Sample size calculation for a one sample logrank test

[pit]

Is there a way in SAS to perform a sample size calculation for a one-sample logrank test? The information I have is a historical based assumption providing a median survival time.

I assumed, that the historical median survival time is 6 months and the estimated survival time will be 10 months.

So far I used proc power and assumed having two samples, so that I can perform a calculation:

proc power;
	twosamplesurvival test=logrank
	groupmedsurvtimes = (6 10)
	accrualtime = 6
	followuptime = 6
	grouplossexphazards = (0 0)
	groupweights = (1 1)
	alpha = 0.025
	sides = 1
	power = 0.8
	ntotal=.;
run;

The chosen parameters are not important to me, it is about finding a method to perform a proper one-sample logrank test in SAS. If this is not possible by now than this information is helpful aswell.

I'm running SAS 9.4.

[tamhane · Accepted solution]

Haven't come across that in SAS but PASS software has it. The reference they cite is:

Wu, Jianrong. 2015. “Sample size calculation for the one-sample log-rank test,” Pharmaceutical Statistics, Volume
14, pages 26-33.

Also attached is the documentation from PASS and a poster.

[pit]

Thank you for your opinion and the attached files! I haven't found a way to perform a sample size calculation for a one sample logrank test within SAS, so I used nQuery Advisor.