Skip to main content
Fig. 3 | BMC Medical Research Methodology

Fig. 3

From: The importance of censoring in competing risks analysis of the subdistribution hazard

Fig. 3

Simulations: differential censoring by age. Empirical bias (top; with 95% confidence interval), standard deviation (middle) and relative mean-squared error (bottom) of the estimate subdistribution hazard ratio (SHR) from Fine–Gray models with four different censoring estimates: pooled (model 1), separated by age (model 2), separated by treatment (model 3) and separated by age and treatment (model 4). Simulated data had a 10% risk of censoring due to loss to follow-up in young patients, and a censoring hazard ratio of 2.7 for older patients. The true exposure effect was zero in the left-hand column and a SHR of 2.7 in the right-hand column

Back to article page