Centre for Person-Computer Studies

CSU (csu@brain.wph.uq.oz.au)
18 Aug 1994 12:28:32 -0500

Advice is sought regarding the interpretation of multidimensional
scaling output. Forty repertory grids (each consisting of 4
supplied and 6 elicited constructs and common elements)were
analysed using Alscal, the individual difference scaling option
in SPSS. Issues are, 1)selecting appropriate dimensionality and
2) confirming interpretations which have been made.
Re 1).
Two dimensions Three dimensions
Stress .237 .163
RSQ .775 .799

The 3 dimensionl model (3DMS) is better fitting,however Rsq shows
little improvement. Cluster analyses of the elements of
individual grids tends to support the separation of elements as
per the 2 dimensional solution (2DMS). A possible advantage of
the 3DMS is that there is greater separation of 5 elelements
which are clustered together in the 2DMS. The first two
dimensions in both options are highly correlated (.98 and .87,
and both solutions can be interpreted, though the third dimension
has a less definite interpretation eg there are two possible
interpretations. My inclination is to accept the two dimensional

Re 2) A regression using the 4 supplied constructs in the grid
as dependent variables and the subject weights as independent
variables did not result in any significant findings. G-Pack and
SPSS were used to examine high factor/pca loadings in individual
grids which might suggest recurring important constructs. The
other strategy has been to seek independent interpretation from
experienced clinicans to confirm my interpretations.

Comments on 1) and any suggestions regarding 2)(particularly
" objective " strategies) would be appreciated.
Bob Green.