Labour Force Survey (LFS) QMI

• Statistical designation: accredited official statistics

• Survey name: Labour Force Survey (LFS)

• Data collection: quarterly

• Frequency: quarterly

• How compiled: longitudinal sample survey

• Geographic coverage: Great Britain and UK

• Related publications: Labour market overview, UK

This quality and methodology information report contains information on the quality characteristics of the data, including the European Statistical System's five dimensions of quality, as well as the methods used to create it.

The information in this report will help you to:

• understand the strengths and limitations of the data

• learn about existing uses and users of the data

• understand the methods used to create the data

• help you to decide suitable uses for the data

• reduce the risk of misusing data

• The Labour Force Survey (LFS) is a study of the employment circumstances of the UK population; it is the largest household study in the UK and provides the official measures of employment and unemployment.

• The survey covers a range of topics including work, unemployment, education and training, income from work and benefits, and health.

• Output from the LFS is quarterly since 1992; the sample is currently made up of approximately 25,000 responding UK households and 55,000 individuals per quarter, as of Quarter 2 (Apr to June) 2024.

• Respondents are interviewed for five successive waves at three-monthly intervals, and 20% of the sample is replaced every quarter; data collection is conducted via face-to-face at Wave 1, and then followed up by telephone at further waves.

• Employment estimates from the LFS are currently published in our monthly Labour market overview, UK bulletins.

• LFS quarterly datasets are provided to government departments and are available to approved researchers through our Secure Research Service (SRS); the UK Data Archive also provides non-disclosive data for public access.

Overview

The main purpose of the Labour Force Survey (LFS) is to provide good quality point-in-time and change estimates for various labour market outputs and related topics. The "labour market" covers all aspects of people's work, including the education and training needed to equip them for work, the jobs themselves, job search for those out of work, and income from work and benefits. Volume 1 of our Labour Force Survey – user guidance provides survey background and methodology.

Uses and users

Users of LFS data often combine them with related data from other sources to provide an overall view of the state of the labour market. One of the most important users of this sort of assessment is the Bank of England's Monetary Policy Committee. Other important users of LFS data are HM Treasury and the Department for Work and Pensions. They are interested in a variety of indicators of the state of the labour market, including the number of people in employment, the number of hours worked, and the number of unemployed people, defined according to the International Labour Organization (ILO). They often analyse these series by age groups, by regions, and by gender.

Other government users include:

• Department for Business and Trade
• Home Office
• Health and Safety Executive
• Department for Transport
• Scottish Government
• Welsh Government

At the international level, LFS data are used by the Organisation for Economic Co-operation and Development (OECD) and the International Labour Organization (ILO).

Other users include:

• local authorities
• Trades Union Congress (TUC)
• Confederation of British Industry
• Institute for Employment Studies
• The Institute of Public Policy Research
• National Institute of Economic and Social Research
• Policy Studies Institute
• Institute for Fiscal Studies
• employers' associations
• academic researchers
• media
• general public

Strengths and limitations

The main strengths of the LFS are:

• it has the largest sample size of any household survey and can generate robust statistics at regional level

• the sampling errors are small, because the LFS has a single-stage, random sample of addresses

• the survey covers a large range of employment-related variables and non-employment-related variables, allowing for cross-linking analyses (earnings against educational attainment, for example)

The main limitations of the LFS are:

• the sample design provides no guarantee of adequate coverage of any industry, because the survey is not stratified by type of industry

• it omits communal establishments, except NHS housing and students in boarding schools and halls of residence, though the relevant sample frame has not been updated since it started

• members of the armed forces are only included if they live in private accommodation

• workers aged 16 years or under are not covered

Recent improvements

Transformation of the Labour Force Survey

We began a transformation programme in 2014 to address the recommendations from the National Statistics Quality Review of the LFS. After a series of large-scale quantitative tests, the Transformed Labour Force Survey (TLFS) was launched in March 2020, in response to the coronavirus (COVID-19) pandemic. More information on the design of this experimental survey can be found in our Transformed Labour Force Survey – user guidance methodology. Further updates on the transformation and transition from the current LFS to the new TLFS can be found in our Labour market transformation – update on progress and plans articles.

Relevance

Relevance is the degree to which the survey meets users' needs.

The main Labour Force Survey (LFS) measures include economic activity and inactivity, all aspects of people's work, job search for the unemployed, education and training, and income from work and benefits. See Volume 2 of our Labour Force Survey - user guidance for all LFS measures.

The LFS runs on a calendar quarter basis: Quarter 1 (Jan to Mar), Quarter 2 (Apr to June), Quarter 3 (July to Sept), Quarter 4 (Oct to Dec). It consists of a sample of approximately 25,000 responding UK households per quarter. Each quarter's sample is made up of five waves. Respondents are interviewed for five successive waves at three-monthly intervals. Approximately 20% of the sample is replaced every quarter. The LFS is intended to be representative of the entire population of the UK. Note that the sample design excludes most communal establishments.

Accuracy and reliability

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

The main threats to the accuracy of the data are sampling error and non-sampling error. Non-sampling error includes coverage error, non-response error, measurement error, and processing error. 

Many of the sources of non-sampling error are difficult to measure. However, in our LFS performance and quality monitoring (PQM) reports, detailed response rates for all waves of the survey are published, as well as an overall response rate, including time series. Response rates by region (formerly Government Office Region) for each wave during the quarter, proxy response rates, response rates for income questions by National Statistics (NS) Socio-economic Classification and attrition rates are also published in our PQM reports.

Surveys like the LFS provide estimates of population characteristics, rather than exact measures. In principle, many random samples could be drawn, and each would give different results, because each sample is made up of different people who give different answers to the questions asked. The spread of these results is the sampling variability, which generally reduces with increasing sample size. Confidence intervals are used to present the sampling variability. For example, with a 95% confidence interval, it is expected that in 95% of the survey samples, the resulting confidence interval will contain the true value that would be obtained by surveying the whole population.

Estimates of quarterly change should be treated with additional caution because of increased volatility of LFS estimates, resulting from smaller achieved sample sizes. We recommend using them as part of our suite of labour market indicators, alongside Workforce Jobs, Claimant Count data, and Pay As You Earn (PAYE) Real Time Information (RTI) estimates.

In our LFS PQM reports, we routinely publish details of achieved sample sizes, in terms of achieved number of household and person interviews, as well as our sampling variability for estimates of key variables, where it is expected that in 95% of samples the range would contain the true value. The sampling variability gives the range above and below the estimate at a 95% confidence interval. Our PQM reports also note changes to the LFS questionnaire and resulting outputs.

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 LFS began in 1973, and it was carried out every two years until 1983. Between 1984 and 1991, data were collected annually. The survey has been running in its present form, with quarterly sampling, since spring 1992, with a change from seasonal to calendar quarters in 2006.

The LFS is one of several sources of data about the labour market. Some sources provide data that overlap with LFS data on employment, unemployment, and earnings. Our Comparison of Labour Market data sources methodology includes the strengths and limitations of each source, in relation to these topics.

Both the LFS and Pay As You Earn (PAYE) Real Time Information (RTI) provide measures of people who are working. PAYE RTI includes employees who are being paid through the PAYE system through company payroll, while the LFS employment includes all forms of employment. A respondent self-defines their employment status as either employee or self-employed on the LFS. Some of those who are actually paid through payroll might classify themselves as self-employed, as they own the business. There are further definitional and methodological differences between LFS and PAYE RTI.

There are several data sources on earnings. Average weekly earnings (AWE) is our lead indicator of short-term changes in earnings. The Annual Survey of Hours and Earnings (ASHE) is our main measure of earnings in terms of structural statistics. It provides information about the levels, distribution and make-up of earnings and hours paid for employees in most industries and occupations across the UK.

The LFS also collects information on the earnings of employees. While the earnings data are known to be underestimated in the LFS, they are a useful source of breakdowns not available in our other sources, such as by ethnicity and education. Further information on the sources of data on income and earnings can be found in our Income and earnings statistics guide.

Accessibility and clarity

Accessibility is the ease with which users can 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.

Analysts wishing to conduct analysis of LFS data can apply for access to LFS microdata through various routes. There are different routes for different types of data user.

General public

• Nomis provides highly disaggregated data for local areas using Annual Population Survey (APS) data that are available free to the public.
• The UK Data Archive End User License provides a comprehensive dataset containing non-disclosive variables.

Those with Accredited Researcher status

• Our Secure Research Service (SRS) provides the opportunity to conduct detailed analysis, in a controlled environment.
• The UK Data Archive Special Licence provides the opportunity to conduct analysis of selected variables through datasets downloaded by the applicant.

The LFS Data Advice and Relations team provides advice and can also provide some ad hoc analysis of data for a fee. They can be contacted by phone at +44 1633 455329 or email at socialsurveys@ons.gov.uk.

For information about conditions of access to data, please refer to our Terms and conditions for data on the website, and our Accessibility statement.

Timeliness and punctuality

Timeliness refers to the lapse of time between data collection and data delivery. Punctuality refers to the gap between planned and actual data delivery dates.

The main labour market statistics are published in our monthly Labour market overview, UK bulletins, first published in April 1998. They focus on the International Labour Organization (ILO) measure of unemployment, as measured by the LFS, instead of the administrative Claimant Count measure. Our bulletins draw together statistics from a range of sources to give a more coherent picture of the labour market. The Claimant Count is not an alternative measure of unemployment.

LFS results are published on a UK-basis, six weeks after the end of the survey period, and relate to the average of the latest three-month period.

Since April 1998, the Northern Ireland Statistics and Research Agency (NISRA) has published a Northern Ireland Labour Market Statistics Release to the same timetable as publication of our Labour market overview bulletins.

Publication takes place strictly in accordance with published release dates for labour market statistics, following the Code of Practice for Statistics. Between 1998 and 2023, the publication date had typically never been missed. However, we were facing the challenge of decreasing response rates for household surveys, as were other comparable countries. This issue became more acute for the LFS data collected for August 2023. The LFS estimates expected to be published in October 2023 were suspended because of quality concerns, with planned improvements made to data collection and methodology, as explained in our LFS: planned improvements and its reintroduction methodology.

Timeliness on a continuous survey like the LFS should be carefully compared with surveys or administrative series that report on a point or only part of the reference period, particularly because of issues with discontinuities in the data. For more information, see Volume 1 of our Labour Force Survey - user guidance.

The historical frequency of LFS data output is:

• 1973 to 1983; biennial

• 1984 to 1991; annual

• 1992 to 2006; seasonal quarters (December to February, March to May, June to August, September to November

• 2006 to 2020; calendar quarters (January to March, April to June, July to September, October to December)

• January 2020 to March 2022; rolling quarters (January to March, February to April, March to May, and so on)

• April 2022 to present; calendar quarters (January to March, April to June, July to September, October to December)

For more details on related releases, see our Release calendar, which 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.

Concepts and definitions

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

The definitions of the three economic activity groups (employed, unemployed and economically inactive) that are used in the LFS are the standard ILO definitions.

The economically active are defined as those aged 16 years or over who are either employed or unemployed in the survey reference week.

The employed are defined as those aged 16 years or over who are in employment. The employed are those who did at least one hour of work in the reference week as an employee, as self-employed, as unpaid workers in a family business, or as participants in government-supported training schemes, and those who had a job that they were temporarily away from (for example, if they are on holiday). Unpaid family workers also belong to the employed category and are those who are doing unpaid work in a family business.

The unemployed are defined as those aged 16 years or over who are without work, have actively sought work in the last four weeks and are available to start work in the next two weeks, or are out of work, but have found a job and are waiting to start it within the next two weeks.

The economically inactive are defined as those aged 16 years or over who are neither in employment nor unemployed. This group includes, for example, all those who are looking after a home or family, have a long-term illness or disability that prevents them working, or are retired.

Why you can trust our data

The ONS is the UK's largest independent producer of statistics and its national statistical iInstitute. Our data policies detail how data are collected, secured, and used in the publication of statistics. We treat the data that we hold with respect, keeping it secure and confidential. We use statistical methods that are professional, ethical, and transparent.

Statistical disclosure control methodology is also applied to the LFS data. This ensures that information attributable to an individual is not disclosed in any publication, and that confidentiality of respondents is protected in datasets. Principle 5: Confidentiality of the Code of Practice for Statistics describes the practices for protecting data from being disclosed. The Statistics and Registration Service Act 2007 includes data confidentiality regulations that apply to the ONS. More information about disclosure control for survey microdata is available in our Policy for social survey microdata.

Main data sources

The Labour Force Survey (LFS) covers private households, including people who are temporarily absent. The resident population includes people who regard the sample address as their main address, and those who have lived in the dwelling for more than six consecutive months, even if they do not regard it as their principal dwelling. People absent for more than six months are not regarded as members of the resident population.

A private household comprises one or more people whose main residence is the same dwelling and/or who share at least one meal per day. Students living in boarding schools and halls of residence are sampled through the private households of their parents. In Great Britain, an additional sample is drawn from a bespoke sampling frame that covers people living in NHS accommodation. 

The LFS survey year is divided into quarters of 13 weeks. Before January 2006, these were seasonal quarters: winter (December to February), spring (March to May), summer (June to August), and autumn (September to November). Since January 2006, the LFS has been conducted on the basis of calendar quarters: Quarter 1 (Jan to Mar), Quarter 2 (Apr to June), Quarter 3 (July to Sept), and Quarter 4 (Oct to Dec). The change to calendar quarters was in response to the European Union Regulation 1 on the conduct of continuous labour force surveys in all member states. This was continued after the UK left the European Union in 2020.

Between January 2020 and March 2022, during the coronavirus (COVID-19) pandemic, the LFS produced rolling monthly quarter datasets. These were January to March, February to April, March to May, and so on. This production ended with the March 2022 to April 2022 quarter, and the LFS reverted to producing datasets on a calendar quarter basis.

Sampling

Four different sampling frames are used in the UK LFS. Great Britain is split into two areas. These are south of the Caledonian Canal, comprising all of England, Wales, and most of Scotland, and north of the Caledonian Canal in Scotland. Northern Ireland has its own sampling frame. A separate list of NHS housing in Great Britain is in place, which was developed in 1992.

For most of Great Britain, the sampling frame is the Royal Mail's Postcode Address File (PAF), a database of all addresses receiving mail. The list is limited to addresses receiving relatively few items of post per day, to exclude businesses. Because of the very low population density in the far north of Scotland (north of the Caledonian Canal), telephone directories are used as sampling frames and interviews are carried out by telephone, because face-to-face interviews are too expensive. In Northern Ireland, the Northern Ireland Statistics and Research Agency (NISRA) Address Register is used, which is taken from the Land and Property Services (LPS) Pointer Address Database.

In Great Britain, a systematic sample is drawn from the three sampling bases each quarter. This yields approximately 16,640 PAF addresses, 80 telephone numbers for the north of Scotland, and 9 units of NHS housing. As of October 2023, the sample size was increased to 25,800 PAF addresses because of improvement measures that were implemented. As the PAF is broken down geographically, the systematic sampling ensures that the sample is representative at the regional level.

In Northern Ireland, a simple random sample is drawn each quarter from each of the three strata, giving 650 addresses in all. Additionally, 260 additional ("booster") new addresses are added to the sample in Quarter 2 of each year and these are spread equally across the five waves.

Because of two changes made to the design in 2010 mean LFS samples in Great Britain and Northern Ireland are strictly no longer equal probability samples, although the effect of the changes is relatively small. These changes relate to multiple occupancy addresses and to households that have only adults aged 75 years or over.

The first change was from the Quarter 3 2010 survey, only one household has been selected for interview where there was more than one household present at the sampled address. The selection of that household was carried out randomly, using random numbers. When the selection process was introduced in 2010, it helped harmonise our social surveys. The effect of the change was that any such household had a lower probability of selection, so it receives a higher weight and then no further waves of interviews are conducted.

When telephone interviewing was introduced for Wave 1 at the start of the pandemic, this random selection became logistically more difficult because interviewers were unable to visit sampled addresses until coronavirus lockdown measures were eased. Since lockdown measures ended, the approach was changed to interview the first household where contact was made at a sampled address. As the numbers of such instances is small, this approach was acceptable, because it would make very little statistical difference to the overall sample quality.

The second change in sample design was also introduced for Quarter 3 2010 interviews. If a household only has adults aged 75 years or over, then no further waves of interviews are conducted.

This amendment had an immediate effect from its introduction. For example, if a household of all occupants aged 75 years or over was found in any wave in Quarter 2 2010, then no interview was conducted in Quarter 3 2010, or any subsequent quarters. Further details of these changes can be found in Volume 1 of our Labour Force Survey – user guidance.

For the most part, the LFS is a single-stage sample of households each quarter. However, changes made in 2010 mean this is no longer strictly the case. The geographical ordering of the frame implicitly stratifies the sample, ensuring a geographic spread of addresses. Since all adults in a household are sampled, the person-level survey may be regarded as mainly a one-stage cluster sample of people, with the clusters (or primary sampling units) being the households.

Data collection

The LFS uses a rotation system of five waves. Respondents are interviewed five times at 13-week intervals, and one-fifth of the sample is replaced each quarter according to the rotation design. The majority of Wave 1 interviews are typically face-to-face, with the help of portable computers, known as Computer Assisted Personal Interviews (CAPI). North of the Caledonian Canal in Scotland, interviews are carried out by telephone, known as Computer Assisted Telephone Interviews (CATI). This is for around 10% to 20% of interviews in Wave 1 from January 2011, and for all interviews in Waves 2 to 5, wherever possible.

From March 2020, during the coronavirus lockdowns, Wave 1 face-to-face data collection was suspended and moved to telephone mode collection. Tele-matching, used for north of the Caledonian Canal cases, was extended to Great Britain to obtain additional telephone numbers for Wave 1 cases. During October 2023, in-home interviewing was reintroduced and promoted by field interviewers as the primary completion mode. Telephone mode is still an alternative completion mode, if the respondent prefers it. Further details of the methodology used in the LFS can be found in Volume 1 of our Labour Force Survey – user guidance.

Proxy response

The LFS must complete fieldwork to a tight timetable and interview as many of the sampled households as possible. This leaves limited time for recalls. LFS interviewers try to interview every adult aged 16 years or over in each sampled household. However, when a household member is unavailable for interview, interviewers accept information by proxy from another responsible adult in the household. The proxy respondents are normally people living with a partner who respond on behalf of their partner, and parents who respond on behalf of their adult offspring who live with them, who are at boarding school, or who are in university halls of residence.

How we process the data

The data are validated and cleaned, variables are derived, and weights are applied. As the LFS collects information on a sample of the population, the data are weighted to enable inferences to be made from this sample to the entire population.

Method of weighting

The LFS uses calibration weighting to assign a calibration weight to each responding individual. These calibration weights are set to sum to a set of calibration totals within a calibration group. For example, the weights of all males aged 18 years in an LFS dataset (a calibration group) will sum to the population total of eligible males aged 18 years in the UK (a calibration total) at the time the survey was taken. Calibration weighting typically involves calculating a design weight, adjusting for non-response, and finally, calibration to population totals.

The LFS assigns a calibration weight to all responding or imputed individuals, but does not assign a weight to individuals whose economic activity is unknown, so non-responders do not get a weight. Standard LFS practice in the case of individuals dropping out between waves is to roll their data forward by one quarter. This is a form of imputation and these individuals receive a weight.

Further details on the production of LFS statistics and weighting methodology and can be found in Volume 1 of our Labour Force Survey – user guidance.

At certain points in time, we release revised population estimates. The LFS conducts reweighting exercises, and rereleases of data and labour market estimates.

Before the pandemic, a typical reweighting exercise for the LFS was to take on the latest subnational population projections. In recent years, the weighting approach for the LFS has had to incorporate tactical methodological changes. These changes reflect the challenges of conducting household surveys and measuring population change through a pandemic. In particular, the enforced change from face-to-face interviewing to telephone interviewing led to an increase in non-response bias in survey responses.

Alongside the changes to the sample and data collection, changes were made to the LFS weighting from 2020 onwards to mitigate these bias risks. The latest reweighting exercise was applied to the July 2022 to December 2023 data. This incorporated the latest estimates of size and composition of the population available at the time and increased the representativeness of the LFS person-level data. More information can be found in our Impact of reweighting on LFS key indicators: 2024 article.

Imputation

If a household is unavailable for interview, but was interviewed in the previous wave, responses from the previous wave are rolled forward. This is referred to as "imputation". Imputation is carried out to minimise non-response bias in estimates and improve precision by boosting the sample size. The rationale is that most LFS variables do not change from one quarter to another for most people. Responses are rolled forward for one wave only. Data are not rolled forward after a second consecutive non-response.

Tables and charts at person or household level that contain responses that have been rolled forward from the previous wave are denoted by the term "including imputed" in our LFS performance and quality monitoring (PQM) report. Tables and charts that do not contain responses that have been rolled forward from the previous wave are denoted by the term "excluding imputed".

LFS household datasets include household members who did not respond to the current wave of interviewing, but their household did. In cases where no proxy information was collected for these people, or where no information was collected for them in the previous wave, their data are imputed with reference to responders with similar personal characteristics (for example, age, sex, and economic status).

Method of calculating income response rates

The income question is asked at Wave 1 and Wave 5 only. Individuals aged 16 to 69 years who are in employment in the reference week form the subset of respondents who are eligible for these questions. A reference week includes information about respondents' activities in a seven-day period that ends on a Sunday. The percentage response rates for the income questions are based on all eligible in-scope respondents at Wave 1 and all eligible in-scope respondents at Wave 5. The total response rate is the cumulative response rate for income for the quarter (Wave 1 and Wave 5), based on all eligible, in-scope respondents.

How we disseminate the data

We publish labour market data, including data from the LFS, every month. The data are widely available through a range of media and are generally free of charge. Our data, including time series data, are available in our Labour market overview, UK bulletins.

How we review and maintain our processes

We regularly seek the views of external and internal LFS stakeholders and sponsors and hold bi-monthly working group consultation meetings to assist with reviewing the survey content and processes. The LFS research team also works closely with our Secure Research Services (SRS) team and the UK Data Service (UKDS) to ensure that wider external user views are considered. The LFS Survey Manager attends the Household and Labour Market Division (HLMD) quarterly liaison meeting with key external stakeholders. The LFS team routinely consults with internal users of the LFS.