Weighting LFS survey data to get population based estimates

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. Each case is given a weight which can be thought of as the number of people that case represents. This weighting factor takes account of differential non-response among different sub-groups in the population. This weighting procedure involves grossing data to sub-regional population estimates and then adjusting for the estimated age and sex composition, by region.

These weighting factors are provided to HSE by the Office for National Statistics (ONS) along with the LFS dataset itself.

Typically, prior to the coronavirus pandemic, the ONS would revise the LFS weights every two years to reflect the latest population estimates and projections, incorporating any changes to the level and composition of the UK population.

However, the coronavirus (COVID-19) pandemic led to practical challenges for all national statistical institutes in collecting survey information. One example is that household surveys could no longer be conducted in a face-to-face environment. As the LFS transitioned to a telephone only approach, ONS found that certain characteristics were not as well represented as in earlier surveys, introducing an increased non-response bias to the survey. Given this, from 2020, various changes were made to the ONS weighting methodology. These adjustments reflected the challenges in conducting household surveys and measuring population change through a pandemic. For further details on the reweighting during the pandemic see Impact of reweighting on Labour Force Survey key indicators - Office for National Statistics (ons.gov.uk).

Following on from the 2021 Census for England and Wales, in November 2023 ONS published updated 2022 mid-year population estimates for England and Wales and combined them with population estimates for Scotland and Northern Ireland to produce updated UK population projections. The LFS has been reweighted using these updated projections, improving the representativeness of the survey. Additionally, the ONS used other data from the Census to update and improve the assumptions underlying some of their weighting methods and calibration. Impact of reweighting on Labour Force Survey key indicators - Office for National Statistics.

Due to time constraints, ONS have only been able to reweight the LFS estimates from the period July to September 2022, but are planning a further reweighting exercise based on the latest population projections published in January 2024. This will cover the period back to 2019. More information can be found in Labour market transformation – update on progress and plans - Office for National Statistics.

Whilst the ONS provided weighting factors take account of non-response to the LFS itself, they do not account for non-response to individual questions within it, in particular the Workplace Injury and SWI survey modules' screening questions. In 2001/02, just over 5% of eligible respondents did not respond to either or both of the screening questions within the workplace injury and SWI survey modules (most of whom were unavailable for interview); in recent years this has increased to around 19%. Since this non-response is not accounted for in the standard LFS weighting procedure, an adjustment is made to the weights to take account of this non-response and provide more reliable estimates.

For the non-response adjustments a procedure is implemented to identify demographic and employment-related variables and codes that best describe the pattern of response to the ill health and workplace injury screening questions. The procedure progressively splits the sample into groups between which the response rates differ to a statistically significant extent. The adjustment for non-response then involves multiplying the standard LFS weights by the reciprocal of the response rate within each of the groups identified.

When ONS update the LFS weights, any revisions made to the work-related illness and workplace injury published estimates are noted in the revision log.to reference of footnote 3