Factor analysis with principal components extraction was used to reduce the number of
variables to a set of independent factors. The “varimax” rotation method was used in the
principal component analysis to ensure that the factors are orthogonal to each other, thus
making them suitable for use in logistic regression. The suitability of the data for factor
analysis was assessed and two variables (“boring people” and “prestige”) were identified
with loadings of more than 0.40 for at least two components denoting that each has a
complex structure. Consequently, these two variables were omitted in the reported
factor analysis shown in Table III (Field, 2009). In addition, a cut off score of 0.46 was
employed to ensure that only variables that significantly loaded into a component
were included in the factor analysis. As a result, the variable “no satisfaction” was
removed and a principal component analysis was run with 12 of the 15 original
variables.