Learn More
In the life sciences, many measurement methods yield only the relative abundances of different components in a sample. With such relative-or compositional-data, differential expression needs careful interpretation, and correlation-a statistical workhorse for analyzing pairwise relationships-is an inappropriate measure of association. Using yeast gene(More)
The application of hierarchic methods of classification needs to establish in advance some or all of the following measures: difference, central tendency and dispersion, in accordance with the nature of the data. In this work, we present the requirements for these measures when the data set to classify is a compositional data set. Specific measures of(More)
Phenomena with a constrained sample space appear frequently in practice. This is the case e.g. with strictly positive data and with compositional data, like percentages and the like. If the natural measure of difference is not the absolute one, it is possible to use simple algebraic properties to show that it is more convenient to work with a geometry that(More)
Condition is a central concept in evolutionary ecology, but the roles of genetic and environmental quality in condition-dependent trait expression remain poorly understood. Theory suggests that condition integrates genetic, epigenetic and somatic factors, and therefore predicts alignment between the phenotypic effects of genetic and environmental quality.(More)
1. ensure the research reported in Proportionality: a valid alternative to correlation for relative data is reproducible. This document was produced in RStudio using Sweave [1] and the knitr package [2] from the file SupplementaryInfo.Rnw available in the Supplementary Information zip file. 2. provide additional detail, figures and information for those(More)
A joint distribution of two discrete random variables with finite support can be displayed as a two way table of probabilities adding to one. Assume that this table has n rows and m columns and all probabilities are non-null. This kind of table can be seen as an element in the simplex of n · m parts. In this context, the marginals are identified as(More)
1. Abstract Instead of using indicator kriging to estimate discrete versions of cumulative distribution functions, with its order-relation problems, we suggest a compositional approach to the estimation of probability functions. A preliminary Bayesian treatment is needed to obtain estimates of the pdf (without zeroes) at sampled locations, and afterwards an(More)
  • 1