2.2. Principal component analysis
The wide variability in citrus blossom volatile composition
shown in Table 2 was unanticipated. In order to examine this large
data set without having to assign classifications ahead of time,
principal component analysis (PCA) was employed. It is an unsupervised
learning technique used to determine hidden structure
(associations) in large data sets and to determine those volatiles
which were most differentiating.