layeranalyzer v0.1.0

This is an R package for causal and correlative time series analysis with hidden layers, using linear stochastic differential equations. The project's Github page is https://github.com/trondreitan/layeranalyzer.

In addition to the R package itself, this page presents the C++ code (used in a standalone program as well as the R package), documentation and example datasets and code for multi-layered analysis using vectorial linear stochastic differential equations. The reason for using stochastic differential equation is to facilitate studying irregularly spaced observations like those we find in our study dataset of micro-fossils. This work was performed in conjuction with doing the research for and writing the manuscript "Phenotypic Evolution studied by Layered Stochastic Differential Equations" by T. Reitan, T. Schweder and J. Henderiks.

Originally, this was used for modelling phenotypic evolution towards a optima that itself could be a stochastic process depending responding to layers below it (climate or primary optimum). However, the method have be used for other applications as well.

Code:

• The R package, layeranalyzer_0.1.0.tar.gz, uses the same underlying C++ code (layeranalyzer.cpp). It can be installed with the R code: install.packages("https://github.com/trondreitan/layeranalyzer/raw/master/layeranalyzer_0.1.0.tar.gz",type="source") or install_github(repo="trondreitan/layeranalyzer",dependencies=FALSE,build_vignettes=TRUE) if devtools is installed.

• layeranalyzer.cpp. This is the current source version of the program. This version does not depend on any library but the Lapack library (for linear algebra operations), which typically can be found in an R installation. The program can then typically be compiled on a Linux machine like this: "g++ -DMAIN -DENGLISH_LANGUAGE -I/usr/include/R -I/usr/include/R/R_ext -o layeranalyzer layeranalyzer.cpp -lm -llapack". If the Lapack library files or header files are somewhere else on your computer, you should change the "-I" (which tells the compiler where to look for header files) and "-L" (which tells the compiler where to search for library files other than in the /usr/lib directory). This has already been tested on multiple platforms. See "help" texts on Github for more on usage.