Date:         Tue, 6 Jun 2006 15:12:23 -0400
Reply-To:     "jakeboot@gmail.com" <jakeboot@GMAIL.COM>
Sender:       "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From:         "jakeboot@gmail.com" <jakeboot@GMAIL.COM>
Subject:      Re: Clinical Trial Ns for Multiple Arms
Comments: To: Kevin Roland Viel <kviel@emory.edu>
In-Reply-To:  <Pine.GSO.4.58.0606061457420.3058@leukothea>
Content-Type: text/plain; charset=ISO-8859-1; format=flowed

Yes, this is ITT, and the question is general in that is there one reason to
do one over the other. That is, what are the differences and ramifications.

On 6/6/06, Kevin Roland Viel <kviel@emory.edu> wrote:
>
> On Tue, 6 Jun 2006, jakeboot@gmail.com wrote:
>
> > I have a general question about multiple arm studies, specifically when
> a
> > patient switches doses --how to count the Ns.  It seems that if a
> subject
> > switches doses, that the subject should be counted in each treatment
> group.
> > Is there a standard for this such that the subject is counted in each
> dosage
> > the subject is on vs. the Ns are the same for each dose (thus reflecting
> the
> > overall Number of Subjects (regardless of dose)?
> >
> > Any information on this is appreciated.
>
> Jake,
>
> Have you considered an "intention to treat" analysis?  Under this
> scenario, the treatment arm into which you randomly assigned the subject
> is the analyses group regardless of treatment.
>
>
> HTH,
>
> Kevin
>
> Kevin Viel
> Department of Epidemiology
> Rollins School of Public Health
> Emory University
> Atlanta, GA 30322
>



--
Jake
---------------------
Change the way you look at things, and the things you look at will change.
Dr. Dyer