Rotation group bias in European Union social indicators

EU-SILC relies on a 4-wave rotating panel design. A new population sample is drawn every year and selected respondents are interviewed annually for up to four years. A complete EU-SILC cross-section dataset therefore contains data from samples drawn independently in four different years. This paper applies influence function regressions methods to examine to what extent the rotating panel design of EU-SILC influences the estimates of four social indicators such as income poverty rates or income inequality measures, in other words whether a “rotation group bias” is observed. Our analysis of the 2014 EU-SILC cross-sectional data highlights that estimates of income inequality and poverty rates for newer rotation groups are often higher than for older ones. Individuals interviewed at least twice (and especially those who have been three or more years in the sample) tend to drag the selected social indicators downwards, compared to individuals interviewed for the first time. These impacts remain significant even when accounting for different socio-demographic characteristics of households. Not all countries are affected by the bias however.