Pseudo-observations for competing risks with covariate dependent censoring
- 622 Downloads
Regression analysis for competing risks data can be based on generalized estimating equations. For the case with right censored data, pseudo-values were proposed to solve the estimating equations. In this article we investigate robustness of the pseudo-values against violation of the assumption that the probability of not being lost to follow-up (un-censored) is independent of the covariates. Modified pseudo-values are proposed which rely on a correctly specified regression model for the censoring times. Bias and efficiency of these methods are compared in a simulation study. Further illustration of the differences is obtained in an application to bone marrow transplantation data and a corresponding sensitivity analysis.
KeywordsCompeting risks Covariate-dependent censoring Cumulative incidence Pseudo-observations
The research was supported by the Danish Natural Science Research Council [grant number 272-06-0442 “Point process modeling and statistical inference”]. We are grateful to CIBMTR for providing us with the example data [Public Health Service Grant/Cooperative Agreement No. U24-CA76518 from the National Cancer Institute (NCI), the National Heart, Lung and Blood Institute (NHLBI), and the National Institute of Allergy and Infectious Diseases (NIAID)].
- Gill RD (1980) Censoring and stochastic integrals. PhD thesis, Math. Centre Tracts 124. Mathematical Centre, AmsterdamGoogle Scholar
- Szydlo R, Goldman JM, Klein JP, Gale RP, Ash RC, Bach FH, Bradley BA, Casper JT, Flomenberg N, Gajewski JL et al (1997) Results of allogeneic bone marrow transplants for leukemia using donors other than HLA-identical siblings. J Clin Oncol 15(5):1767–1777Google Scholar