Identifying and monitoring vulnerable groups in the European Union Labour Force Survey 2018 Explanatory note including STATA-do-files and the R code, Deliverable 11.3 & 13.1

The aim of this paper is twofold: first it shows how the identification of seven vulnerable labour market groups in the 2018 European Union Labour Force Survey (EU-LFS) is possible. These groups include age, gender identity, sexual orientation, single parenthood, migration (ethnicity, nationality, and migration status), religion, and disability. Second, it presents a study on how statistically reliable indicators can be obtained for a selection of those identified vulnerable groups. For the first identification part, the exercise showed that the sample size of the vulnerable group is largely dependent on the operationalisation utilised. Several of the vulnerable groups included straightforward definitions that are widely agreed on and correspond well with items in the EU-LFS. For other groups, such as disability and migrant status, the sample size varied widely based on operationalisation used to identify respondents. Age and gender identity all provide for straightforward identification with sizeable sample sizes. Sexual orientation was limited to same-sex couples living in the same household, which faced additional restrictions like anonymisation and limited detailed household data. Identification of single parenthood depended on the age cut off for children in the household, as the EU-LFS defines a dependent child in a way that deviates from research norms. Identifying disability and migrant status also provided difficult as there is not a single operationalisation for either and identification has to be done indirectly. There was no measurement for religion. Additionally, we find issues with removing duplicate responses from the EU-LFS as repeat sampling varies at the country level and there are no consistent identifiers for both household and individuals in all countries In the second part, the use of Small Area Estimation methods was proved to be useful for obtaining reliable estimates of some selected vulnerable groups indicators based on the EU-LFS 2018 data.