For this purpose, correspondence analysis was used to
facilitate the data analysis process as it is the most
appropriate method of analysis to quantify the more
qualitative and descriptive data commonly associated
with nominal variables. The correspondence analysis
can transform the nonmetric data to a metric-level form
and perform dimensional reduction to determine the
degree of association among variable categories. Corre-
spondence analysis was a statistical technique recently
developed which facilitates dimensional reduction and
conducts multidimensional scaling. It can be classified as
a compositional technique because it creates a percep-
tual map based on the association between objects and a
set of descriptive characteristics or attributes. Thus the
association is based on the attributes specified by the
researcher. Among the compositional techniques, factor
analysis is probably the most similar equivalent statis-
tical technique, but correspondence analysis has been
extended past the application of factor analysis. Its most
direct application is in portraying the ‘correspondence’
of categories of variables, particularly those measured in
nominal terms. This correspondence then becomes the
basis for developing perceptual maps or ‘pictures’. The
correspondence analysis is particularly useful to give a
more accurate picture on how multidimensional objects
are related to each other (Feng and Page, 2000).