Skip to content

variance estimator for the cumulative incidence function

3 messages · Pintilie, Melania, Thomas Lumley, Göran Broström

Pintilie, Melania
# 
Hi everyone,
I am using the package cmprsk in R to estimate the cumulative incidence
function and its variance. In the manual it is mentioned that the variance
is calculated based on Dr. Aalen's paper (1978, Nonparametric estimation of
partial transition probabilities in multiple decrement models). 

I would appreciate if someone could provide me with a source where the
variance is expressed in a more readable way, for example as a sum. 

I appreciate your help. 
Thank you. 



Melania
Rm 15-433, ext 4886

Fax: (416) 946-2048






This e-mail may contain confidential and/or privileged infor...{{dropped}}
Thomas Lumley
#
On Thu, 26 Feb 2004, Pintilie, Melania wrote:

            

      
      
      
    

        
It may well be that the simplest thing is to read the source code.
Survival analysis has pretty much moved to counting process notation.

	-thomas

  
  


  


      

    

    

      
      

        


  

        

      Göran Broström
    

    

      
      #
    

  


  

      
On Thu, Feb 26, 2004 at 07:48:40AM -0800, Thomas Lumley wrote:

            

      
      
      
    

        
One option is to check the old classic, Kalbfleisch & Prentice (1980),
"The Statistical Analysis of Failure Time Data", Wiley. If I remember
correctly, you'll find Greenwood's formula there for the log survivor 
function, which is what you want.