Statistical programming, matrix languages, and more

Proc IML generation help

Reply
N/A
Posts: 0

Proc IML generation help

Good day,

I have been struggling for a while trying to get this program to work. It keeps on giving me the error: Error (Execution) Matrix has not been set to a value. I am trying to generate a sample space from n observations and repeating it g times. My aim is to find the beta hat parameters and to place them into a results (rst) matrix.

Could someone be so kind as to point out where I am going wrong?

This is the code:

proc iml;

n = 200;
k = 3;
g = 30;


do it = 1 to g ;

/*x = J(n,k,1) ;
u = J(n,1,99999) ;
y = J(n,1,99999) ;*/
sd = J(n,1,0);
rst = J(n,1,99999);


do i= 1 to n;

x2 = ranuni(sd)*100+100;
x3 = ranuni(sd)*50+150;
u = rannor(sd)*100;
y = 100+3*x2+15*x3+u;
x = J(n,1,1) || x2 || x3;
end;
bh = inv(x`*x)*x`*y;
print bh;

rst[i,] = bh`;

print rst;
end;
quit; Message was edited by: Reytla
N/A
Posts: 0

Re: Proc IML generation help

I've sorted it out. Thanks all the same!
Ask a Question
Discussion stats
  • 1 reply
  • 205 views
  • 0 likes
  • 1 in conversation