Article ID: | iaor1994885 |
Country: | United Kingdom |
Volume: | 42 |
Issue: | 1 |
Start Page Number: | 63 |
End Page Number: | 83 |
Publication Date: | Jan 1993 |
Journal: | Applied Statistics |
Authors: | Narendranathan Wiji, Stewart Mark B. |
Unemployment durations are generally modelled by using survival analysis. In the past, in Britain, all such studies have not only used very restrictive parametric specifications of the hazard functions, most commonly Weibull in form, but also only modelled unemployment durations without distinguishing the nature of the exit. These restrictions potentially bias the estimated effects, particularly those of the time varying economic variables and the base-line hazard. When the authors use semiparametric methods to estimate models with completely unrestricted base-line hazards, they find the restrictions implied by the Weibull specification to be rejected for Britain. The authors then use a competing risks model to distinguish exit into a job from other exits. They find that the single-risk model of exit understates the effects of income in and out of work on the probability of entering a job.