Neil wrote:
> This may sound like a silly question, but for those of you are
> familiar with Q-Sort Analysis / Q-Methodology, (a type of Factor
> Analysis), does someone know what the "Q" actually stands for? 
> 
> I have found many journal articles and websites on this analysis/
> methodology, but have not been able to find the above information in
> any of my sources. A definitive reference where this information can
> be found will help.
> 
> TIA

I initially thought Neil was talking about "Q-mode factor 
analysis", as did some other respondents.  David Garson 
describes Q-mode factor analysis as follows 
(http://www2.chass.ncsu.edu/garson/pa765/factor.htm):

------------------------------------------------------
Factor Analytic Data Modes

     * R-mode factor analysis. R-mode is by far the most 
common, so much so that it is normally assumed and not 
labeled as such. In R-mode, rows are cases, columns are 
variables, and cell entries are scores of the cases on the 
variables. In R-mode, the factors are clusters of variables 
on a set of people or other entities, at a given point of time.

     * Q-mode factor analysis, also called inverse factor 
analysis, is factor analysis which seeks to cluster the 
cases rather than the variables. That is, in Q-mode the rows 
are variables and the columns are cases (ex., people), and 
the cell entries are scores of the cases on the variables. 
In Q-mode the factors are clusters of people for a set of 
variables. Q-mode is used to establish the factional 
composition of a group on a set of issues at a given point 
in time.

       The Q-mode has the special problem of negative factor 
loadings. In conventional factor analysis of variables, a 
negative loading indicates a negative relation of the 
variable to the factor. In Q-mode factor analysis, a 
negative loading does not have a clear meaning. One common 
approach is to consider all cases with negative loadings as 
being in a cluster of their own. Some researchers consider 
Q-mode factor analysis suspect due to negative loadings, the 
possibility of singularities (columns with the same values), 
and ranking problems. Most researchers prefer to use a more 
accepted technique, such as some form of cluster analysis.
------------------------------------------------------

But I don't think this is what Neil was talking about.  The 
following is from David Clark-Carter's book (reference given 
below), in a section called "Techniques to Measure Meaning" 
(p. 97):

"Q-methodology is an approach to research which was devised 
by Stephenson (1953). It requires participants or judges to 
rate statements or other elements on a given dimension or on 
a given basis.  One technique which Q-methodology employs is 
getting participants to perform Q-sorts. Typically a Q-sort 
involves participants being presented with a set of 
statements, each on an individual card, and being asked to 
place those statements on a dimension, such as /very 
important to me/ to /not imporant to me/." etc

Clark-Carter refers to Kerlinger (1973), and says that 
"[Carl] Rogers (1951, 1961) has used Q-sorts in the context 
of counselling."

Here's the Clark-Carter book info:

Clark-Carter, D. (1997). Doing quantitative psychological 
research: From design to report. East Hove, Sussex: 
Psychological Press.

Cheers,
Bruce
-- 
Bruce Weaver
[EMAIL PROTECTED]
www.angelfire.com/wv/bwhomedir/

.
.
=================================================================
Instructions for joining and leaving this list, remarks about the
problem of INAPPROPRIATE MESSAGES, and archives are available at:
.                  http://jse.stat.ncsu.edu/                    .
=================================================================

Reply via email to