Title: The proportional odds cumulative incidence model for competing risks
Authors: Frank Eriksson - University of Copenhagen (Denmark) [presenting]
Thomas Scheike - University of Copenhagen (Denmark)
Li Jianing - Medical College of Wisconsin (United States)
Zhang Mei-Jie - Medical College of Wisconsin (United States)
Abstract: An estimator for the proportional odds cumulative incidence model for competing risks data is suggested. The key advantage of this model is that the regression parameters have the simple and useful odds ratio interpretation. The model has been considered by many authors, but it is rarely used in practice due to the lack of reliable estimation procedures. Such procedures are suggested and it is shown that their performance improve considerably on existing methods. A goodness-of-fit test for the proportional odds assumption is also suggested. The large sample properties are derived and estimators of the asymptotic variance are provided. The method is illustrated by an application in a bone marrow transplant study.