Working Paper: NBER ID: w30979
Authors: Andreas I. Mueller; Johannes Spinnewijn
Abstract: This paper studies the predictability of long-term unemployment (LTU) using rich administrative data from Sweden. We establish substantial heterogeneity in LTU risk across individuals, accounting for both observed and unobserved heterogeneity using a wide range of observable predictors and multiple spell outcomes respectively. We apply our prediction algorithm to study the dynamics of job finding over the unemployment spell and the business cycle. Selection effects can explain most of the decline in average job finding over the unemployment spell, but little of its cyclicality. We also find sizeable heterogeneity in the profiles of job finding over the unemployment spell, but not so over the business cycle.
Keywords: long-term unemployment; predictability; heterogeneity; selection
JEL Codes: E24; J64; J68
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| Dynamic selection into long-term unemployment (J64) | Observed decline in job finding rates (J68) |
| Lower initial job finding probabilities (J68) | Greater declines in job finding rates (J68) |
| Within-individual changes (J62) | Cyclicality of long-term unemployment risk (J64) |
| Richer administrative data (C81) | Prediction accuracy (C52) |