Title: Analysis of multi-factorial compositional data main principles and perspectives
Authors: Kamila Facevicova - Palacky University Olomouc (Czech Republic) [presenting]
Peter Filzmoser - Vienna University of Technology (Austria)
Karel Hron - Palacky University Olomouc (Czech Republic)
Abstract: Compositional data are in their traditional setting understood as vector observations of positive entries. This means, that the observations carry information about the relative structure given by levels of one factor. The contribution will focus on a more complex situation where the structure is given by two or more determining factors. The two-factorial case is already thoroughly described in the literature and can be found under the keyword compositional tables. It turns out that the main findings of the geometrical structure of tables and their coordinate representation can be further extended to the multi-factorial case. The presentation brings an overview of the current state of knowledge in the field of analysis of multi-factorial compositional data. The theoretical principles will be followed by practical examples and, finally, perspectives of the further research in the field will be discussed.