Date:         Sat, 30 Apr 2005 09:52:33 -0700
Reply-To:     shiling99@YAHOO.COM
Sender:       "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From:         shiling99@YAHOO.COM
Organization: http://groups.google.com
Subject:      Re: caluating predicted value(outsample)
Comments: To: sas-l@uga.edu
In-Reply-To:  <1114877668.783545.131300@l41g2000cwc.googlegroups.com>
Content-Type: text/plain; charset="iso-8859-1"

You may append you forecast x's values into the data set. The program
will spit out a fitted/project value for any given x value when y is
missing. Take a look the following example.

Another way is to save all parms into a table then calculate all
forecasts in a data step. I believe you can save parms via ODS.

HTH

data t1;
  do i = 1 to 30;
     x=rannor(123);
         y=2+3*x+rannor(123);
         if i>=25 then y=.;
         output;
   end;
run;

proc glm data=t1;
  model y=x;
  output out=t2 p=py r=err;
quit;

proc print; run;
luckyalis wrote:
> Thank you so much! but I need to calculate the predicted value using
> outsample.
> That is the obs. not in the original sample which come up the
estimated
> model.
> Can you help me and tell where I can find the documents?
>
> Thank you so much!!!! Much appreciated!
>
> puzzelalis