Abstract
The statistical analysis of compositional data based on logratios of parts is commonly used in geological studies. In particular, descriptive methods of reduction of dimensionality as the biplot or Principal Component Analysis are very useful tools in a multivariate context. These methods are difficult to use correctly with compositional data in standard packages. In this paper we describe a freeware package, named CoDaPack, which implements most of the basic statistical methods suitable for compositional data. An example using real data is presented to illustrate the use of the package.
| Original language | English |
|---|---|
| Pages (from-to) | 773-793 |
| Number of pages | 21 |
| Journal | Mathematical Geology |
| Volume | 37 |
| Issue number | 7 |
| DOIs | |
| Publication status | Published - Oct 2005 |
Keywords
- Aitchison geometry
- Atypicality index
- Logratio transformation
- Outliers
- Perturbation
- Principal components
- Simplex
- Ternary diagram
Fingerprint
Dive into the research topics of 'Dealing with compositional data: The freeware CoDaPack'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver