>Tony Downing wrote (in part) in response to,
>
>>Devi Jancowicz's prompt reply to Suzanne
that for
>> those constructs that
>>re-emerge with the same labels on the second occasion, do a matrix
>>subtraction of the ratings for Time 2 from the ratings for Time 1. I'm
>>still not quite gettng my head round the status of the resulting numbers,
>>though. If we process the grid in the usual way, doing either hierarchical
>>cluster analysis or principal components analysis, what will it mean?
>
and Devi went on to say
> Richard Bell should have something
>interesting to say on all this.
Sorry, Devi, nothing really interesting but -
I must admit I would never be too sure about what was happening in a series
of difference scores. The differences could be due to:
i) Shifts in specific element locations on specific constructs
ii) General shifts in constructs
iii) General shifts in elements
iv) Shifts in construct structures
v) Shifts in element structures
vi) All of the above
The Row & Slater chapter 8 in Patrick Slater's 1976 book Explorations of
Intrapersonal Space shows a pretty systematic evaluation of change in
perfectly replicated grids. I think one could use parts of their strategy
to look at some of the sources of possible differences in the present
situation though
Richard
Richard C. Bell
Associate Professor
Department of Psychology
University of Melbourne
Parkville Vic 3052 Australia
ph: +61 3 9344 6364
fax: +61 3 9347 6618
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%