Hello all!
I'm rather rusty at SAS and was hoping for a bit of help. I have 5 binary variables and want to know how many observations reported "yes" for all 5 of them. Is there a way to do this? Thank you!
Well, if you have something like:
data have; var1=1; var2=0; var3=1; var4=1; output; var1=1; var2=1; var3=1; var4=1; output; run; data want; set have end=last; retain result 0; array var{4}; if sum(of var{*})=4 then result=sum(result,1); if last then output; run;
There are indeed many different ways to achieve this. I agree with @Reeza that it's nice to see all combinations. Here is an alternative to the "table binary1*binary2*binary3*binary4*binary5" approach with PROC FREQ. (Sometimes I have encountered memory shortage issues when applying such a 5- or higher-dimensional cross-table request to a large dataset.)
data have; /* just to create dummy data */
array var a b c d e;
do j=1 to 100;
do i=1 to 5;
var[i]=(ranuni(314159)<0.5);
end;
output;
end;
drop i j;
run;
data combi;
set have;
length comb $5;
comb=cats(of a--e); /* creates the combinations like '01101' */
run;
proc freq data=combi;
tables comb;
run;
Or you could use PROC SQL without creating a new dataset (like COMBI above):
proc sql;
select a, b, c, d, e, count(*) as cnt
from have
group by a, b, c, d, e;
quit;
@Reeza @RW9 @FreelanceReinhard Thank you all for your replies!
Registration is open! SAS is returning 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. Register for just $495 by 12/31/2023.
If you are interested in speaking, there is still time to submit a session idea. More details are posted on the website.
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.