Date:         Sun, 2 Nov 2008 08:58:37 -0500
Reply-To:     Ken Borowiak <EvilPettingZoo97@AOL.COM>
Sender:       "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From:         Ken Borowiak <EvilPettingZoo97@AOL.COM>
Subject:      Re: Means

On Sun, 2 Nov 2008 08:44:30 -0500, Randy <randistan69@HOTMAIL.COM> wrote:

>Dear all:
>  Is there a one step data process to calculate the means of the entire
>sample; and the means according to the class.
>So, for example;
>
>Class    VarA
>A         20
>A         31
>B         22
>A         12
>B         4
>
>I want the mean of VarA for all the observations and according to Class A
>and Class B.  I would like to do this in one data step.  Is this possible?
>          Randy


Randy,

Try PROC SUMMARY *without* using the NWAY option.

data sup ;
input Class $  VarA ;
datalines ;
A         20
A         31
B         22
A         12
B         4
;
run ;

proc summary data=sup ;
 class class ;
 var vara ;
 output out=sup2 mean= / autoname ;
 run ;

hth,
Ken