Compositional PLS biplot based on pivoting balances: an application to explore the association between 24-h movement behaviours and adiposity

Nikola Štefelová (), Javier Palarea-Albaladejo (), Karel Hron (), Aleš Gába () and Jan Dygrýn ()
Additional contact information
Nikola Štefelová: Palacký University
Javier Palarea-Albaladejo: University of Girona
Karel Hron: Palacký University
Aleš Gába: Palacký University
Jan Dygrýn: Palacký University

Computational Statistics, 2024, vol. 39, issue 2, No 18, 835-863

Abstract: Abstract Movement behaviour data are compositional in nature, therefore the logratio methodology has been demonstrated appropriate for their statistical analysis. Compositional data can be mapped into the ordinary real space through new sets of variables (orthonormal logratio coordinates) representing balances between the original compositional parts. Geometric rotation between orthonormal logratio coordinates systems can be used to extract relevant information from any of them. We exploit this idea to introduce the concept of pivoting balances, which facilitates the construction and use of interpretable balances according to the purpose of the data analysis. Moreover, graphical representation through ternary diagrams has been ordinarily used to explore time-use compositions consisting of, or being amalgamated into, three parts. Data dimension reduction techniques can however serve well for visualisation and facilitate understanding in the case of larger compositions. We here develop suitable pivoting balance coordinates that in combination with an adapted formulation of compositional partial least squares regression biplots enable meaningful visualisation of more complex time-use patterns and their relationships with an outcome variable. The use and features of the proposed method are illustrated in a study examining the association between movement behaviours and adiposity from a sample of Czech school-aged girls. The results suggest that an adequate strategy for obesity prevention in this group would be to focus on achieving a positive balance of vigorous physical activity in combination with sleep against the other daily behaviours.

Keywords: Compositional data analysis; Logratio methodology; Balances; PLS regression and biplot; Time-use data; Adiposity (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s00180-023-01324-w Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:compst:v:39:y:2024:i:2:d:10.1007_s00180-023-01324-w

Ordering information: This journal article can be ordered from
http://www.springer.com/statistics/journal/180/PS2

DOI: 10.1007/s00180-023-01324-w

Access Statistics for this article

Computational Statistics is currently edited by Wataru Sakamoto, Ricardo Cao and Jürgen Symanzik

More articles in Computational Statistics from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().