You are right. I thougt this is based on maximum number but this is not the case. ... View more

data want(drop=i); set have; array x{*} x:; do i=1 to dim(x); MostFreq=max(of x(*)); Count=countc(cats(of x(*)),MostFreq,'i'); end; run; ... View more

data want(drop=i); set have; array a Vol_1 Vol_2 Vol_3 Rev_1 Rev_2 Rev_3 Profit_1 Profit_2 Profit_3 SP_1 SP_2 SP_3; do i=1 to 3; volume=vname(a(i)); volume_fig=a(i); Revenue=vname(a(i+3)); Revenue_fig=a(i+3); Profit=vname(a(i+6)); Profit_fig=a(i+6); SP=vname(a(i+9)); SP_fig=a(i+9); output; end; drop Vol_1 Vol_2 Vol_3 Rev_1 Rev_2 Rev_3 Profit_1 Profit_2 Profit_3 SP_1 SP_2 SP_3; run; ... View more

Please try the following syntax that will maintain the first instance of zero for proc corr:   data want(keep=variable price value); set have; array p(*) Participant:; do i=1 to dim(p); value=p(i); variable=vname(p(i)); output; end; run;   proc sort data=want; by variable; run;   data corr(drop=flag); do until(last.variable); set want; by variable; if not flag then output; if value=0 then flag = 1; end; run;   proc corr data=corr; by variable; var price; with value; run; ... View more

One way to do this is to stack all variables' names and values then use by processing in proc corr for values greater than 0. Something like this:   data have; input Price Participant1 Participant2 Participant3; datalines; 1 10 25 0 2 8 25 0 3 6 25 0 4 4 20 0 5 2 18 0 6 0 15 0 7 0 10 0 8 0 0 0 9 0 0 0 10 0 0 0 ;   data want(keep=variable price value); set have; array p(*) Participant:; do i=1 to dim(p); value=p(i); variable=vname(p(i)); output; end; run;   proc sort data=want; by variable; run;   proc corr data=want(where=(value>0)); by variable; var price; with value; run; ... View more

data Test; q1=5; q2=10; z=Largest(1,q1, q2); run; ... View more

Still not significantly different:   proc glm data=want; class groupid; model x y z=groupid; run; ... View more

 @PGStats:  Interesting approach. To learn more about this just a few questions:   Why PCA with only one principal component? Why only two groups and are these two groups sufficient to make sure variation between groups is large enough to conclude that means are significantly different? ... View more

This seems to be a clustering problem. If you are okay with SAS/STAT try proc cluster or proc fastclus to assign a label to each observation. ... View more

Try this.   proc sort data=SUMMARY94; by CLIENT_ID; run;   proc surveyselect data = SUMMARY94 method = URS sampsize = 1 seed = 12345 out = hsbs3; strata CLIENT_ID; run; ... View more

proc tabulate data=have; class date code; var Code_Amt; table date,code*sum=''*Code_Amt='' /misstext='0'; run; ... View more

Below is one approach using sql and data steps:   data have; input P1 $ P2 $ P3 $; datalines; AP AP AP 30 25 80 50 30 120 NO 50 NO NO 20 NO ;   data want(keep=vname values); set have; array p(*) P1-P3; do i=1 to dim(p); vname=vname(p(i)); values=p(i); output; end; run;   proc sql; select distinct vname into :del separated by ' ' from want where values='NO'; quit;   data final; set have(drop=&del); run; ... View more