Parallel co-ordinate geometry and principal component analysis for the interpretation of large multi-response experimental designs

In the evaluation of large or complex data sets the use of visualization methods can be of great benefit. In this paper, the use of parallel co-ordinate geometry (PCG) plots, principal component analysis (PCA) and N-way PCA as visualization procedures for large multi-response experimental designs was compared with the more traditional approach of calculating factor effects by multiple linear regression. PCG plots are a recent addition to the visualization tools and offer a possibility to visualize multi-dimensional data in two dimensions while no calculations are required. It was found that PCA and PCG each have their own benefits and disadvantages. Both methods can be used to some extent to select optimal conditions. Moreover, it was possible to use the PCA score plot as a Pareto optimality plot that allowed to select the experiments considered to be Pareto optimal. Therefore, the examined visualization methods can be useful and complementary aids in the interpretation of large multi-response experimental design data and they add a multivariate dimension to the more classical univariate analysis of such data.