K-means cluster analysis was then run using the three cluster
centres that were shown by the hierarchical analysis as the initial
seed points. The final cluster centres were then examined in order
to label the clusters (see Table 3 below). An ANOVA was performed
to examine the differences between the mean factor scores
of each cluster according to their responses to each variable in the
factor solution (Table 4). A Tukey HSD post-hoc test was used to determine
where these differences lie, which showed that there were
differences in cluster means for all factors other than ‘Value of
Produce’ (for which clusters 2 and 3 did not differ significantly)