Characterizing Measurement Error in the German Socio-Economic Panel Using Linked Survey and Administrative Data

Abstract

This paper exploits the linkage of German administrative social security data (GER: Integrierte Erwerbsbiografien) and survey data from the socio-economic panel (GER: Sozio-ökonomisches Panel, SOEP) for the characterization of measurement error in metrics quantifying individual-specific labor earnings in Germany. We find that survey participants’ decision whether to consent to linkage is non-random based on observables. In that sense, the studied sample does not constitute a random sample of SOEP. Further, measurement error is not classical: we observe underreporting of income on average, autocorrelation, and non-zero correlation with the true signal and other observable characteristics. In levels, calculated reliability ratios above 0.94 hint at a relaitvely small attenuation bias in simple linear univariate regressions with earnings as the explanatory variable. For changes in income, i.e. first differences, the bias from measurement error is exacerbated.