Compositional data analysis in epidemiology. (June 2018)

• Record Type: Journal Article
• Authors: Mert, Mehmet C; Filzmoser, Peter; Endel, Gottfried; Wilbacher, Ingrid
• Is Part Of: Statistical methods in medical research. Volume 27:Number 6(2018)
• Page Start: 1878
• Page End: 1891
• Publication Date: 2018-06
• Subjects: Log-ratio approach -- multivariate statistics -- Euclidean geometry -- compositional data -- isometric log-ratio coordinates; Medicine -- Research -- Statistical methods -- Periodicals; Research -- Periodicals; Review Literature -- Periodicals; Statistics -- methods -- Periodicals; Médecine -- Recherche -- Méthodes statistiques -- Périodiques; 610.727
• DOI: 10.1177/0962280216671536
• Languages: English
• ISSNs: 0962-2802

Abstract

Compositional data analysis refers to analyzing relative information, based on ratios between the variables in a data set. Data from epidemiology are usually treated as absolute information in an analysis. We outline the differences in both approaches for univariate and multivariate statistical analyses, using illustrative data sets from Austrian districts. Not only the results of the analyses can differ, but in particular the interpretation differs. It is demonstrated that the compositional data analysis approach leads to new and interesting insights.