ANOVA-principal component analysis and ANOVA-simultaneous component analysis: a comparison

ANOVA–simultaneous component analysis (ASCA) is a recently developed tool to analyze multivariate data. In this paper, we enhance the explorative capability of ASCA by introducing a projection of the observations on the principal component subspace to visualize the variation among the measurements. We compare the significance of experimental effects for ASCA and ANOVA–principal component analysis (PCA), a similar tool to explore multivariate data, by using permutation tests. Furthermore, we quantify the quality of the loadings estimate obtained with ASCA and compare this with the loadings estimate obtained with ANOVA–PCA. Copyright © 2011 John Wiley & Sons, Ltd. This work presents an enhancement of ANOVA‐simultaneous component analysis by projecting the observations onto the principal component subspace, thus allowing the visualization of the variation of the measurements. Furthermore, using a synthetic data set, a comparison is made between the significance of experimental effects and the quality of estimated loadings for ANOVA‐simultaneous component analysis and ANOVA‐principal component analysis.