Date:         Thu, 16 Feb 2006 14:16:54 -0500
Reply-To:     mah-j@statworks.com
Sender:       "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From:         "mah-j@statworks.com" <msoobader@VERIZON.NET>
Subject:      Re: mianalyze convert to odds ratio's
In-Reply-To:  <20060216182136.74663.qmail@web32215.mail.mud.yahoo.com>
Content-type: text/plain; charset=iso-8859-1

As a follow up question.

I can now output estimates from MIANALYZE but would like to find an easy way
to convert them to odds ratio's.  I can calculate them by hand- but that
will take a lot of time- since I have multiple models with varying numbers
of variables. The number of variables will also differ between models.

Here is what I have:
                                    Obs    Parm             Estimate
StdErr

                                     1     intercept        1.354719
0.035408
                                     2     ageyr           -0.030406
0.001475
                                     3     male            -0.118662
0.014742
Here is what I need:

Var     OR                      Upper and lower confidence intervals
ageyr exp(-0.030406)    (est+/-1.96*SE)

Any help or suggestions will be very much appreciated,
Mah-J

M. Soobader, PhD
STATWORKS
www.statworks.com