temporalEF is an R package that computes eigenfunctions for use in explaining patterns in multivariate time series. The basic idea is taken from recent developments in the field of spatial analysis in multivariate data sets.
Principal coordinates of neighbour matrices (PCNM) and the more recent Asymmetric eigenvector maps (AEM) were designed to model variation at multiple spatial scales. temporalEF utilises these methods by taking the time direction as a one-dimensional spatial process. The resulting eigenfunctions represent sinusoidal functions of varying periodicity.
The resulting eigenfunctions can be used in constrained ordinations such as redundancy analysis (RDA), canonical correspondence analysis (CCA), or constrained analysis of principal coordinates (CAP) to decompose a species data matrix into independent patterns of temporal variation or trends.
The simplest way to install temporalEF is to use the devtools package
devtools::install_github("gavinsimpson/temporalEF")
temporalEF is made available under the GNU GPL version 2 licence.
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.