CSB Working Paper, 2016, 2: Notes on updating the EU-SILC UDB sample design variables 2012-2014

Indicators based on EU-SILC should be accompanied by appropriate standard errors, and in order to do so, it is necessary to consider the sample design. Because important sample design variables are missing in the EU-SILC User Database (UDB), the aim of this note is to explain the update of EU-SILC UDB sample design variables for 2012 (version 4), 2013 (version 3) and 2014 (version 1), based on the methodology developed by Goedemé (2010b, 2013a). Although several of the challenges for reconstruct…

Indicators based on EU-SILC should be accompanied by appropriate standard errors, and in order to do so, it is necessary to consider the sample design. Because important sample design variables are missing in the EU-SILC User Database (UDB), the aim of this note is to explain the update of EU-SILC UDB sample design variables for 2012 (version 4), 2013 (version 3) and 2014 (version 1), based on the methodology developed by Goedemé (2010b, 2013a). Although several of the challenges for reconstructing the EU-SILC sample design variables are identical for all releases of the data, the update required minor adjustments in the computation of the new sample design variables psu1 and strata1. The effect of the use of the new sample design variables on standard errors is observed for ‘At risk of poverty’ and ‘Material deprivation’, for which SE values are found to be larger when the sample design variables are considered.