by Ralf B. Schäfer, University of Koblenz-Landau, Winter Semester 2022/23
This repository provides all course materials including R code, slides and data as well as the links to teaching videos. Note that all material comes without guarantee! In case you have any comments regarding content, please feel free to contact me, but note that I generally do not respond to computer issues or questions for statistical advice (unless working on a joint publication).
To prepare your computer for the lecture, you need to install R and R Studio. I use several packages in the course, if you want to have all packages ready at the beginning of the course, run the script 0_install_packgs.R in the Code folder. Note that the course is work in progress and you should run this script again from to time to time to be up to date with the packages required. Alternatively, you can just install a new package whenever it is needed:
install.packages("package_name")
Session 1: Introduction to data analysis
Session 3: Assessing hypotheses and simulation-based tools
Session 4: ANOVA, ANCOVA, multiple regression and interactions
Session 5: Multiple regression: Modelling strategies
Session 7: Unsupervised learning: CART
Session 8: Principal component analysis
Session 9: Redundancy analysis, Similarity measures, NMDS and multivariate GLMs
(university account required, choose these links if you are student of the university)
Session 3: Assessing hypotheses and simulation-based tools
Session 4: ANOVA, ANCOVA, multiple regression and interactions
Session 5: Multiple regression: Modelling strategies
Session 9: Multivariate gradients tutorial
(no university account required, choose these links if you are in an online study program without university account or for general access)
Session 3: Assessing hypotheses and simulation-based tools
Session 4: ANOVA, ANCOVA, multiple regression and interactions
Session 5: Multiple regression: Modelling strategies
Session 9: Multivariate gradients tutorial
- Noel Juvigny-Khenafou is thanked for replacing me in teaching this lecture and dealing with the students (I was given partial teaching relief to join university management in the merger process with the TU Kaiserslautern).
- Achim Zeileis is thanked for development and support with the R exams package that is used for automated test generation in this course. Felix Högerl is thanked for help with exam evaluation.
- and of course a huge thanks to all the package authors and the whole R community as well as the stackexchange and stackoverflow community.