A Hazard Model with Dynamic Unobserved Heterogeneity

Abstract

This paper identifies and estimates a hazard model in which the unobserved heterogeneity is modeled as a positive Levy stochastic process. The paper provides empirically relevant examples of such a model. Conditions for the identification of the parameters of interest and for the consistency of the sieve maximum likelihood estimators are given. Results of Monte Carlo simulations are presented.