Flexible Modelling of Time to Failure in Risky Careers

Failure time models correcting for heterogeneity are used to explain the length of participation in a risky career. Using data from t he National Football League, the authors first employ a class of techniques whic h ignore unobserved heterogeneity; hence these methods impose severe restriction s on the estimated hazard. The authors then examine a second class of techniques which correct for unobserv-ables and thereby allow greater flexibility in the e stimated hazard. Within this second class, they find that the estimated hazard u sing the Burr-12 density is much more accurate than densities in the first class , which include the exponential and Weibull. They expect that this density could be employed to successfully explain career duration in other high-risk, high-st resscareers as well. Copyright 1986 by MIT Press.