Weighting LFS survey data to get population based estimates

The LFS collects information from a sample of the population. To produce estimates for the population as a whole, survey responses are weighted. Each respondent is assigned a weight representing the number of people in the population that they represent. The weighting process is designed to improve the representativeness of the survey and calibrates estimates to population totals by age, sex and region.

These weighting factors are provided to HSE by the Office for National Statistics (ONS) as part of the LFS dataset. Whilst these weights account for non-response to the survey itself, they do not account for non-response to individual survey questions, including the screening questions used in the Workplace Injury and SWI survey modules. In 2025/26, around 15% of eligible respondents did not provide a response to one or both of these screening questions, the majority because they were unavailable for interview. As this item non-response is not addressed by the standard LFS weighting procedure, an additional adjustment is applied to reduce potential bias and improve the reliability of estimates of workplace injury and work-related ill health.

The adjustment is based on differences in response rates to the Workplace Injury and SWI screening questions across groups of respondents defined by demographic and employment-related characteristics. A CHAID (Chi-squared Automatic Interaction Detection) decision-tree procedure is used to identify groups with statistically significant differences in response rates. The standard LFS weight is then multiplied by the reciprocal of the response rate for the group to which each respondent belongs.

LFS estimates for January to March 2019 onwards are currently weighted using population estimates and projections that incorporate information from the 2021 Census for England and Wales, the 2022 Census for Scotland, updated estimates of international migration, and other recent demographic information. For further details see Impact of reweighting on Labour Force Survey key indicators - Office for National Statistics. Estimates prior to January to March 2019 continue to use the weighting methodology and population estimates available at the time.

A more comprehensive reweighting of the Labour Force Survey is expected to be implemented by ONS in November 2026 and is expected to revise estimates back to 2011. Any resulting revisions to estimates of workplace injury and work-related ill health will be incorporated in the next update to these statistics, currently scheduled for autumn 2027.

Is this page useful?

Updated 2026-11-04