/*select data from raw data set*/
data x;
set y;
where var1 = ‘xxx’ and var2 = ‘yyy’;
run;
/*check frequency on variables of interest*/
proc freq;
tables var1 var2;
run;
/*merge to get additional variables needed for analysis*/
proc sort data = x;
by var3;
proc sort data =z;
by var3;
data xz;
merge x (in =a) z;
by var3;
if a;
run;