About the Labour Force Survey (LFS)

What is it?

The Labour Force Survey is a survey of households living at private addresses in the UK. Its purpose is to provide information on the UK labour market which can then be used to develop, manage, evaluate and report on labour market policies. The survey is managed by the Office for National Statistics in Great Britain and by the Central Survey Unit of the Northern Ireland Statistics and Research Agency (NISRA) in Northern Ireland on behalf of the Economic Labour Market Statistics Branch (ELMSB) of the Department of Finance and Personnel.

Since 1992, the LFS in Great Britain has run as a quarterly survey (1994/95 for Northern Ireland). The quarterly surveys have until spring 2006 operated on a seasonal quarter basis. However, mostly due to an EU requirement under regulation, in May 2006 the LFS moved to calendar quarters. The 2006/07 data is the first set of HSE data based on the LFS to be affected by this change. For more details about this change see 'Comparability of LFS data over time'.

How is it structured?

The LFS is intended to be representative of the whole population of the UK, and the sample design currently consists of around 23,000 responding households in every quarter. The quarterly survey has a panel design whereby households stay in the sample for five consecutive quarters (or waves), with a fifth of the sample replaced each quarter. Thus, there is an 80% overlap in the samples for each successive survey.

In response to the coronavirus (COVID-19) pandemic, the Office for National Statistics (ONS) made some changes to the LFS data collection and various refinements to the weighting1methodology. From March 2020 (with the onset of the coronavirus pandemic), face-to-face interviews for respondents newly joining the survey2were moved to telephone interviews. With a corresponding fall in response rates, the issued sample size for wave 1 was increased to maintain the achieved sample at the pre-pandemic level and a field strategy referred to as 'Knock and Nudge'3was introduced. As the survey transitioned to telephone only interviews, ONS found that certain characteristics were not as well represented as in earlier surveys, introducing an increased non-response bias to the survey. To address this, ONS implemented various improvements to the ONS weighting methodology during the coronavirus pandemic. For further details see Impact of reweighting on Labour Force Survey key indicators - Office for National Statistics (ons.gov.uk).

In line with other countries conducting household surveys, the LFS response rates have been falling in recent years, increasing sampling variability, and widening 95% confidence intervals around estimates. In response to this, ONS launched an improvement plan in late 2023 covering both data collection and methodological improvements. This has included reintroducing face-to-face interviews, boosting the sample size, increasing incentives for survey participation, and reweighting the LFS (from the period July-September 2022) using improved methods and more up-to-date population projection estimates. For more details see  Labour Force Survey: planned improvements and its reintroduction - Office for National Statistics and Impact of reweighting on Labour Force Survey key indicators - Office for National Statistics.

What are the participation levels?

In line with other countries conducting household surveys, the LFS response rates have been falling. The LFS household specific response rates were below 40% during the coronavirus pandemic (including information for earlier waves rolled forward for refusals) down from around 50% at the start of 2010. Response rates have continued to fall, dropping to less than 25% in recent data collections. More details about LFS response rates and other quality-related issues are available in the LFS Performance and Quality Monitoring Reports.

To increase the LFS response rates, in late 2023, ONS introduced an improvement plan. This has included reintroducing face-to-face wave 1 interviews (which were moved to telephone interviews at the onset of the coronavirus pandemic), boosting the sample size and increasing incentives for people who take part in the survey. For more details see  Labour Force Survey: planned improvements and its reintroduction - Office for National Statistics.

ONS are also looking at additional ways to improve the LFS response rates. However, the longer-term solution is moving to a transformed online-first version of the LFS which is being developed by the ONS. The ambition of the Transformed Labour Force Survey (TLFS) is to allow a more adaptive and responsive survey to meet user needs, enhance respondent experience and improve the quality of the labour market statistics. For more details see Labour Force Survey transformation - updates on progress and plans.

The LFS allows interviewers to take answers to questions by proxy if a respondent is unavailable. This is usually from another related adult who is a member of the same household. About a third of the LFS responses are collected by proxy, with variation in this proportion by age, sex, ethnicity and economic activity.

Dawe and Knight (1997)4showed that for many key variables the agreement between proxy informants and the same information given by the subjects themselves to be high - above 80%. However, for those variables requiring very detailed numerical information such as hours worked, agreement was found to be less satisfactory.

Based on 1993/94-2003/04 data, R.Davies et al5 showed that proxy respondents are 24% less likely than first person respondents to report the occurrence of a workplace injury. In terms of work-related illness, J R Jones et al6 reported that in 2004/05 proxies reported rather less work-related illness (3.6% of interviews) than first person respondents (5.3% of interviews). Likewise, based on 2001/02, 2003/04-2008/09 data restricted to individuals in work, R.Davies et al7 showed that spouses or partners acting as proxy respondents are 26% less likely than first person respondent to report suffering from a work-related illness. This increased where the proxy respondent was not a spouse or partner.  Whilst these differences may reflect the difficulty that a proxy respondent has in correctly providing this personal information, it may reflect a 'healthy worker' effect whereby the respondent is more likely to be away from home and their response correctly given by a proxy respondent. Because of this and other uncertainties (see Reliability of self-reported work-related illness), no adjustment is made in the data for proxy responses.

For more detailed background information on the LFS than is given here see 'The LFS User Guide Volume 1: Background and Methodology'.

How is the LFS being improved?

The Labour Force Survey is being transformed. ONS are working on radical plans to both streamline and improve the Labour Force Survey, to significantly increase the sample size and approach people in different ways, notably changing it to become an online-first survey, followed up by teams phoning households and knocking on doors in areas of low response, vastly increasing response rates. The transformed survey will allow for more robust estimates, as well as more granular breakdowns of the data. Updates on progress and plans can be found at Labour Force Survey transformation - updates on progress and plans.

Notes and references

  1. The LFS collects data on a sample of the population. To convert this information to give estimates for the population, the sample data is weighted. Back
  2. For the LFS, people are interviewed in five consecutive quarters, with the first interview (wave 1) generally being face-to-face. Back
  3. Interviewers visit sampled addresses where no telephone number can be obtained and encourage respondents to provide their phone number and arrange an appointment by knocking on the door. Back
  4. Dawe, F and Knight, I (1997): A Study of proxy response in the Labour Force Survey. Survey Methodology Bulletin (No. 40). Back
  5. Rhys Davies and Paul Jones (2005): Trends and context to rates of workplace injury. Back
  6. J R Jones MSc, C S Huxtable BSc and J T Hodgson MSc: Self-reported work-related illness in 2004/05: Results from the Labour Force Survey. Back
  7. Rhys Davies, Huw Lloyd-Williams and Emma Wadsworth: Analysis of the Correlates of Self-reported Work-related Illness in the Labour Force Survey . Back
Back to top

Is this page useful?

Updated 2024-11-13