A major issue in the analysis of unemployment durations concerns disti
nguishing genuine duration dependence of the exit rate out of unemploy
ment from unobserved heterogeneity. We present a method for the nonpar
ametric estimation of both phenomena, designed to be applicable to tim
e-series data on aggregate outflows from different duration classes. T
he model explicitly takes into account that individual exit rates are
affected by the business cycle and by seasonal effects. The method is
applied to U.S. data. We find diverging duration effects among black a
nd white individuals. However, except for white males, duration depend
ence is dominated by unobserved heterogeneity.