Three-Mode Principal Components Analysis of Semantic Differential Data: The Case of a Triple Personality

This paper shows how three-mode principal compo-nents analysis can be useful for the analysis of seman-tic differential ratings, in particular because no sum-mation is necessary over any one mode. The use of "joint plots " (a variant of the biplot) and sums-of-squares interpretations is explained and illustrated. The aim of this paper is to show the power of three-mode principal components analysis in con-structing one unified description of data collected under different circumstances, but referring to the same underlying structure. This is illustrated with data from probably the most famous case of a mul-tiple personality: Eve White, Eve Black, and Jane (Thigpen & Cleckley, 1954). Osgood and Luria (1954/1969) published scores on semantic differ