A1071
Title: A single risk approach to the semiparametric copula competing risks model
Authors: Ming Sum Simon Lo - United Arab Emirates University (United Arab Emirates) [presenting]
Ralf Wilke - Copenhagen Business School (Denmark)
Abstract: A typical situation in competing risks analysis is that the researcher is only interested in a subset of risks and no distributional information is available about risks that are not of interest. A depending competing risks model is considered with one risk of interest that is known to have a (semi)parametric model, while the model for the other risk is unknown. Identifiability is shown for popular classes of models such as the accelerated failure time model and the semiparametric proportional hazards model. While the semiparametric model requires at least one covariate, the parametric model is identifiable with and without. Different estimation approaches are suggested which are shown to be $\sqrt{n}-$consistent. The applicability is demonstrated with the help of simulations and data examples.