This paper uses tight parametric assumptions to model individual unemployment
histories in a structural form. Starting from a simple search model it is shown
that individual spells are distributed exponentially with different hazard rates
for different individuals. In contrast to the usual reduced form approach the
choice of the reservation wage is directly incorporated into the analysis. In
effect, a log—linear simultaneous equations system is derived that explains both
reservation wages and elapsed spell durations of currently unemployed individuals
in terms of exogeneous variables. Moreover, it is demonstrated that apart from
constant terms an identical structural form should be valid for accepted wages
and completed spell durations for individuals who are re-employed at the time of
the survey.
The empirical part of the paper uses data from the Federal Republic of Germany
to estimate the parameters of this structural form both for a subsample of
unemployed and a subsample of re-employed individuals. Evidence on the
performance of structural search models was previously provided only for
currently unemployed individuals by the studies by Kiefer/Neumann (1979),
Lancaster (1985), and Jones (1988). This study is therefore the first to provide
evidence for re-employed individuals. Furthermore it is the first of its kind to
investigate German data. In this paper the main emphasis is given to the
robustness of the estimation results across subsamples, not to the formulation
of formal tests for the validity of cross—subsample restrictions. The resulting
evidence is mainly favorable, and the paper concludes with an extensive
discussion of merits and remaining deficiencies of the proposed model.

We propose a new econometric estimation method for analyzing the probability of leaving unemployment
using uncompleted spells from repeated cross-section data, which can be especially
useful when panel data are not available. The proposed method-of-moments-based estimator
has two important features: (1) it estimates the exit probability at the individual level and (2)
it does not rely on the stationarity assumption of the inflow composition. We illustrate and
gauge the performance of the proposed estimator using the Spanish Labor Force Survey data,
and analyze the changes in distribution of unemployment between the 1980s and 1990s during
a period of labor market reform. We find that the relative probability of leaving unemployment
of the short-term unemployed versus the long-term unemployed becomes significantly higher in
the 1990s.