Flexible Modelling of Duration of Unemployment Using Functional Hazard Models and Penalized Splines: A Case Study Comparing Germany and the UK

Abstract

The intention of this paper is to demonstrate the flexibility and capacity of penalized spline smoothing as estimation routine for modelling duration time data. We investigate the unemployment behaviour in Germany and the UK between 1995 and 2005 based on data from national panel studies. Functional duration time models are used to investigate the dynamics of covariate effects. The focus of our analysis is on contrasting the two economies. The statistical model being employed is built upon the hazard function, where we allow all covariate effects to vary smoothly with time. As result of the analyses, we demonstrate that the most striking difference between the countries is that elderly unemployed in Germany have decreasing chances for reemployment compared to the UK.