Date:         Wed, 19 Dec 2007 12:21:23 -0800
Reply-To:     Ryan <Ryan.Andrew.Black@GMAIL.COM>
Sender:       "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From:         Ryan <Ryan.Andrew.Black@GMAIL.COM>
Organization: http://groups.google.com
Subject:      Re: Deviance Test?
Comments: To: sas-l@uga.edu
Content-Type: text/plain; charset=ISO-8859-1

On Dec 19, 2:28 pm, mlhow...@avalon.net (Mary) wrote:
> Ryan,
>
> Certainly there is the Type III Sum of Squares that test whether the =
> additional variable given the other variables are already in the model =
> is significant.  How would a "deviance test" differ from this?  I took 6 =
> courses from SAS Institute in their Statistics curriculum and it was =
> never mentioned.
>
> -Mary
>
>
>
>   ----- Original Message -----=20
>   From: Ryan=20
>   To: SA...@LISTSERV.UGA.EDU=20
>   Sent: Wednesday, December 19, 2007 9:06 AM
>   Subject: Deviance Test?
>
>   Hello,
>
>   I was recently reading an article that stated that they ran a deviance
>   test to test "cohort effects." They were concerned because the
>   treatment was in a group setting, so each group was labeled a cohort.
>   The "treatment" variable had two levels (intervention and placebo,
>   both of which were administered in group settings). I believe they
>   used a Generalized Linear Modeling approach (commonly referred to as
>   GENMOD in SAS) to test if the treatment was effective on a continous
>   variable over time.
>
>   I've never heard of the term "deviance test" and after googling,
>   searching message boards, etc. I found a term called "Analysis of
>   Deviance" or ANODEV. According to what I read ANODEV measures whether
>   a variable is significantly predicting the DV above and beyond the
>   other variables in the model. You compare a full model to a reduced
>   model. I just do not see how that would answer whether cohort effect
>   (a categorical variable) on some variable of interest is significant.
>   Would you not run a nested model where groups are nested within
>   treatments?
>
>   Perhaps there is another deviance test I am not familiar with, or I am
>   simply not making the connection.
>
>   Any thoughts would be greatly appreciated.
>
>   Ryan- Hide quoted text -
>
> - Show quoted text -

It is the same test. It surprises me that this test was used to assess
group-within-treatments effects.