Date:         Thu, 28 Sep 2006 16:38:58 -0400
Reply-To:     Jim Groeneveld <jim2stat@YAHOO.CO.UK>
Sender:       "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From:         Jim Groeneveld <jim2stat@YAHOO.CO.UK>
Subject:      Re: How to use SAS to determine patient group and control group?
Comments: To: tonywolf@YAHOO.COM

Hi Tony,

Do the patients in each of your 24 groups already have comparable size, age,
gender, etc.? If not then you should develop an algorithm to match patients
as good as possible (within limits).

But do you really need matched (paired) patients? Can't you do with just two
random (unpaired) groups that match on the average? Tell us about your design.

Regards - Jim.
--
Jim Groeneveld, Netherlands
statistician, SAS consultant
home.hccnet.nl/jim.groeneveld


On Thu, 28 Sep 2006 11:14:00 -0700, Tonywang <tonywolf@YAHOO.COM> wrote:

>Hi Guys,
>
>I have 24 groups of patients with different size, age, gender percent,
>medical cost etc. and I want to divide those 24 groups into 2 big
>groups: Patient group and Control group. The two groups should have
>similiar size, age, gender....etc.
>
>Is there anyway we can do this with SAS?
>
>Thanks for your help.
>
>Tony