Programming the statistical procedures from SAS

Default ProdcutLimitEstimates (PROC LIFETEST)

Accepted Solution Solved
Reply
Regular Contributor
Posts: 220
Accepted Solution

Default ProdcutLimitEstimates (PROC LIFETEST)

While producing a Kaplan-Meier survival plot, I added the number of patients at risk at given time points.  To get the at-risk counts, I used the default values (the LEFT variable) produced in PROC LIFETEST from the ProductLimitEstimates ODS output table:

ods output ProductLimitEstimates=ple;

proc lifetest data=efficacy timelist=(0 to 75 by 5);

      time survtime*censorflag(0);

      strata trtgrp;

run;

If a patient experiences an event at a time point cut off (say, exactly 10 weeks), then SAS does not count that patient as being at risk.  However, I have been told by both our program validator and biostatistician consultant that such patients should be counted as being at risk.  Is there an option in SAS that would allow me to specify to count those patients, or do I have to manually run the data through a loop and count them up on my own?  I was originally using SAS 9.1.3, but I was able to upgrade to SAS 9.3 this week.  Wahoo!


Accepted Solutions
Solution
‎10-26-2012 01:12 PM
Super User
Posts: 18,498

Re: Default ProdcutLimitEstimates (PROC LIFETEST)

Don't have a book to double check at the moment but try changing the method to the actuarial method Method=LT in your proc lifetest statement, or add a slight 'fudge' factor, ie change 10 to 10.0001.  Or compute it manually.

View solution in original post


All Replies
Solution
‎10-26-2012 01:12 PM
Super User
Posts: 18,498

Re: Default ProdcutLimitEstimates (PROC LIFETEST)

Don't have a book to double check at the moment but try changing the method to the actuarial method Method=LT in your proc lifetest statement, or add a slight 'fudge' factor, ie change 10 to 10.0001.  Or compute it manually.

Regular Contributor
Posts: 220

Re: Default ProdcutLimitEstimates (PROC LIFETEST)

The fudge factor seemed to be my best bet.  Thanks!

🔒 This topic is solved and locked.

Need further help from the community? Please ask a new question.

Discussion stats
  • 2 replies
  • 219 views
  • 0 likes
  • 2 in conversation