Zum Inhalt springen
Technische Universität München

TUM|Stat Kurse

Die Statistikberatung der Technischen Universität München, TUM|Stat, bietet verschiedene Statistik-Kurse an. Alle Kurse nutzen die Benutzeroberfläche RStudio und zeigen auch, wie man mit R Markdown-und/oder Quarto Dokumenten arbeitet.

Die TUM|Stat Kurse sind in erster Linie Teil des Kursprogramms der TUM Graduate School oder eines TUM Graduate Centers. Wenn Ihre Forschungsgruppe einen der Kurse besuchen möchte, wenden Sie sich an TUM|Stat.

R for data science

In this learning-by-doing course, the participants will be introduced to how to get started in R. In particular, the course will give a guide into the tidyverse, a collection of R packages designed for data science. After introducing each topic, the participants will work on hands-on exercises.

Topics:

  • introduction to R and the RStudio IDE
  • import/export data using readr
  • data management using dplyr
  • visualisation using ggplot2
  • creating tidy tibbles with tidyr and tibble
  • basic ideas about programming - how to write functions in R, how to do loops efficiently
  • importing data - special topics

In addition, the course will show how to do reproducible research by using R. Therefore, we will use the knitr and rmarkdown packages.

Trainer: Stephan Haug

Duration: 15 hours

Pre-course preparations:

Literature:

  • Wickham, H.,  Cetinkaya-Rundel, M., and Grolemund, G.  (2023). R for Data Science (2nd ed.). O'Reilly Media.

Using R for regression analysis

In this learning-by-doing course, the participants will receive an introduction on how to do regression analysis in R. After introducing each topic, the participants will work on hands-on exercises.

Topics:

  • linear regression models
  • generalised linear regression models
  • ordinal regression models
  • linear mixed-effects models
  • multiple comparisons in linear (mixed) models

In addition, the course will show how to do reproducible research by using R. Therefore, we will use the knitr and rmarkdown packages.

Trainer: Stephan Haug

Duration: 15 hours

Pre-course preparations:


Prerequisites: You should understand basic concepts of statistical inference, such as hypothesis testing and parameter estimation, along with fundamental R skills like working with data frames, importing data, and executing functions.

Literature:

  • Agresti, A. (2002). Categorial Data Analysis. John Wiley & Sons.
  • Christensen, R.H.B. (2018). Cumulative Link Models for Ordinal Regression with the R Package ordinal.
  • Everitt, B.S. and Hothhorn, T. (2006). A Handbook of Statistical Analyses Using R. Chapman & Hall/CRC.
  • Fahrmeir, L., Kneib, T., Lang, S. and Marx, B. (2013). Regression - Models, Methods and Applications. Springer.
  • Field,A., Miles, J. and Field, Z. (2012). Discovering Statistics Using R. SAGE Publications.
  • Gałecki, A. and Burzykowski, T. (2013). Linear Mixed-Effects Models Using R - A Step-by-Step Approach. Springer.
  • Grolemund, G. and Wickham, H. (2016). R for Data Science. O'Reilly Media.
  • Wickham, H. (2009). ggplot2. Elegant Graphics for Data Analysis. Springer.

Using R for statistical data analysis

In this learning-by-doing course, the participants will receive an introduction on how to use R for statistical data analysis. After an introduction to each topic, the participants will work on hands-on exercises.

Topics:

  • introduction to R and the RStudio IDE
  • import/export data
  • data management using dplyr
  • visualisation using ggplot2
  • hypothesis testing in R using infer
  • introduction to regression analysis in R

In addition, the course will show how to do reproducible research by using R. Therefore, we will use the knitr and rmarkdown packages.

Trainer: Stephan Haug

duration: 14 hours

Pre-course preparations:

Literature:

  • Grolemund, G. and Wickham, H. (2016). R for Data Science. O'Reilly Media.
  • Ismay, C. and Kim, A.Y. (2019). Statistical Inference via Data Science: A ModernDive into R and the Tidyverse. CRC Press.
  • Wickham, H. (2009). ggplot2. Elegant Graphics for Data Analysis. Springer.

Design and analysis of experiments

In this course, the participants will receive an introduction to the basic steps of designing and analysing experiments. Most of the steps are illustrated using R.

Topics:

  • introduction to the idea of DoE
  • screening designs
  • fractional and full factorial designs
  • ANOVA
  • response surface methods

Trainer: Stephan Haug

Duration: two to three hours

Literature:

  • Lawson, J. (2015). Design and Analysis of Experiments with R. Wiley.
  • Montgomery, D.C. (2009). Design and Analysis of Experiments. Wiley.
  • Siebertz, K., van Bebber, D., und Hochkirchner, T. (2010). Statistische Versuchsplanung - Design of Experiments. Springer.
To top