Abstract:
This paper is concerned with the analysis of the determinants of unemployment durations of French Young People. The data used are extracted from the Enquete Emploi 1990-1992 and the Module Jeunes 1992, both carried out by INSEE. A reduced form approach has been adopted and it is based on the estimation of a discrete-time hazard model which derives from the extension of the Cox model (1972) as in Prentice and Gloecker (1978). The baseline rate is piecewise constant in each interval of two months. A discrete-time hazard model with unobserved heterogeneity has been estimated, too. In it the unobserved heterogeneity has been modelled by means of a gamma distribution. Estimations have been performed separately on men and women durations. Various explanatory variables have been introduced in the analysis; they are significant in most cases, but their effects vary according the population of reference. The conditions to access the labour market will then seem to be very different for the two groups studied. Only the education level and the french nationality of the individual's father have a positive effect on the hazard rate of both the two subgroups studied. It is also worthwhile to remark that the variables introduced to take account for the date of entry in the unemployment spell, have a significant negative effect on the probability of leaving unemployment both for men and women showing that this is very sensitive to the economic situation.