I am currently using PROC surveyselect to pull a random sample from a data set using this code:
proc surveyselect data= out.care_statement_all_q&rptqtr.
method=srs n=60 out=out.care_statement_q&rptqtr.;
run;
Is there a way to set the size as a range. Every run the user would like a varying sample size between 60-70. This is part of an automated process so I would like there to be no manual involvement.
Make a random macro variable :
%let n=%sysevalf(%sysfunc(rand(uniform))*10+60,i);
%put NOTE: n=&n;
proc surveyselect ............... n=&n ........
What environment is the user using to run the code? Base SAS, Enterprise Guide, something else?
Sorry for the lack of details. It is currently being run in SAS EG on our companies UNIX envrionment. I am new to SAS programming and not sure all the correct terms. It is executed from an auto file that kicks off automatically.
Create 11 fake strata in your data
data fakeStrataCare;
set out.care_statement_all_q&rptqtr.;
do stratum=60 to 70;
output;
end;
run;
proc sort data=fakeStrataCare; by stratum; run;
and call proc surveyselect with a different sample size for each stratum
proc surveyselect data= fakeStrataCare
method=srs n=(60 61 62 63 64 65 66 67 68 69 70) out=out.care_statement_q&rptqtr.;
strata stratum;
run;
(untested)
Make a random macro variable :
%let n=%sysevalf(%sysfunc(rand(uniform))*10+60,i);
%put NOTE: n=&n;
proc surveyselect ............... n=&n ........
Thank you so much Ksharp. This worked perfectly and is simple for what I am doing. Could you explain it a bit so if I never needed to use this again but for varying sample size. Like if I need between 30-40 how would I change the numbers.
%let n=%sysevalf(%sysfunc(rand(uniform))*10+30,i);
int(rand('uniform')*10) will generate the random number 0,1,2,3,4,5,6,7,8,9
here 10 is the range between 30 and 40 .
here 30 is the base of range(or left value of range) .
SAS is headed back to Vegas for an AI and analytics experience like no other! Whether you're an executive, manager, end user or SAS partner, SAS Innovate is designed for everyone on your team.
Interested in speaking? Content from our attendees is one of the reasons that makes SAS Innovate such a special event!
Learn the difference between classical and Bayesian statistical approaches and see a few PROC examples to perform Bayesian analysis in this video.
Find more tutorials on the SAS Users YouTube channel.