In sensory evaluation, principal component analysis (PCA) is often used to explore differences between products. In some studies, there is one control product (e.g. a reference or benchmark) and many test products, where test-control paired differences are of primary interest. We discovered there are two equivalent ways to investigate these results using PCA. The first approach is a centred PCA
This tutorial surveys some of the most frequently used methods for exploring multivariate data sets fromsensory and consumer science. Component-based methods are often applied for data reduction andvisualization of results.The tutorial is divided into three parts.In Part 1, we contrast principal component analysis (PCA) with principal variable analysis, then discussmultiple factor analysis (MFA), which is often used to investigate multiblock
Relationships between sensory and instrumental variables are often investigated using partial least squares regression (PLSR). We describe the conventional PLSR solution. Next, we describe two new approaches for conducting PLSR based on paired comparisons of objects. First, we describe the PLSR of all paired comparisons. Conducting PLSR of all paired comparisons is equivalent to the conventional solution in the sense
Test-control paired comparisons can be investigated after principal component analysis (PCA). We show that a centred PCA of test-control paired comparisons is equivalent to an uncentred PCA of control-centred results. We demonstrate how to conduct these analyses. We illustrate key properties of centred and uncentred PCA. We justify why coordinates of control-centred results can be visualized in principal components obtained
Principal component analysis (PCA) is a popular technique for summarizing and exploring multivariate data sets. We propose how to conduct PCA of results from sensory studies that have a special structure, where only a subset of the product paired comparisons are of interest. We illustrate the proposed approach with two data sets, both from trained sensory panels. In the first
Principal component analysis (PCA) is often used to summarize and explore multivariate data sets, including sensory evaluation data sets. We propose how to conduct PCA of a results matrix in which only a subset of the paired comparisons is of interest. We illustrate the proposed approach with two data sets, both from trained sensory panels. In the first example, assessors
We propose and evaluate numerical and visual methods for investigating paired comparisons after principal component analysis (PCA). PCA results can be visualized to facilitate an understanding of the relationships between the products and the sensory attributes. But identifying and visualizing significant product differences in multiple PCs simultaneously is not straightforward. A benefit of the proposed methods is that they provide