GESIS Leibniz Institute for the Social Sciences: Go to homepage

GESIS Spring Seminar 2023

Cutting-Edge Methods

February 27 - March 17, 2023, On-site in Cologne

The GESIS Spring Seminar (formerly ZA Spring Seminar) offers three consecutive one-week courses in advanced methods of quantitative data analysis for Social Scientists. It has been taking place in Cologne annually every spring since 1972. The Spring Seminar 2023 provided in depth knowledge of cutting-edge methods in the social sciences. It enabled participants to apply state of the art techniques to their own research projects and provided participants with the opportunity to discuss their own research with interested colleagues and foremost experts.

27 Feb - 03 March, 2023


Daniel Seddig

Eldad Davidov 

Peter Schmidt

Yannick Diehl

Short Course Description:

Determining whether people in certain countries, or at different time points score differently in measurements of interest, or whether constructs relate differently to each other across nations can indisputably assist in testing social sciences theories and advancing our knowledge. However, meaningful comparisons require equivalent measurements of these constructs. This is especially true for subjective attributes such as values, attitudes, perceptions, or opinions. In this course, we first discuss the meaning of cross-group measurement equivalence, look at possible sources of nonequivalence, and suggest ways to prevent it. Next, we examine the social science methodological literature for ways to empirically test for full or partial measurement equivalence using multiple group confirmatory factor analysis (MGCFA). In addition, we discuss how to test equivalence of regression coefficients and/or latent means and variances using MGCFA and multiple group structural equation modeling (MGSEM). We present such tests using the software environment R (e.g., lavaan). Furthermore, we consider what may be done when exact and partial equivalence is not supported by the data. We discuss strategies based on the less strict assumption of approximate equivalence, such as alignment optimization and the Bayesian estimation procedure. These methods offer exciting directions and solutions for future research in cross-group measurement equivalence assessment when exact equivalence is not supported by the data. Finally, we will address the analysis of categorical data. During the exercises, participants will have the opportunity to conduct these tests using data on human values from the European Social Survey, and if time allows data on biodiversity and intentions to behave in an environmentally friendly way with a reasoned action approach. We also encourage participants to bring their own data and apply the methods discussed in the course to their data.

06 - 10 March, 2023


Johannes Giesecke 

Ben Jann 

Short Course Description:

Is the difference in wages between men and women (the gender wage gap) due to less labor market experience of women compared to men, or is it due to discrimination against women, for example because labor market experience of women is valued less than labor market experience of men? How much of the gender wage gap can be "explained" by differences in endowments such as education, skill, or experience? How much do changes in educational attainment and general trends in earnings inequality contribute to the change in the wage gap over time? How would test scores of pupils with and without migration background compare if there would be no differences in average socio-economic status? How much did de-unionization and the decline in real minimum wages contribute to rising wage inequality? How high would the mortality rate in country A be if it had the demographic composition of country B?

Decomposition methods can help finding answers to such and other questions by providing insights into the mechanics of group differentials (such as earnings differences between men and women). Based on methodological developments mostly in labor economics (and some parallel developments in demography), these methods are increasingly popular in various fields of the social sciences. The seminar introduces the statistical concepts of decomposition methods, provides an overview of various approaches, and makes students familiar with the application of the methods and the interpretation of their results. Theoretical inputs and practical exercises (using Stata) will be alternated throughout the course.

13 - 17 March, 2023


Daniel Oberski 

Short Course Description:

Latent class analysis is the name social scientists originally gave to the study of “mixtures of Bernoulli models” – the search for hidden groups in categorical data. Since then, the term has grown to mean almost any kind of model in which there are thought to be different groups, and the problem is that we do not know which groups. Examples are “latent profile analysis”, “Gaussian Mixture Modeling”, “mixture structural equation modeling”, “model-based clustering”, Hidden Markov modeling, and many many more. Latent class(-type) models have found application in market segmentation, ideal point modeling in political science, diagnostic test evaluation without a gold standard, probabilistic record linkage, disease stratification, image recognition, and student mastery models (CDM), to name just a few.