PULS
Foto: Matthias Friel
Abstract
The primary goal of the colloquium is to teach transparent and reproducible workflows for research data management and statistical analysis using the free R programming language for statistical computing and graphics and the RStudio environment. The basic idea is that transparent data management anticipates the data representation needed for statistical analyses and modeling. A transparent representation of data greatly facilitates the specification of statistical models that are appropriate for the data; in other words, it effectively prevents the specification of incorrect statistical models. The secondary goal of the colloquium is to introduce some multivariate statistical analyses. However, the extent and amount of time spent on the secondary goal depends on how fast the primary goal is reached, that is it depends on students’ background and success in achieving the primary goal.
Meeting times
The colloquium will take place om seven Fridays from 8:15-9:45 and 10:15-11:45 in a hybrid format. The exact dates are: 22.04. (zoom), 29.04. (zoom), 13.05 (UNIP), 20.05 (UNIP), 10.06. (UNIP), 01.07. (zoom), 22.07. (UNIP).
Expected learning outcomes
• To know and implement the steps of a data science project: import, clean, transform, visualize, and model data as well as communicate results
• To be able to formulate goals and research questions about observational and (quasi-)experimental studies
• To know principles of good scientific practice and learn to document research in a reproducible format
Assessment
Homework 1: An early report describing and documenting a data set to be completed early in the colloquium
Homework 2: A final report documenting a complete analysis of the data to be completed at the end of the colloquium
Literature
Recommended basic literature
Ismay, C., & Kennedy, P.C. (2021-12-30). Getting used to R, RStudio, and R Markdown. https://ismayc.github.io/rbasics-book/
Data Carpentry (2018-2022). R for Social Scientists. https://datacarpentry.org/r-socialsci/
Recommended additional literature
Gelman, A., Hill. J., & Vehtari, A. (2020). Regression and other stories. Boston: Cambridge University Press. https://users.aalto.fi/~ave/ROS.pdf
Ismay, C., & Kim, A.Y. (2020). Statistical Inference via Data Science: A Modern Dive into R and the Tidyverse. https://moderndive.com/index.html#sec:intro-instructors
Wickham, H., & Grolemund, G. (2017). R for Data Science. Boston: O’Reilly. https://r4ds.had.co.nz/
Ismay, C., & Kennedy, P.C. (2021-12-30). Getting used to R, RStudio, and R Markdown.
https://ismayc.github.io/rbasics-book/
Data Carpentry (2018-2022). R for Social Scientists.
https://datacarpentry.org/r-socialsci/
Gelman, A., Hill. J., & Vehtari, A. (2020). Regression and other stories. Boston: Cambridge University Press.
https://users.aalto.fi/~ave/ROS.pdf
Ismay, C., & Kim, A.Y. (2020). Statistical Inference via Data Science: A Modern Dive into R and the Tidyverse.
https://moderndive.com/index.html#sec:intro-instructors
1. Some statistics course -- the more the better.
2. The more experience with statistical software, the better. The ideal background is the combination of R and RStudo, but students with experience in SPSS, SAS, Stata, Julia are also welcome.
The colloquium can be attended for credit. This requires:
1. Homework 1: An early report describing and documenting a data set to be completed early in the colloquium
2. Presentation in the colloquium.
3. Homework 2: A final report documenting a complete analysis of the data to be completed at the end of the colloquium
• To know principles of good scientific practice and learn to document their research in a reproducible format
1. Students from the faculty of human sciences -- all departments.
2. Students are also welcome from other fields dealing with (quasi-)experimental and observational data (e.g., social and biological sciences, economics)
© Copyright HISHochschul-Informations-System eG