how to get the confidence interval of difference in the survival rate at a given time point?

[SAS_John]

In OS table, we have the survival rate at each time point and the confidence interval of each of the two arms, but now we want to see the confidence interval in the survival rate difference. How to calculate the CI of the survival rate difference between two arms, say 5-year OS rate difference CI? Thank you very much! 

John

[SAS_John]

The data is as the followings
Time (Year) Trt (at risk) Trt Survival Rate Ctrl (at risk) Ctrl Survival Rate S Rate Difference
0 664 0 670 0 0
1 626 97.2 614 96.7 0.5
2 598 96.5 587 94.7 1.8
3 572 95.6 545 93.3 2.3
4 538 94.9 505 92.1 2.8
5 494 94.8 454 91.2 3.6

[SteveDenham]

A bit more information would help.  Which survival analysis PROC are you using?  All of them support a TEST statement, and most support the LSMEANS and LSMESTIMATE statement.

SteveDenham

[SAS_John]

Hi, Steve: Thanks for the response. I am using proc lifetest to generate the survival rate estimate and 95% CI for both trt and ctrl arms with an increment of 1 year. Just wondering if there is a way to calculate the 95% CI for the survival rate difference between the two arms.

[SteveDenham]

You might be able to get what you want by doing a restricted mean analysis.  Here is a link to an example:

https://documentation.sas.com/doc/en/statug/15.2/statug_lifetest_examples05.htm#:~:text=The%20follow... 

Depending on which level of SAS/STAT you have, you could consider moving to PROC RMSTREG, which has an LSMEANS statement.  If it supports the DIFF and CL option, and especially the AT= option, you are in good shape.  See this example for a first step:

https://documentation.sas.com/doc/en/statug/15.2/statug_rmstreg_examples02.htm 

and this for a more complete analysis

https://documentation.sas.com/doc/en/statug/15.2/statug_rmstreg_examples03.htm 

SteveDenham.

[SAS_John]

Thanks, Steve for the information. I will take a look. Best, John