GESIS Leibniz Institute for the Social Sciences: Go to homepage

Key Topics

GESIS Training offers courses on all aspects of empirical social research. Our focus is on Data Analysis, Survey Methodology, Computational Social Science, and Research Data Management.

Should you be unsure which course is the right one for you, please do not hesitate to contact us. We are happy to assist you!

Data Analysis

In the key topic of Data Analysis, we offer courses that teach the theoretical foundations and practical application of various data analysis methods. The underlying data sources here range from surveys to experimental studies to digital trace data obtained, for example, from social media (Computational Social Science). Many of the data used in our courses and relevant for scientific analyses can be found in the GESIS data archive. At GESIS Training, we offer courses for beginners in data analysis methods who have no or very little prior knowledge, as well as for advanced users with prior experience in this area. The majority of the courses in this area are related to quantitative data, but you will also find courses with a qualitative focus.

If you have not worked much with quantitative data so far, we recommend that you first attend an introductory course in univariate and bivariate statistics, inferential statistics, as well as an introductory course in a statistics software such as Stata or R. Introductory courses in linear or logistic regression are also well suited for beginners.

Depending on your research question, you can then attend courses on, for example, structural equation modeling, panel data analysis, or causal analysis.

An overview of all courses that are currently offered on Data Analysis can be found here.

Survey Methodology

In the empirical social sciences, surveys are of the traditional and most frequently used methods of data collection. In the key area of Survey Methodology, we offer courses that deal with conducting surveys and their quality. In the Total Survey Error (TSE) framework, the numerous sources of error are assigned to the areas of measurement and representation: Measurement errors can result, for example, from poor questionnaire design or undesirable respondent behavior. Representation errors result, among other things, from sampling errors, selective sample dropouts, or inadequate sample adjustments. You can learn how to avoid such errors in our courses.

Do you not yet have any experience with conducting surveys? Then we recommend that you first attend an introduction to survey design and a course on questionnaire development. Afterwards, you can choose from a variety of different courses on specific topics, depending on your concrete research question.

The Summer School in Survey Methodology offers you the possibility to combine a larger number of courses.

An overview of all courses that are currently offered on Survey Methodology can be found here​​​​​​​.

Computational Social Science

The still-young field of Computational Social Science studies the same sociocultural phenomena as all social sciences. It is characterized by the use of new types of data ("Digitial Trace Data"), large amounts of data ("Big Data"), and computationally intensive technologies. Computational Social Science thus lies at the intersection of the social sciences and computer science. Our course offerings include courses that address the collection of new types of data, as well as analysis procedures that either relate to these data sources or analyze traditional data sources using new computational techniques. Examples of collecting new data sources include web scraping, social media data collection via APIs, or sensor data. Computational analysis techniques include network analysis, affective computing, machine learning, and other methods that use artificial intelligence.

A good foundation for taking advanced courses is an introduction to Python. Web scraping and social media data collection using APIs also tend to have a low entry barrier. These courses prepare well for success in an advanced course in the field, such as network analysis.

Computational Social Sciences have their own format at GESIS Training, the Fall Seminar in Computational Social Science, in which participants can advance from beginner to advanced user of Computational Social Sciences in three consecutive weeks.

An overview of all courses that are currently offered on Computational Social Sciences can be found here.

Research Data Management

Research data management (RDM) is a key aspect in complying with the rules of good scientific practice as well as in implementing funding requirements in the context of Open Data, according to the FAIR-Data-Principles. FDM contains all measures and strategies for planning, collecting, processing, archiving and long-term preservation of data, as well as access to and re-use of data, standards for data documentation and legal issues relating to secure data handling. To support researchers and data managers in conducting good RDM, GESIS offers a series of courses on the various topics of (research) data management. The courses cover different aspects of RDM, enabling participants to independently address data management issues. Our RDM courses cover topics such as:

  • introduction to (research) data management in the social sciences
  • data protection regulations, informed consent, and secure data handling
  • data cleaning, data documentation and metadata
  • data organization and storage
  • data sharing and re-use, following the FAIR-Data-Principles
  • long-term preservation of research data and materials

An overview of all courses that are currently offered on Research Data Management can be found here.