Investigating control-centred results after uncentred principal component analysis
This study examines how to carry out test-control paired comparisons after performing principal component analysis (PCA). Different approaches are proposed here, involving either centred or uncentred PCA, and their respective key properties are highlighted. In particular, we show centred PCA of test-control paired comparisons is equivalent to uncentred PCA of control-centred paired differences. It is customary to use a column-centred PCA, but we justify why results from this uncentred PCA better investigate the test-control paired comparisons. In addition, the benefit of situating the control product at the origin of score plots is emphasized. The proposed methods are illustrated using a sensory quantitative descriptive analysis dataset involving a control product and nine test product formulations.
Castura, J. C., Cariou, V., & Næs, T. (2024). Investigating control-centred results after uncentred principal component analysis. Zenodo. https://doi.org/10.5281/zenodo.11496201