| Date: | Mon, 9 Feb 2009 11:28:04 -0600 |
| Reply-To: | "./ ADD NAME=Data _null_;" <iebupdte@GMAIL.COM> |
| Sender: | "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU> |
| From: | "./ ADD NAME=Data _null_;" <iebupdte@GMAIL.COM> |
| Subject: | Re: proc plan |
|
| In-Reply-To: | <705bcd670902090905p50a5b0b1xf53c61c2ddd1d6b8@mail.gmail.com> |
| Content-Type: | text/plain; charset=ISO-8859-1 |
See if this is suitable.
proc plan seed=309955295;
factors r=6 ordered c=8 ordered i=1 of 48 cyclic;
output out=plan r cvals=('A' 'B' 'C' 'D' 'E' 'F') i nvals=(1 to 48) random;
run;
quit;
proc report nowd list;
columns r c,i dummy;
define r / group;
define c / across;
define i / display format=2. '--';
define dummy / noprint;
run;
On 2/9/09, joey m <sasuser.joey.m@gmail.com> wrote:
> Hi all:
>
> With help of proc plan I have been trying to randomize a design like this: 6
> rows and 8 columns, and each cell
> will have a number (from 1 to 48) at random:
>
> 1 2 3 4 5 6 7 8
> A
> B
> C
> D
> E
> F
>
> Thus, any ij (i=A to F, and j=1 to 8), say A6, will be equal to any number
> from 1 to 48
> (without repeating them in any other cell).
>
> What I want is something like this:
> 1 2 3 4 5 6 7 8
> A 5 4 35 30 7 48 5 45
> B 1 6 . . . . . .
> C . . . . . . . .
> D . . . . . . . .
> E . . . . . . . .
> F . . . . . . . etc
>
> My attempts have produced something like this
>
> 1 2 3 4 5 6 7 8
> 3 5 3 4 8 7 1 6 2
> 2 3 2 5 8 1 4 7 6
> 4 3 2 6 1 5 7 4 8
> 6 3 2 6 4 1 7 5 8
> 1 6 1 2 5 7 4 3 8
> 5 6 3 1 2 7 5 8 4
>
> Then, I change rows ids from 1 to 6 to A to F.
> As always any help will be greatly appreciated.
>
|