Proc SEQDESIGN and futility

rmacarthur — Sun, 19 Jan 2020 17:05:59 GMT

Hi SAS Friends,

Am looking for examples of how to use the PROC SEQDESIGN procedure when adding an interim FUTILITY analysis only to a study design. All examples seen so far in the SAS PROC SEQDESIGN Manual and meeting papers include an interim analysis for efficacy with a futility analysis added. However none with futility alone.

For example, the following code:

proc seqdesign pss stopprob errspend ;

onesidedtwostage: design nstages=2 info=cum(.6 1) alt=upper

alpha=0.025 beta=.20

method(reject)=errfuncobf /* INTERIM EFFICACY BOUNDARY */

METHOD(ACCEPT)=ERRFUNCOBF STOP=BOTH ; /* INTERIM FUTILITY BOUNDARY */

samplesize model=twosamplefreq(nullprop=.5 prop=.70 ref=nullprop test=prop);

title1 "Stopping early for futility " ;

run;

The above code generates efficacy and futility boundaries, however if the efficacy line is deactivated (as /*method(reject)=errfuncobf */) then the code will not run and the following error is produced:

ERROR: Methods for all boundaries must be specified in the DESIGN statement if more than one
stage is specified.

Any suggestions how produce an interim futility analysis only, using the above code, or any SAS code, would be greatly appreciated.

Thank you !

Re: Proc SEQDESIGN and futility

Rick_SAS — Wed, 22 Jan 2020 21:17:04 GMT

I do not use PROC SEQDESIGN myself, but I notice in the doc that the syntax supports

STOP=ACCEPT
STOP=REJECT

Is that useful?

topic Proc SEQDESIGN and futility in Statistical Procedures

Proc SEQDESIGN and futility

Re: Proc SEQDESIGN and futility