This paper examines the relation between individual unemployment durations and incidence on the one hand, and the time-varying macroeconomic conditions in the economy on the other. We allow for calendar time effects acting on the exit probabilities for all currently unemployed. We also allow for the composition of the inflow into unemployment to depend on calendar time at the moment of inflow. In both cases we distinguish between business cycle effects and seasonal effects. We apply the model to aggregate unemployment duration data, in which we allow for unobserved heterogeneity and correlated measurement errors. We do not make parametric assumptions on the genuine duration dependence pattern or the unobserved heterogeneity distribution. The results enable us to give a complete decomposition of the dynamics of unemployment over calendar time. This is also used to test the popular ranking model of unemployment.
Downloads: (external link) http://www.cepr.org/pubs/dps/DP1202.asp (application/pdf)
CEPR Discussion Papers are free to download for our researchers, subscribers and members. If you fall into one of these categories but have trouble downloading our papers, please contact us at firstname.lastname@example.org