SAS Code for Calculation of Average Correlation Among Variables

Data defines the model by dint of genetic programming, producing the best decile table.

SAS Code for Calculation of Average Correlation Among Variables
Bruce Ratner, Ph.D.

Live chat by Bold chat

%let varlist =
Var1 Var2 Var3;
title2 " AVG_CORR of &varlist ";
%let numvars=3;

data dat1;
input Var1 Var2 Var3 :4.0;
cards;
1234 2345 3456
5678 4567 8798
1256 0978 4567
;
run;

proc corr data=dat1 out=out;
var &varlist;
run;

data out1;
set out;
if _type_='MEAN' or _type_='STD' or _type_='N' then delete;
drop _type_;
array vars (&numvars)
&varlist;
array pos (&numvars) x1 - x&numvars;
do i= 1 to &numvars;
pos(i)=abs(vars(i));
end;
drop
&varlist i;
run;

data out2;
set out1;
array poss (&numvars) x1- x&numvars;
do i= 1 to &numvars;
if poss(i) =1 then poss(i)=.;
drop i;
end;
run;

proc print;
run;

proc means data=out2 sum;
output out=out3 sum=;
proc print;
run;

data out4;
set out3;
sum_=sum(of x1-x&numvars);
sum_div2= sum_/2;
bot= ((_freq_*_freq_)-_freq_)/2;
avg_corr= sum_div2/bot;
run;

data avg_corr;
set out4;
keep avg_corr;
proc print;
run;

For more information about this article, call Bruce Ratner at 516.791.3544 or 1 800 DM STAT-1; or e-mail at br@dmstat1.com.

Sign-up for a free GenIQ webcast: Click here.