Three-way Principal Component Analysis for the Visualization of Trace Elemental Patterns in Vegetables after Different Cooking Procedures

Studies on the nutritional content of foodstuffs often lead to large or complex data sets. The situation described here is complex in the sense that the table has a three-way structure (elemental content×type of vegetable×cooking style) and the question is to find the main trends in this data. The use of three-way principal component analysis (PCA) is proposed for this purpose and compared with the use of the better known two-way PCA. How vegetables can be classified according to their elemental content and the effect of cooking style on that content are shown. It is concluded from this example that three-way PCA can be a useful tool in the analysis of nutritional tables.