1982
DOI: 10.1111/j.2517-6161.1982.tb01195.x
|View full text |Cite
|
Sign up to set email alerts
|

The Statistical Analysis of Compositional Data

Abstract: Summary The simplex plays an important role as sample space in many practical situations where compositional data, in the form of proportions of some whole, require interpretation. It is argued that the statistical analysis of such data has proved difficult because of a lack both of concepts of independence and of rich enough parametric classes of distributions in the simplex. A variety of independence hypotheses are introduced and interrelated, and new classes of transformed‐normal distributions in the simple… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

8
2,446
0
23

Year Published

1990
1990
2018
2018

Publication Types

Select...
10

Relationship

0
10

Authors

Journals

citations
Cited by 2,370 publications
(2,641 citation statements)
references
References 45 publications
8
2,446
0
23
Order By: Relevance
“…Afterwards, a multiple linear regression was done using the stepwise method to determine if the explanatory variables measured (growth ring characteristics, mechanical, and physical properties) were good predictors of the weighted mean chip thickness. A multivariate analysis of variance (MANOVA) was performed using the Aitchison approach of compositional data (Aitchison 1982) for the Domtar and Williams chip class distributions. Growth ring characteristics, mechanical, and physical properties were used as covariates, keeping only the ones that were significant for the model.…”
Section: Statistical Analysesmentioning
confidence: 99%
“…Afterwards, a multiple linear regression was done using the stepwise method to determine if the explanatory variables measured (growth ring characteristics, mechanical, and physical properties) were good predictors of the weighted mean chip thickness. A multivariate analysis of variance (MANOVA) was performed using the Aitchison approach of compositional data (Aitchison 1982) for the Domtar and Williams chip class distributions. Growth ring characteristics, mechanical, and physical properties were used as covariates, keeping only the ones that were significant for the model.…”
Section: Statistical Analysesmentioning
confidence: 99%
“…For example, the fact that a species consumes two-thirds insects constrains its seed consumption to be less than or equal to one-third. Special transformations are needed to account for this non-independence (Aitchison 1982). We used the "rcomp" function in the "compositions" package in R (v.2.6.0) to run a compositional principal components analysis (PCA).…”
Section: Diet Classiwcationmentioning
confidence: 99%
“…All variables were arcsine transformed and only three of six possible behaviors were used in the analysis. This reduced potential problems of dependence between behavior categories (Aitchison 1982). The behavior of the control fish was included as an additional independent variable in these analyses.…”
Section: Removal Experimentsmentioning
confidence: 99%