[R] comparing SAS and R survival analysis with time-dependent covariates

Svetlana Eden svetlana.eden at Vanderbilt.Edu
Fri Dec 5 18:11:48 CET 2008


Thank you so much, this was very helpful.

Svetlana

Terry Therneau wrote:
>   This query of "why do SAS and S give different answers for Cox models" comes 
> up every so often.  The two most common reasons are that
>   	a. they are using different options for the ties
>   	b. the SAS and S data sets are slightly different.
> You have both errors.
>
> First, make sure I have the same data set by reading a common file, and then
> compare the results.
>
> tmt54% more sdata.txt
>  1   0.0  0.5     0       0
>  1   0.5  3.0     1       1
>  2   0.0  1.0     0       0
>  2   1.0  1.5     1       1
>  3   0.0  6.0     0       0
>  4   0.0  8.0     0       1
>  5   0.0  1.0     0       0
>  5   1.0  8.0     1       0
>  6   0.0 21.0     0       1
>  7   0.0  3.0     0       0
>  7   3.0 11.0     1       1
>
> tmt55% more test.sas
> options linesize=80;
>
> data trythis;
>     infile 'sdata.txt';
>     input id start end delir outcome;
>
> proc phreg data=trythis;
>   model (start, end)*outcome(0)=delir/ ties=discrete;
>
> proc phreg data=trythis;
>   model (start, end)*outcome(0)=delir/ ties=efron;
>
>
> tmt56% more test.r
> trythis <- read.table('sdata.txt',
>                       col.names=c("id", "start", "end", "delir", "outcome"))
>
> coxph(Surv(start, end, outcome) ~ delir, data=trythis, ties='exact')
> coxph(Surv(start, end, outcome) ~ delir, data=trythis, ties='efron')
>
> -----------------
>  I now get comparable answers.  Note that Cox's "exact partial likelihood" is 
> the correct form to use for discrete time data.  I labeled this as the 'exact' 
> method and SAS as the 'discrete' method.  The "exact marginal likelihood" of 
> Prentice et al, which SAS calls the 'exact' method is not implemented in S.
>  
>   As to which package is more reliable, I can only point to a set of formal test 
> cases that are found in Appendix E of the book by Therneau and Grambsch.  These 
> are small data sets where the coefficients, log-likelihood, residuals, etc have 
> all been worked out exactly in closed form.  R gets all of these test cases 
> right, SAS gets almost all.
>  
>  	Terry Therneau
>  	
> -----------------------------------------
> Svetlan Eden wrote
> Dear R-help,
>
> I was comparing SAS (I do not know what version it is) and R (version 
> 2.6.0 (2007-10-03) on Linux) survival analyses with time-dependent 
> covariates. The results differed significantly so I tried to understand 
> on a short example where I went wrong. The following example shows that 
> even when argument 'method' in R function coxph and argument 'ties' in 
> SAS procedure phreg are the same, the results of Cox regr.  are 
> different. This seems to happen when there are ties in the 
> events/covariates times.
>
> My question is what software, R or SAS, is more reliable for the 
> survival analysis with time-dependent covariates or if you could point 
> out a problem in the following example.
>
>  ...
>  
>
>
>



More information about the R-help mailing list