About the Course
S Exploratory data analysis using the European Social Survey (ESS). Reproducable research, automation and visualization (AMS, Teil I / II)
Hypothesis driven theory testing is the textbook example of data analysis in the social sciences. In the absence of any hypotheses, however, social scientists often face the challenge of getting a general overview of complex data sets. Additionally, it is equally important to communicate the essence of the data to others comprehensibly and -- first and foremost -- fast.
In this seminar students are taught to analyze larger data sets automatedly and reproducably, and to export the results into nice documents, such as Word-, HTML- or PDF-files. Mostly, we are going to work with RStudio. At the end of the semester students are asked to produce a short automated report on a research question of their own choice using the skills acquired in the seminar.
1. Introduction into the usage of R and RStudio
- Smart setup
- Workflow
2. Reading and manipulating data
- Basic packages and functions
- Application example: European Social Survey (ESS)
3. Analyzing and visualizing data
- How to handle variable types and scales
- Descriptive statistics and, if applicable, inductive statistics Output: Presenting results and visualization techniques4. Automation
4. Presenting results via (R)Markdown and knitr
- Vectorization and loops
- Parameterization within R Markdown
Voraussetzungen für Studiennachweise / Modulprüfungen
Module exams and study records can be obtained by working on exercises and writing a short seminar paper (~10 pages).