Year: 2025
Type: article
Abstract: In many research fields, it is quite common to deal with multiple data sets containing information about the same group of individuals, where one data set aims to explain the others. To address this need, a new multiway regression method called Binary 3-way PARAFAC Partial Least Squares (Bin-3-Way-PARAFAC-PLS) is introduced. This method is specifically designed for the case where a three-way real-valued data array serves as the explanatory role, together with a matrix of binary response data. An algorithm implementing this method is provided, along with its practical application. Additionally, biplot representations are described to assist in the interpretation of the results. The software necessary to implement the method is also provided. Finally, the proposed method is applied to a data set from psychology to demonstrate its usefulness in addressing real-world problems.
Source: Axioms
Institutions: Universidad de Salamanca, Universidad Rey Juan Carlos
Language: English
Subfield: Computational Mathematics
Field: Mathematics
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $2,896
OpenAlex ID: W4413958459