Hi,
I have these equations (as an example):
ACVF1=c1+c1*c2+c2*c3+c3*c4;
ACVF2=c2+c1*c3+c2*c4;
ACVF3=c3+c1*c4;
ACVF4=c4;
I need to fulfill them in general to be able to calculate various LAG autocorrelation's for ma(q) process.
Here is what I have accomplished so far:
%let LAG = 4; %let cmax = 0.9; %let cmin = 0.3; %let cvalue = (&cmax.-&cmin.)/(&LAG.-1); data tACVF; array ACVF(&LAG.); array c(&LAG.); do i=1 to dim(c); c(i)=&cmax.-(&cvalue.*(i-1)); ACVF(i)=c(i); do j=1 to dim(c); ACVF(j)=ACVF(j)+c(i)*c(j+1); output; end; end; proc print; run;
I'm getting this:
ERROR: Array subscript out of range at line 66 column 22.
I assume this is because of reaching higher index then there is, but I don't know how to solve this issue. Can anyone help ?
That's a bit closer to what I wanted to achieve, but you gave me an idea on how to solve my issue here. Many thanks!
Here's the code:
%let LAG = 4; %let cmax = 0.9; %let cmin = 0.3; %let cvalue = (&cmax.-&cmin.)/(&LAG.-1); data tACVF; array ACVF(&LAG.); array c(&LAG.); /* initialize C array*/ do i=1 to dim(c); c(i)=&cmax.-(&cvalue.*(i-1)); end; do k=1 to dim(Acvf); ACVF(k)=c(k); do j=1 to (dim(c)-k); s=j+k; ACVF(k)=sum(ACVF(k),c(j)*c(s)); end; /* possible output here*/ end; proc print; run;
You say
do j=1 to dim(c);
and then refer to c(j+1), That's obviously out of range...
Are you looking for something like this:
%let LAG = 4;
%let cmax = 0.9;
%let cmin = 0.3;
%let cvalue = (&cmax.-&cmin.)/(&LAG.-1);
data tACVF;
array ACVF(&LAG.);
array c(&LAG.);
/* initialize C array*/
do i=1 to dim(c);
c(i)=&cmax.-(&cvalue.*(i-1));
end;
do k=1 to dim(Acvf);
ACVF(k)=c(k);
do j=k to (dim(c)-1);
ACVF(j)=sum(ACVF(j),c(j)*c(j+1));
end;
/* possible output here*/
end;
run;
That has all the values in one record.
If you are looking for triangle of values for ACVF then use the location indicated for the output. Your original output statement was going to create possibly more records than you really wanted as you had intermediate values of the ACVF. Drop the i, j, k if desired.
That's a bit closer to what I wanted to achieve, but you gave me an idea on how to solve my issue here. Many thanks!
Here's the code:
%let LAG = 4; %let cmax = 0.9; %let cmin = 0.3; %let cvalue = (&cmax.-&cmin.)/(&LAG.-1); data tACVF; array ACVF(&LAG.); array c(&LAG.); /* initialize C array*/ do i=1 to dim(c); c(i)=&cmax.-(&cvalue.*(i-1)); end; do k=1 to dim(Acvf); ACVF(k)=c(k); do j=1 to (dim(c)-k); s=j+k; ACVF(k)=sum(ACVF(k),c(j)*c(s)); end; /* possible output here*/ end; proc print; run;
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 how use the CAT functions in SAS to join values from multiple variables into a single value.
Find more tutorials on the SAS Users YouTube channel.