Correcting for time series breaks in the Swedish Labour Force Survey at the micro level – combining models and calibration

The Swedish Labour Force Survey (LFS) is the foundation for official statistics on the Swedish labour market. As from 2021, it must comply with the new EU framework regulation on social statistics. To this end, several changes were made to the survey, both regarding the population and the questionnaire. Moreover, the auxiliary information used in the estimation was revised at the same time. The combined effect of these changes caused breaks in many of the LFS time series. To estimate and correct for the breaks in the LFS time series, Statistics Sweden performed a parallel run with both the old and the new questionnaires during 2021. In this paper, we describe how the parallel run was complemented with other available data to analyse the breaks in the time series. Moreover, using a combination of imputation models for the micro data and calibration, we derive recalibrated weights for all the LFS respondents during 2005–2020. These recalibrated weights constitute a link at the micro level between the old and new procedures. Time series derived using the recalibrated weights and the imputed microdata are fully comparable over time with time series calculated using the new procedure from 2021 and on.