Principal components analysis of descriptive sensory data; reflections, challenges and suggestions

This paper presents a discussion of principal components analysis of descriptive sensory data. Focus is on standardisation, many correlated variables, validation and the use of descriptive data in preference mapping. Different ways of performing the analysis are presented and discussed with focus on how to obtain informative and reliable results. The results will be commented on in light of experience. All methods will be illustrated by calculations based on real data. The paper ends with a list of suggestions for all the topics covered. Practical application: The paper is about using PCA in sensory science. The applicability of the methods and ideas presented in this paper are relevant for all types of descriptive sensory data. The ideas are general and comprise areas such as standardisation, validation and many correlated variables. The target group of readers for the paper is the sensory scientist who uses PCA on a daily basis and who may have questions regarding how to use the method the best possible way.