside other aspects of migration in a migration indicator tool once a year in August, enabling users to observe local migration patterns at local authority level. Figures presented in this tool show the number of residents who are non-UK born and non-British nationals.

Timeliness and punctuality

(Timeliness refers to the lapse of time between publication and the period to which the data refer. Punctuality refers to the gap between planned and actual publication dates.)

Estimates of the UK population by country of birth and nationality were published each quarter until August 2012, but following a consultation exercise were moved to an annual publication accompanied by a statistical report (see Assessment of user needs and perceptions). However, user requirements have changed, following a consultation exercise in December 2016, with requests for more frequent, timely data. Therefore, the data are now published twice a year, in May (calendar year data) and November (mid-year data), which is five months after the end of the reference period (previously data were published eight months after the reference period).

For more details on related releases see the Migration statistics first time user guide and the GOV.UK release calendar provides 12 months’ advance notice of release dates. If there are any changes to the pre-announced release schedule, public attention will be drawn to the change and the reasons for the change will be explained fully at the same time, as set out in the Code of Practice for Statistics.

Back to table of contents

6. How the output is created

The Annual Population Survey (APS), Labour Force Survey (LFS) plus various local area sample “boosts” to increase the sample size) ensures minimum representation of each area of the UK in the sample. Boost interviews are conducted throughout the year and included in the APS dataset in the quarter in which they are conducted. Respondents in the LFS boost are interviewed only once a year, for four consecutive years. Only in the main LFS do interviews take place each quarter.

The LFS is a household survey of people in the UK. It includes those deemed resident at private addresses, so covers students in halls of residence with parents resident in the UK. However, it does not cover most communal establishments. Its purpose is to provide information on the UK labour market but it includes data on a variety of other variables such as country of birth and nationality. For a more comprehensive estimate of the UK population, please refer to Office for National Statistics’ official population estimates.

Each quarter’s LFS sample of 40,000 households is made up from five “waves”, each of approximately 8,000 households. Each wave is interviewed in five successive quarters, such that in any one quarter, one wave will be receiving their first interview, one wave their second and so on, with one wave receiving their fifth and final interview. Thus, there is an 80% overlap in the samples for each successive quarter and the sample is completely different after six quarters.

In some areas of the UK, the sample boost makes up the bulk of the APS dataset with a smaller contribution from the main LFS. The sample boost has a four-year wave structure instead of the five-quarter wave structure in the main LFS; after the initial interview, sampled households are interviewed three more times on an annual basis. Therefore, the sample boost for these areas may be slower to react to a change in migration patterns than the main LFS and the speed with which the APS sample responds to changes in the household population may vary across the UK.

The APS combines results from the LFS and the English, Welsh and Scottish Labour Force Survey sample boosts. During 2004 and 2005, the APS also included an additional sample boost for England. Northern Ireland does not have an additional boost. More robust estimates are available by using the APS than from the main LFS. APS datasets are produced quarterly with each dataset containing 12 months of data. There are approximately 300,000 persons per dataset.

The relevant APS dataset is then used to create the estimates and confidence intervals on population in the UK by country of birth and nationality, by using certain variables to calculate the estimates and confidence intervals to publish in the tables (see About the output for a list of the tables published).

For further information on statistical quality and data collection methods within the LFS and APS, please see the Quality and Methodology Information documents for the LFS and the APS.

Back to table of contents

7. Validation and quality assurance

Accuracy

Accuracy is the degree of closeness between an estimate and the true value.

In March 2015, the Annual Population Survey (APS) was reweighted using revised UK and subnational population estimates consistent with the 2011 Census. In July 2015, the Office for National Statistics (ONS) published reweighted estimates of the UK population by country of birth and nationality for calendar years 2004 to 2013. A comparisons paper has been written looking at the differences between the old estimates and the reweighted estimates (PDF, 199KB). The reweighting caused the estimate of the population of the UK to increase by 538,000 between 2004 and 2013.

In 2020, the coronavirus (COVID-19) pandemic led to operational changes being made to the Labour Force Survey (LFS). Alongside the general impact the coronavirus had on the population, these changes resulted in higher non-response from those who rent their accommodation and those with a non-UK country of birth or nationality. This left them less well represented in the achieved sample. The LFS weighting methodology was also using population projections that predated the pandemic and are therefore not able to reflect the demographic and structural impact the UK has faced.

In July 2021, the LFS was reweighted. This reweighting introduced controls for housing tenure and country of birth (UK, EU and non-EU) from January 2020 onwards, as detailed in Coronavirus and its impact on the Labour Force Survey. Reweighting of the LFS and APS has made the estimates for UK, EU and non-EU more robust, but there remains a high level of uncertainty for data below this level. Changes in estimates below EU or non-EU level are likely to reflect the fact that the methodological changes were not targeted at this detailed level, and therefore numbers should not be compared against previous years.

This means that all estimates from the July 2019 to June 2020 edition of this dataset onwards use the new Labour Force Survey weighting methodology, which provides further information on the method used to reweight the LFS.

As estimates of the UK population by country of birth and nationality are based on sample surveys, all estimates produced are subject to sampling variability. This is because the sample selected is only one of a large number of possible samples that could have been drawn from the population. Estimates produced from a sample survey vary according to the specific characteristics of the respondents that have been sampled. Non-response by age, sex, and region (as well as country of birth (UK, EU, non-EU) and housing tenure in 2020) is accounted for through the weighting of the dataset, when calibrated to UK population totals. In 2020, the weighting also included a non-response adjustment using factors based on local area level information from the 2011 Census. However, other variables cannot be accounted for in this way.

Confidence intervals are commonly used as indicators of the extent to which the estimate based on a sample differs from the true population value; the larger the confidence interval, the less precise the estimate is. Confidence intervals are shown next to the estimates.

A confidence interval provides an estimated range of values in which an actual data value is likely to fall. The confidence interval provided is a 95% interval. This means that, across the dataset as a whole, the confidence intervals are expected to contain the true values around 95% of the time (for example, 95 out of 100 times it would contain that value, 5 out of 100 times it would not). It is obtained as:

1.96 x standard error

Before publication, suppression techniques are used in the tables for disclosure control purposes. As a rule, if there have been fewer than three contacts used to create an estimate, then the figures will be suppressed.

Symbols used to denote suppression in the publication

  • . No contact: This value is used where the APS has had no contact with any resident with a particular country of birth or nationality.
  • : Not available: This value is used where estimates for a geographical area are not available in the source data.
  • z Not applicable: This value is used for estimates which are not determined by random sampling so that the concept of confidence interval does not apply.
  • c Not available because of disclosure control: This value is used where an estimate cannot be disclosed due to confidentiality reasons, as there have been less than three APS contacts.
  • 0~ Rounded to zero: This value is used where an estimate or a confidence interval rounds to zero. All estimates and confidence intervals in these tables are rounded to the nearest thousand, so 0~ (zero tilde) indicates that the unrounded value is less than 500.

The published tables are accompanied by datasheets containing estimates by individual country of birth and nationality down to Local Authority level, and follow the same suppression techniques.

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, for example, geographic level.

The population totals used in APS and Labour Force Survey (LFS) estimates of the UK population by country of birth and nationality are not directly comparable with the mid-year estimates. Office for National Statistics (ONS) mid-year estimates refer to the entire UK population. The APS and LFS population totals include only those living in private households and omit those living in most types of communal establishments. In August 2017, ONS published research outputs by ethnicity, country of birth and nationality that matched the UK population total from the ONS mid-year estimates publication. These three new tables provide data by local authority for ethnic group, UK and non-UK born, and British and non-British nationals.

It is important to note that all figures contained in the population by country of birth and nationality publication refer to estimates from the APS and do not refer to any data collected as part of the 2011 Census. ONS have released a report on detailed country of birth and nationality analysis from the 2011 Census of England and Wales. Findings from this report are similar to findings from the APS data.

Further data from the 2011 Census is available. A discussion on the differences between these data and estimates of Long-Term International Migration can be found in the report: Note on the differences between Long-Term International Migration flows derived from the International Passenger Survey and estimates of the population obtained from the Annual Population Survey: December 2016.

There are many sources of official statistics about international migration to and from the UK, each valuable in its own right in measuring particular aspects of international migration. Comparing sources of international migration statistics outlines the differences between the data sources and points to more detailed articles regarding this.

International sources of data that can be used to compare with the population by country of birth and nationality figures.

External data sources to compare to published population by country of birth and nationality

Potential sources of data and their comparability with the ONS’ estimates

Eurostat

Eurostat publish tables on EU country residents by country of birth and nationality.

The ONS supplies Eurostat with data for the following variables:

  • country of birth by age and sex
  • nationality by age and sex

These are statistically adjusted by the ONS to match the mid-year estimate population totals, which include the population living in communal establishments. They are then combined with data supplied by other European countries to populate the Eurostat tables.

United Nations

The United Nations Statistics Division (UNSD) collects and disseminates statistics on the stock of migrant population through the Demographic Yearbook data collection system.

The UNSD collects data from national statistical authorities using a set of questionnaires that are sent to over 230 national statistical offices.

Introducing the Annual Population Survey

The APS was introduced in 2004 as a further improvement to the local LFS. A similar survey existed from 2000 to 2003 as an enhancement to the LFS to help improve labour market information at a local level. The APS then enhanced this for 2004 onwards by boosting the sample further in the urban areas of England in order to improve the sample of the economically active. Therefore, annual estimates from 2000 onwards can be directly compared with one another. However, before 2000, only the quarterly LFS can be used to estimate the population by country of birth or nationality.

In the APS before 2007, many small countries were grouped together to form "Other” country groupings, such as "Other Asia” and "Other Africa”. It was decided that these would be excluded from the most common list of countries of birth and nationalities produced in this release, as it is unclear how each ”Other” estimate is divided between the individual countries in these categories.

At the start of 2007, the list of countries of birth and nationalities was expanded to produce a longer list of countries, with fewer put into "Other” categories. This has meant that a country may appear in the most common list of countries of birth or nationality for the first time in the 2007 period because it has no longer been placed in an “Other” category.

Back to table of contents

8. Concepts and definitions

(Concepts and definitions describe the legislation governing the output and a description of the classifications used in the output.)

Nationality refers to that stated by the respondent during the interview. Country of birth is the country in which they were born. It is possible that an individual’s nationality may change, but the respondent’s country of birth cannot change (the list of countries includes those that are now obsolete, for example, Yugoslavia). This means that country of birth gives a more robust estimate of the resident population change over time.

There are three main reasons for differences between nationality and country of birth. These are:

  • when people born abroad decide to remain in the UK, they often apply to become British nationals
  • that some people born abroad have British nationality. For example, this may be the case for that people whose parents were in the military services and were based abroad when they were born
  • some people born in the UK to migrant parents take the nationality of their parents

Countries and country groupings used in the publication

UK or British

UK born includes Guernsey, Jersey, Isle of Man, and Channel Islands Not Otherwise Specified. British nationals additionally include Anguilla, Bermuda, British Indian Ocean Territory, British Virgin Islands, Cayman Islands, Falkland Islands, Gibraltar, Montserrat, Pitcairn, Henderson, Ducie and Oeno Islands, South Georgia and The South Sandwich Islands, St Helena, and Turks and Caicos Islands.

European Union 27 (EU27)

These are all of the countries of the EU, as constituted between 1 January 2007 and 1 July 2013, with the exception of the UK. They include the EU14, EU8 and EU2 groups plus Cyprus, Malta, and Croatia (from 1 July 2013 when it joined the EU).

European Union 14 (EU14)

These are the countries of the EU, as constituted between 1 January 1995 and 1 May 2004, with the exception of the UK (Austria, Belgium, Denmark, Finland, France, Germany, Greece, Italy, Luxembourg, the Netherlands, Portugal, Republic of Ireland, Spain and Sweden).

European Union 8 (EU8)

These are the eight Central and Eastern European countries that acceded to the EU on 1 May 2004 (Czech Republic, Estonia, Hungary, Latvia, Lithuania, Poland, Slovakia and Slovenia).

European Union 2 (EU2)

These are the two countries that acceded to the EU on 1 January 2007 (Bulgaria and Romania).

Non-European Union

This is defined as all those countries not in the UK or EU27 groups. This group excludes Croatia from 1 July 2013 when it joined the EU. Estimates are given for the group as a whole and also split geographically.

Where a respondent has dual nationality the first one stated by the respondent is recorded.

Back to table of contents

9. Other information

Output quality trade-offs

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

Estimates of the UK population by country of birth and nationality were published each quarter until August 2012, but following a consultation exercise were moved to an annual publication accompanied by a statistical report (see Assessment of user needs and perceptions). However, user requirements have changed, with requests for more frequent, timely data following a consultation exercise in December 2016. Therefore, the data are now published twice a year, in May (calendar year data) and November (mid-year data), which is five months after the end of the reference period (previously data was published eight months after the reference period).

Assessment of user needs and perceptions

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

Office for National Statistics (ONS) regularly consults with users to gather insight and seek views on the presentation and timing of our international migration and population publications.

The consultation on international migration outputs ran from 11 November 2016 until 23 December 2016. It was held to gather insight and seek user views on the presentation and timing of the published international migration statistics outputs, specifically considering which outputs are used, why and what other data sources users would like to see published.

There were a number of themes running through the consultation responses for all outputs:

  • overall users were broadly happy with the range of data sources and statistics published although gaps were identified when requested
  • there was strong support for a more coherent narrative bringing together the different sources to present a comprehensive picture of international migration in the UK
  • there was broad support for shorter quarterly reports with more detailed annual or topic-specific reports or articles
  • respondents emphasised that all underlying data should continue to be provided regularly

Our main conclusions to note from the consultation responses and our next steps are:

  • international migration statistics are used for a wide range of purposes
  • ONS and the Home Office began to move to shorter more streamlined quarterly publications from 2017
  • ONS will continue to publish short-term international migration estimates and look to improve coverage and timeliness
  • work to implement changes to redesign migration products that meet user needs as much as possible began in the round of publications in May 2017

Overall, there were some clear differences in users’ needs, suggesting that a suite of products, which can support the main MSQR bulletin, is needed.

The previous consultation on the reporting of international migration statistics ran from 20 June 2014 to 18 July 2014. The main findings were requests for a shorter bulletin, more information on the reliability of migration estimates and for ONS to announce short stories in advance of publication.

Users also requested a single web page that could provide links to all migration-related data. The international migration landing page on our website has been developed and now does this.

The consultation on country groupings ran from 21 January 2014 to 18 March 2014. As a result of the consultation we now produce our quarterly International Passenger Survey (IPS) data tables to the new country groupings and in November 2015 we extended our 3-series tables to include data for the new country groupings. As of February 2016, we now included new country groupings in the 2-series tables too. In 2017, old country groupings were removed from published tables.

The Public Administration Select Committee (PASC) published a report in July 2013 on Migration Statistics (PDF, 967KB) following a review conducted in April 2013.

A previous consultation on international migration statistical outputs took place in 2012.

The main outcomes to this 2012 consultation were:

  • population by nationality and country of birth tables will no longer be updated quarterly, but will be published annually in August, to include figures referring to the previous calendar year
  • local area migration indicators will no longer be updated quarterly, but will be published annually in August
  • we should continue to publish quarterly data on international migration flows and the Migration Statistics Quarterly Report

We consult users on our statistical work programme every four years via the ONS website. The most recent ONS consultation was held between 13 December 2015 and 8 February 2016 and responses will be used to inform ONS’s work programme between 2016 and 2020.

Stakeholders were asked to provide information on what ONS outputs they use, how they use them and their views on the impact for them of possible reductions in various areas of ONS work following the 2015 Spending Review. The consultation confirmed there is widespread user support for main population statistics such as the Long-Term International Migration (LTIM) and International Passenger Survey (IPS) estimates. The results of this consultation are available.

The Migration Statistics Improvement Programme (MSIP) was a substantial programme that included taking forward the recommendations of the 2006 Inter-departmental Task Force on Migration Statistics and the more recent Treasury Select Committee report, Counting the Population. Phase 1 of MSIP ended in May 2010 and resulted in significant improvements to migration and population statistics including:

  • revised population estimates at local authority level for 2002 to 2008 based on improved model-based immigration estimates, including the use of timelier administrative data and an adjustment for student moves, pre- and post-university, based on new data
  • changes to the IPS sample to optimise it for migration, for example, by introducing new sites to reflect the changing flows of migration
  • published estimates of short-term migrants and publication of the Local Area Migration Indicators Suite
  • improved access to administrative data relevant to estimating migration including data from the Higher Education Statistics Agency
  • improved reporting through the production of Migration Statistics Quarterly Reports, which include migration data from other government departments

Phase 2 of the MSIP ran until March 2012. It consisted of three main workstreams:

  • reconciling administrative sources and population estimates
  • improving migrant distribution
  • statistical benefits of e-Borders

The MSIP team held a series of end-of-programme seminars to present research and findings to stakeholders and statistical users, to make sure they were fully engaged with the programme achievements. This series of seminars aimed to review the success of the programme and outlined plans for taking forward future improvements. More detail on the nature of each work stream, and information on the improvement programme is available.

Also, in 2009, the UK Statistics Authority has reported on Migration Statistics – The Way Ahead (PDF, 1.1MB) and the recommendations can be found in their report.

Back to table of contents

10. Sources for further information or advice

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 release details, illustrations and accompanying advice.)

The population by country of birth and nationality data and supporting information are available.

The estimates are available online from 2000. For data before 2000, further information is available from the Labour Market team, which can be contacted by phone (+44 (0)1633 455678) or by email (preferred): socialsurveys@ons.gov.uk

Our recommended format for accessible content is a combination of HTML webpages for narrative, charts and graphs, with data being provided in usable formats such as CSV and Excel. We also offer users the option to download the narrative in PDF format. In some instances, other software may be used, or may be available on request. For further information contact migstatsunit@ons.gov.uk

For information regarding conditions of access to data, please refer to the following links:

In addition to this Quality and Methodology Information, quality information relevant to each release is available in the relevant statistical bulletin.

Back to table of contents

Contact details for this Methodology

pop.info@ons.gov.uk
Telephone: +44 1329 444661

You might also be interested in: