Date:         Tue, 24 Mar 2009 10:20:17 -0500
Reply-To:     Mary <mlhoward@avalon.net>
Sender:       "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From:         Mary <mlhoward@AVALON.NET>
Subject:      Re: How can I detect any real deviation from a uniform monthly
              distribution?
Comments: To: irinfigvam@yahoo.com
Content-Type: text/plain; format=flowed; charset="iso-8859-1";
              reply-type=original

You'd have to have a control group, those who do not have depression.

Then if you are after the season of birth as a predictor of depression you
would create a new variable in a data step:

data newtable;
set oldtable;
if month_of_birth in (12,1,2) then season='Winter';
else if month_of_birth in (3,4,5) then season='Spring';
else if month_of_birth in (6,7,8) then season='Summer';
else if month_of_birth in (9,10,11) then season='Fall';
if diagnosis='Depression' then disease=1;
else disease=0;
run;


proc logisitic data=newtable;
class season(param=ref ref='Summer');
model disease(DESC)= season;
run;

-Mary

----- Original Message -----
From: "Irin later" <irinfigvam@YAHOO.COM>
To: <SAS-L@LISTSERV.UGA.EDU>
Sent: Tuesday, March 24, 2009 10:04 AM
Subject: How can I detect any real deviation from a uniform monthly
distribution?


I have a file of unique patients who had diagnosis "Depression" during the
calendar year.
For each of the patients I have Month of Birth value (1-12).

I expect seasonal variations in the diagnosis of depression (depending on
what was
the month of the birth value).
How can I validate or disprove this hypothesis? How can I detect any real
deviation
from a uniform monthly distribution?

How to implement it in SAS code?

Could you, please, give me a hand?

Thank you in advance,

Irin