Nonparametric Identication of Accelerated Failure Time Competing Risks Models

We provide new conditions for identi…cation of accelerated failure time competing risks models. These include Roy models and some auction models. In our set up, unknown regression functions and the joint survivor function of latent disturbance terms are all nonparametric. We show that this model is identi…ed given covariates that are independent of latent errors, provided that a certain rank condition is satis…ed. We present a simple example in which our rank condition for identi…cation is veri…ed. Our identi…cation strategy does not depend on identi…cation at in…nity or near zero, and it does not require exclusion assumptions. Given our identi…cation, we show estimation can be accomplished using sieves. Key Words: accelerated failure time models; competing risks; identi…ability. We would like to thank Xiaohong Chen for very helpful discussions at the early stage of this project. We also would like to thank Hidehiko Ichimura, Ivana Komunjer, Rosa Matzkin, Whitney Newey, Jean-Marc Robin, and Elie Tamer for helpful comments. Financial support from the Economic and Social Research Council for the ESRC Centre for Microdata Methods and Practice (RES-589-28-0001) and the small research grant (RES000-22-2761) is gratefully acknowledged.