426 Computational Modelling of Biomechanics and Biotribology
Unfortunately, it is impossible to capture the interrelationship of the param-
eters on the variability of the model response. Principal component anal-
yses enable the combination of variables that are interrelated by a single
variable, thereby reducing the complexity of the system. During a principal
component analysis, a new set of variables (principal components) is cre-
ated, but each principal component is a linear combination of the original
variables, and they are also orthogonal to each other thereby resulting in no
redundancy.
The rst principal component is a single axis in space (eigenvector of the
matrix of variables). Projection of the results on this axis results in ...