CPB: Predictability and (co-)incidence of labor and health shocks
Onderdeel van
Trefwoorden
This paper employs machine learning techniques to estimate the ex-ante probabilities that individuals will be confronted with adverse labor and health events. Using rich administrative data on the entire Dutch population, CPB documents that shock incidence is predictable especially in the labor domain and to a lesser degree in the domain of mental and physical health. Moving from ex-post incidence to ex-ante probabilities allows the organisation to separate predictable components of shocks, interpreted as ex-ante risk types, from random components. It brings together risk estimates for many different shocks and uncover that risk concurrence is sizable, monotone, non-linear and extended across domains. CPB shows that socioeconomic characteristics pertaining to employment status, educational attainment, migration background, income and wealth are overrepresented in the upper tails of the estimated risk distributions. Lastly, CPB discusses the implications of our findings for targeted prevention policies based on individual risk estimates, shock (co-)incidence and person characteristics.
@ CPB
Publicatie: CPB Discussion Paper 453 'Predictability and (co-)incidence of labor and health shocks' | CPB.nl
Afbeelding credits
Icon afbeelding: Icon - CPB