期刊名称：Electronic Journal of Applied Statistical Analysis
电子版ISSN：2070-5948
出版年度：2012
卷号：5
期号：3
页码：400-405
DOI：10.1285/i20705948v5n3p400
语种：English
出版社：University of Salento
摘要：The object of these short notes is to give a set of convenient symbols to define the sample space for the different compositional vectors that can be arranged into a three-way array. For the exploratory analysis of three-way data, Parafac/Candecomp and Tucker3 are some of the most applied models for low-rank decomposition of three-way arrays. Here, in addition to the relative geometry, is presented a concise overview as to how the elements of a three-way array can be transformed into compositional form and the relative geometry is given.
Loading...
