Date:         Wed, 15 Jul 2009 07:42:42 -0700
Reply-To:     Shaheen <siqubal@GMAIL.COM>
Sender:       "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From:         Shaheen <siqubal@GMAIL.COM>
Organization: http://groups.google.com
Subject:      Re: PROC RANK
Comments: To: sas-l@uga.edu
Content-Type: text/plain; charset=ISO-8859-1

On Jul 15, 5:52 am, xinrong <xleiu...@gmail.com> wrote:
> use "procsql" left join the origninal 506 records with the 504 "procrank" output,
> then it is easy to find out which 2 records has been ignored.
> hope these can help you find out what goes wrong.
>
> On Jul 14, 4:37 pm, Shaheen <siqu...@gmail.com> wrote:
>
>
>
> > Hi,
> > I have a dataset with 506 record and I am usingPROCRanktoRankthis
> > data into quintiles.  I was expecting to see 101-101-101-101-102
> > observation or 102-101-101-101-101 but instead I get
> > 100-102-102-100-100.  Ranking field has no missing value and no
> > duplicates.  Is there a way to get the ranking I want?
>
> > Regards,
> > Shaheen
>
> >PROCSORT DATA=InvSys.Test1;
> >         By Ranking_Field;
> > run;
>
> >PROCRANKDATA=InvSys.Test OUT=InvSys.Test1 groups=5;
> >         VAR Ranking_Field;
> >         RANKSRank;
> > run;
>
> >PROCSQL;
> >         CREATE TABLE InvSys.Test2
> >         AS
> >         (
> >         SELECTRank,Count(Rank)
> >         FROM InvSys.Test1
> >         Group ByRank
> >         );
> > quit;- Hide quoted text -
>
> - Show quoted text -

I am still getting 506 record 100-102-102-101-101 but I was hoping
proc rank to divide equal # of companies in each bucket so if I have
506 then it should put 101 companies in each bucket and then add 1
company either in the first or middle or last bucket.  Sorry for the
confusion.