Re: PCA analysis of rep grids

Richard Bell (rcbell@rubens.its.unimelb.edu.au)
Thu, 06 Mar 1997 11:28:59 +1100


At 10:11 AM 3/5/97 +0000, you wrote:
>I'm investigating using PRINCALS for rep-grids. This allows appropriate
level of representation for different levels of measurement.
>see a conference paper at
>http://s-tagg.market.strath.ac.uk/princals/princals.htm

An interesting paper. Of course to go one step simpler and use the ANACOR
procedure would be identical (I hope) with the Feixas & Cornejo GRIDCOR
program. One thing I have found useful when considering the data as ordinal
is to use the monotone regression estimates (QUANTIFICATION) as an indicator
of the range of convenience of a construct.

Peter Caputi (University of Wollongong) gave a paper at the Australian
Psychological Society Conference in 1994 comparing PRINCALS (actually the
SAS equivalent) with traditional principal component solutions for a grid

Richard Bell
Richard C Bell
Department of Psychology
University of Melbourne
Parkville Vic 3052 Australia
Phone: +61 (0)3 9344 6364
Fax: +61 (0)3 9347 6618

%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%