Compositional data analysis in epidemiology
- 6 October 2016
- journal article
- research article
- Published by SAGE Publications in Statistical Methods in Medical Research
- Vol. 27 (6), 1878-1891
- https://doi.org/10.1177/0962280216671536
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.Keywords
This publication has 19 references indexed in Scilit:
- Linear regression with compositional explanatory variablesJournal of Applied Statistics, 2012
- On the Interpretation of Orthonormal Coordinates for Compositional DataMathematical Geosciences, 2011
- Principal component analysis for compositional data with outliersEnvironmetrics, 2009
- Outlier Detection for Compositional Data Using Robust MethodsMathematical Geosciences, 2008
- Application of Robust Statistical Methods for Sensitivity Analysis of Health-Related Quality of Life OutcomesQuality of Life Research, 2006
- Groups of Parts and Their Balances in Compositional Data AnalysisMathematical Geology, 2005
- Biplots of Compositional DataJournal of the Royal Statistical Society Series C: Applied Statistics, 2002
- Unmasking Multivariate Outliers and Leverage PointsJournal of the American Statistical Association, 1990
- High Breakdown-Point and High Efficiency Robust Estimates for RegressionThe Annals of Statistics, 1987
- The biplot graphic display of matrices with application to principal component analysisBiometrika, 1971