Hello,
I'm trying to compute column percentages and total percentages for my data. The problem is, proc freq gets correct results, but not the desired table layout, with proc tabulate I can get desired layout but slightly different column percentages results, how is this possible? Can someone advise me how to adjust my proc tabulate to get the same column percentages and total percentages as my proc freq?
My data step is the same for both procedures:
data work.subset1;
set library.database
where HS01 between 1 and 5;
keep pid AGE sex WGT HS01;
run;
My proc freq step and output:
proc freq data=work.subset1;
tables HS01*(sex AGE)/nofreq norow;
weight WGT;
format HS01 sbjzdravie. sex pohlavie. AGE vek.;
run;
My proc tabulate step with the same data step.. and output:
proc tabulate data=work.subset1;
class HS01 sex AGE;
table (HS01 all)*f=5.1, (all sex)*(colpctn)*f=5.1 AGE*colpctn*f=5.1;
weight WGT;
format HS01 sbjzdravie. sex pohlavie. AGE vek.;
run;
Thanks! Looked at the documentation, and apparently weight statements for each procedure has slightly different use. In proc freq weight statement it is used for multiplication of observations for counts, whereas in proc tabulate it is used for computation of weighted statistics like mean, variance etc. For the same use as in proc freq, you have to use freq statement in proc tabulate, that will get the same results.
Look at the documentation of the WEIGHT statement for each proc - specifically the defaults.
Thanks! Looked at the documentation, and apparently weight statements for each procedure has slightly different use. In proc freq weight statement it is used for multiplication of observations for counts, whereas in proc tabulate it is used for computation of weighted statistics like mean, variance etc. For the same use as in proc freq, you have to use freq statement in proc tabulate, that will get the same results.
Hi Gabon,
Could you please show how you specified FREQ freq statement in proc tabulate? I am stuggling with exact same problem here. My proc tabulate reqult is diff from that of proc freq.
Are you ready for the spotlight? We're accepting content ideas for SAS Innovate 2025 to be held May 6-9 in Orlando, FL. The call is open until September 25. Read more here about why you should contribute and what is in it for you!
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.