On Omitted Variables, Proxies and Unobserved Effects in Analysis of Administrative Labour Market Data

Empirical research addresses omitted variable bias in regression analysis by means of various approaches. We present a framework that nests some of them and put it to German linked administrative labour market data. We find evidence for sizable omitted variable bias in a wage regression, while a labour market transition model appears to be less affected. Additional survey variables contribute only to the wage model, while the use of work history variables and panel models lead to changes in coefficients in the two models. Overall, unobserved effects panel data models with a restricted regressor set are found to control for more information than cross sectional analysis with an extended variable set.