The aim of the course is to provide an introduction to the analysis of multivariate data arising from observation and experimental studies with the R statistical software.
After completing the course, participants will
Active participation in the course including attendance at lectures and completion of computer-based classes and exercises. A learn-by-teaching approach will be used for the computer-based assessments, where each participant will be expected to, as part of a small group, demonstrate their approach to the analysis of a problem data set from the previous day. Completion of short, computer-based assessments testing their understanding of a topic and the practical skills taught.
The course is based on a series of lectures and computer based practical classes led by an international expert in the analysis of multivariate data, who is also one of the senior developers of the vegan R package and the creator of the permute R package.
The course covers the following topics:
This course is suitable for Phd students (including senior thesis-based masters students) and researchers working with multivariate data sets in biology (inter alia animal science, ecology, agriculture, microbial ecology/microbiology). Some basic prior knowledge of R is required.
Participants need to bring their own laptop with the latest version of R installed (version 4.2.0 or later), as well as the current version of RStudio. If you use another editor for your R code feel free to use it instead of Rstudio, but we cannot help you if you encounter problems with it.
You can download R from cloud.r-project.org and select from the three links at the top of the page as required for your operating system.
You can download RStudio from www.rstudio.com and choose from the list of installers as appropriate for your operating system.
If you have already installed R and RStudio, please check that they are both up-to-date. Within R you can run:
version
and look at the entry next to version.string:
r$> version
_
platform x86_64-pc-linux-gnu
arch x86_64
os linux-gnu
system x86_64, linux-gnu
status
major 4
minor 2.1
year 2022
month 06
day 23
svn rev 82513
language R
version.string R version 4.2.1 (2022-06-23)
nickname Funny-Looking Kid
This should include 4.2.1 if you are running the latest release, but should be no lower than 4.2.0. If the installed version of R is < 4.2.0, install a newver version of R by downloading and running one of the installers from cloud.r-project.org as mentioned above.
To check that RStudio is up-to-date, open RStudio, open the Help menu, and choose Check for Updates. RStudio will then check to see if there is a newer version available and if there is it will give you the option to download the newer version.
Prior to arriving at AU Viborg on the 19th of September, make sure you have updated your installed R packages and that you have installed the following packages: tidyverse, vegan, mvabund, boral, ecoCopula, and cocorresp. To do this, open RStudio (or R) and in the console window (usually lower left, with a prompt that looks like >) run
parallel::detectCores(logical = FALSE)
This checks to see how many CPU cores you have available, which we use in the next chunk.
update.packages(ask = FALSE, checkBuilt = TRUE, Ncpus = 4)
Change the value of Ncpus to the number cores you have on your computer as this will speed up package updates if you have many packages installed that require updating. If you want to work while this is being done, set Ncpus to a number less than that returned by parallel::detectCores(logical = FALSE).
Now we can install the required packages
install.packages(c("tidyverse", "vegan", "mvabund", "boral", "ecoCopula", "cocorresp"))
Gavin Simpson, Assistant Professor, Department of Animal Science, Aarhus University gavin@anivet.au.dk