Unemployment duration and competing risks: A regional investigation

This paper presents empirical findings by applying a duration analysis and competing risks models (CRM) to Lombardy’s labour force survey for 2004 and 2005. CR and duration models are becoming increasingly pervasive in applied research to explain the factors determining both the time in a state (i.e. unemployment) and the exit route from the state (i.e. leaving unemployment for a job or non-participation).Starting from a description of the main features and findings on unemployment duration for European countries we add empirical evidence for the Italian context. For a sample of 823 individuals experiencing unemployment we obtain useful insights on the baseline hazard by applying nonparametric estimation of the survivor function and we estimate four different parametric models within which the Weibull one provides the best fit to the duration data. We find evidence of negative duration dependence and higher hazards of leaving unemployment for married, younger and better educated males. Then, by considering four different competing causes, we estimate CR models to investigate what the characteristics are which drive transitions out of unemployment. Males again present higher employment probabilities, while a consistent proportion of females leave the labour force after a joblessness experience, signalling the presence of a discouragement effect. These findings renew the importance of the kind of analysis conducted, mainly from a policy perspective.