Related Experiment Video
Updated: Nov 19, 2025

The Terroir Concept Interpreted through Grape Berry Metabolomics and Transcriptomics
Published on: October 5, 2016
Exploration of geochemical data with compositional canonical biplots
Jan Graffelman1,2, Vera Pawlowsky-Glahn3, Juan José Egozcue4
1Department of Statistics and Operations Research, Universitat Politècnica de Catalunya, Avinguda Diagonal 647, Barcelona 08028, Spain.
This study introduces compositional canonical correlation analysis (CoDA-CCO) to explore relationships in geochemical data. CoDA-CCO, using log-ratio transformations and biplots, effectively reveals key compositional associations.
Area of Science:
- Geochemistry
- Statistical Analysis
- Data Science
Background:
- Analyzing relationships between multiple chemical compositions is crucial in geochemistry.
- Traditional methods may not adequately handle the complexities of compositional data.
Purpose of the Study:
- To develop a compositional approach to canonical correlation analysis (CoDA-CCO).
- To introduce and evaluate compositional canonical biplots for visualizing compositional relationships.
Main Methods:
- Utilized centered log-ratio (CLR) and pairwise log-ratio transformations.
- Employed generalized inverses to handle structurally singular covariance matrices.
- Developed and analyzed compositional canonical biplots.
Main Results:
- CoDA-CCO effectively identifies salient relationships between geochemical compositions.
- Compositional canonical biplots provide powerful visualization tools.
- Demonstrated the utility of the method on a European floodplain dataset.
Conclusions:
- The proposed CoDA-CCO method offers a robust framework for analyzing compositional data in geochemistry.
- Compositional canonical biplots are effective for exploring complex multivariate relationships.
More Related Videos
Related Concept Videos
Arrhenius Plots
The Arrhenius equation can be used...
Phase Diagrams
What are Biogeochemical Cycles?
Plotting of Topographic Maps
Modified Boxplots
However, the box plot does not tell the reader about outliers - values that lie far from the center of the data. We can modify the standard box and whisker plot to identify the outliers and visualize the actual spread of the data in a sample.
Initially, we calculate the adjusted...
pV-Diagrams

