Your CIOS file request: Q-METHOD/06099090.420 hotline item

-
Received:  by CIOS Mailer; Tuesday 9 Jun 2009 09:04:20
Date:         Tue, 9 Jun 2009 15:03:07 +0200
From:         Peter Schmolck 
Subject: Re: Consensus statements
To:           Q-METHOD@LISTSERV.KENT.EDU
List-Help: ,              
List-Unsubscribe: 
List-Subscribe: 
List-Owner: 
List-Archive: 

On 09.06.2009 12:25, Louise Bryant wrote:
> Dear all,
> 
> Can someone explain why the consensus statements output (i.e. those
> that do not distinguish between any pair of factors) are not always
> the same ones as those at the top of the "Statements sorted by
> Consensus vs. Disagreement" output?

Different approaches, simplified in short: overall level of factor score 
variability across factors vs. maximal pairwise difference between any 
two factor scores is insignificant.
The long story is that I once created the "Statements sorted by 
Consensus vs. Disagreement" table as a substitute for an earlier, 
unsuccessful implementation of the consensus-statements table. The 
problem for John Atkinson and me was to understand that the consensus 
statements were not just those that did not qualify as "Distinguishing 
Statements" for any factor. Brain-teasing exercise on the meaning of 
non-significance at .05 and .01. ;^)
Peter


-- 
Peter Schmolck   http://www.unibw.de/paed/esf-en/pers/schmolck