Identifying outlying assessors in sensory profiling using fuzzy clustering and multi-block methodology

In this paper we discuss methods for detecting outlying assessors in descriptive sensory analysis. A new method is proposed which is based on fuzzy clustering with the use of the noise cluster method. The technique ends up with a plot which can be used to provide information about which assessors that are different from the rest and also to suggest reasons why the assessors are different. The method is based on data compression by the use of either Tucker-1 or Tucker-2 for multi-block data. The technique is used on a dataset based on an oxidation experiment of cheese. There are 9 trained and 3 untrained assessors in the panel.