Quantitative Social Research
With its own professorship at the Institute, Quantitative Social Research is one of the main research areas. The research focuses on the validity of quantitative empirical work – from measurement issues to causal inference –, the logic and practice (and problems) of advanced regression analysis for the social sciences, model uncertainty and robustness testing.
In quantitative empirical work and regression analysis, research is based on a profound understanding of the logic of empirical social science, i.e. the theoretical foundations of empirical research and the empirical foundations of theories as well as knowledge and understanding of valid inferential strategies and appropriate research designs. Projects in this research area discuss critically how scientific theories about socio-economic phenomena can be examined and tested in the most reliable way.
Robustness is the degree to which an estimate using a plausible alternative model specification supports the baseline model’s estimated effect of interest. The uncertainty researchers face in specifying their estimation model threatens the validity of their inferences. In regression analyses of observational data the “true model” remains unknown and researchers face a choice between plausible alternative specifications. Robustness testing allows researchers to explore the stability of their main estimates to plausible variations in model specifications.