Again, see that documentation for info on all options, but PARAM=GLM creates the typical 0,1 coded design columns that most people use to represent categorical predictors. But if your only categorical predictors are binary and you already have them coded as 0,1, then you can just omit the CLASS statement. ... View more

First way is trying SPARSE option: proc freq data=work.datarequest; tables zipcode*ASTHMA / norow nocol nopercent sparse ; run; Second way is using WEIGHT statement @Rick_SAS mentioned this skill in one of his blog. Post your sample data that would be better to demonstrate how to use WEIGHT . ... View more

Adding on to @ballardw answer.    You may need to rename some variables (RENAME option), and want to indicate which dataset it came from (INDSNAME option).   data want; length src source $50.; set data2016 (keep=<your desired variables go here> rename=(oldname1=newname1 oldname2=newname2)) data2017 (keep=<your desired variables go here>) data2018 (keep=<your desired variables go here>) INDSNAME = SRC; Source = src; run; ... View more

Add the following options on the top of the code, run it and then share the SAS log with us (please as an attachment and not just copy/past into the body of the conversation). Before attaching the log: Make sure you browse over it and remove anything confidential/internal from it. ... View more