Date:         Wed, 22 Feb 2006 11:24:19 -0500
Reply-To:     "Droogendyk, Harry" <harry.droogendyk@RBC.COM>
Sender:       "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From:         "Droogendyk, Harry" <harry.droogendyk@RBC.COM>
Subject:      Re: Collapsing data into meaningful categories
Content-Type: text/plain; charset="iso-8859-1"

Create a format to categorize the house values.  Read up on the specifying value ranges, paying particular attention to the "low", "high", "-<" stuff.

There was a value range missing in your specs.  If that was intentional ( ie. you don't care to categorize the houses in the 100-150K range ), remove the range from the PROC FORMAT stuff below and add "other = 'Not categorized'" to the value specification.

See: http://support.sas.com/onlinedoc/913/docMainpage.jsp

proc format;
        value house
                low      -< 50000        = '<50K'
                50000  -< 100000   = '50-100K'
                100000 -< 150000         = '100-150K'
                150000 -< 200000         = '150-200K'
                200000 -< 300000   = '200-300K'
                300000 -< 500000         = '300-500K'
                500000 -< 1000000        = '500-1,000K'
             1000000 - high      = '1m+';
run;

data a;
        input value freq;
        category = put(value,house.);
cards;
100000  2
200000  7
299999.99  7
102934     2
98328       1
400831     5
1039482    2
50000        3
run;

proc print data=a;
run;

-----Original Message-----
From: owner-sas-l@listserv.uga.edu
[mailto:owner-sas-l@listserv.uga.edu]On Behalf Of Ron
Sent: Wednesday, February 22, 2006 11:00 AM
To: sas-l@uga.edu
Subject: Collapsing data into meaningful categories


Hello,

I'm new to the SAS world. please forgive my elementary question.

I have data on customer home values (around 5000 obs). The values are
listed as actual values. There is another column of frequencies. So
there are something like 3500 unique values.

I would like to collapse the actual home values into more tracteable
categories while maintaining the frequencies for each category.

The category breakdown would be something like:
<50K
50-100k
150-200k
200-300k
300-500k
500-1,000k
1m+


Sample data

value          freq
102934     2
98328       1
400831     5
1039482    2
50000        3

If someone could point me in the right direction I would be grateful.

Best,

RON
User0492@hotmail.com
_______________________________________________________________________

This e-mail may be privileged and/or confidential, and the sender does not waive any related rights and obligations.
Any distribution, use or copying of this e-mail or the information it contains by other than an intended recipient is unauthorized.
If you received this e-mail in error, please advise me (by return e-mail or otherwise) immediately.

Ce courrier électronique est confidentiel et protégé. L'expéditeur ne renonce pas aux droits et obligations qui s'y rapportent.
Toute diffusion, utilisation ou copie de ce message ou des renseignements qu'il contient par une personne autre que le (les) destinataire(s) désigné(s) est interdite.
Si vous recevez ce courrier électronique par erreur, veuillez m'en aviser immédiatement, par retour de courrier électronique ou par un autre moyen.