Date:         Wed, 22 Aug 2007 14:45:21 -0400
Reply-To:     Kevin Roland Viel <kviel@EMORY.EDU>
Sender:       "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From:         Kevin Roland Viel <kviel@EMORY.EDU>
Subject:      Re: Proc Rank
In-Reply-To:  <200708221757.l7MFRkqk015787@mailgw.cc.uga.edu>
Content-Type: TEXT/PLAIN; charset=US-ASCII

On Wed, 22 Aug 2007, E Henderson wrote:

> proc sort data=bb9303gpatest2 (keep=id stembach gpastand ct);
> by stembach;
> run;
>
> PROC RANK data=bb9303gpatest2
> GROUPS=5 OUT=bb9303gpatest2_rk;
> VAR gpastand;
> by stembach;
> RANKS gpa_quint;
> label gpa_quint='GPA Quintile';
> *format stembach stembach.;
> run;


"GROUPS=number-of-groups

If the number of observations is evenly divisible by the number of groups,
each group has the same number of observations, provided there are no tied
values at the boundaries of the groups. Grouping observations by a
variable that has many tied values can result in unbalanced groups because
PROC RANK always assigns observations with the same value to the same
group."

In fact, I think unbalanced rank groups will result with the other
options, too.

HTH,

Kevin

Kevin Viel, PhD
Post-doctoral fellow
Department of Genetics
Southwest Foundation for Biomedical Research
San Antonio, TX 78227