Date:         Tue, 22 Nov 2005 08:30:47 -0900
Reply-To:     David Neal <afdbn@UAA.ALASKA.EDU>
Sender:       "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From:         David Neal <afdbn@UAA.ALASKA.EDU>
Subject:      Re: Proc Means with statistical Test
Comments: To: anne olean <annekolean@YAHOO.COM>
In-Reply-To:  <20051122165500.86088.qmail@web30613.mail.mud.yahoo.com>
Content-type: text/plain; charset=ISO-8859-1; format=flowed

Anne,

PROC MEANS isn't designed to compare means, unless you count the PROBT
option which compares the mean to zero.  If you are comparing two means
then look at PROC TTEST.  Basically what I am trying to say is that you
are going to have to do it with another procedure.  Why do you need to
do it in PROC MEANS?  Are you limited to just BASE?

Are you looking for pairwise comparisons accross all 3 means or are you
looking for a single test (ANOVA)?  My assumption is that you are
looking for a single F-Test and an easy way to do that is PROC GLM.  You
can use ODS to grab the F-Test results and then combine them with your
original data.  You can then use PROC TABULATE to create a nice little
table with exactly what you want.

David Neal

anne olean wrote:
> Hi,
> i have a variable (age) that i want to compare wrt
> means across three groups. I used proc means to do
> that:
>
> proc means data=preds n mean median std;
>   class group;
>   var age;
> run;
>
> this gives a nice table, but is there an option to get
> a test statistic comparing the 3 groups(all i found is
> the "t-test" and that's not what i want). i know i can
> get the statistic from proc glm, but i want to create
> a table as in proc means with the last column being
> the test statistic and p-value....can that be done
> within proc means? if not, how can i get the nice
> looking table that proc means produces in proc glm?
>
> thanks so much, ako
>
>
>
>
>
> __________________________________
> Start your day with Yahoo! - Make it your home page!
> http://www.yahoo.com/r/hs