Constrained parametric model for simultaneous inference of two cumulative incidence functions
Article first published online: 23 OCT 2012
© 2012 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim
Volume 55, Issue 1, pages 82–96, January 2013
How to Cite
Shi, H., Cheng, Y. and Jeong, J.-H. (2013), Constrained parametric model for simultaneous inference of two cumulative incidence functions. Biom. J., 55: 82–96. doi: 10.1002/bimj.201200011
- Issue published online: 7 JAN 2013
- Article first published online: 23 OCT 2012
- Manuscript Accepted: 20 AUG 2012
- Manuscript Revised: 15 AUG 2012
- Manuscript Received: 7 JAN 2012
- NSF. Grant Numbers: 0906449, 1207711
- National Health Institute (NIH). Grant Numbers: 5-U10-CA69974-09, 5-U10-CA69651-11
Disclaimer: Supplementary materials have been peer-reviewed but not copyedited.
Table S1 Simulation results on censoring time following a proportional odds model; the data were simulated from the modified logistic or Gompertz base with a proportional subdistribution hazard transformation (LOG+PSH and GOM+PSH) or with a generalized odds-rate transformation (LOG + GOR and GOM + GOR); referring to Table 1 for the definition of AVE, MSE, ESE, and Cov.
Table S2 Simulation results where the data were simulated from our proposed modified logistic (panel LOG + PSH) or Gompertz model (panel GOM + PSH) with complimentary log–log transformation or with generalized odds-rate transformation (panels LOG + GOR and GOM + GOR) with sample size n=500 and 40% censoring rate, where AVE is the average of the estimates, MSE is the average of the model-based standard errors, ESE is the empirical standard error, and Cov is the coverage rates of the 95% Wald confidence intervals.
Please note: Wiley Blackwell is not responsible for the content or functionality of any supporting information supplied by the authors. Any queries (other than missing content) should be directed to the corresponding author for the article.