Social science methodology currently goes through a period of rapid change. Since the turn of the century, social scientist replaced the dominant concept of causality, tipped the fragile balance between inductive and deductive research in favour of inductive designs, and abandoned statistical significance as dominant inferential criteria.

‘Quantitative and Qualitative Methods’ provides a critical introduction to modern social science methodology. The course consists of the following main building blocks:

- The Logic of Social Science

- The Nature of Causality

- Qualitative Research Designs: From an Inductive Logic to Comparative Case Designs

- Model Uncertainty and the Logic of Regression

- Research Design for Causal Inference

On completion of the course, participants will have an overview of modern social science methodology and understand the strengths and weaknesses of each approach. The course is appropriate for students that have a basic understanding of research methodology and regression analysis.

Covered Topics

1. The Purposes of Science

2. Towards a Bayesian Philosophy of Science

3. Causality Then and Now

4. The Scientific Method

5. Causal Inference

- internal and external validity

- statistical inference

- counterfactuals

- robustness

6. Error Processes

7. OLS

8. Limited Dependent Variable Models

9. Count Models

10. Predictions

11. The Lost Case

12. Case-oriented Qualitative Research Designs

13. The Importance of Case Selection

14. The Comparative Method

15. Process-Tracing The Case-Based Method

16. Cases and Variables: The False Promise of QCA

17. Bringing the Case Back in: Quantitative Research

18. Panel-Data Analysis

19. Event Onset

20. Duration and Survival Models

21. Spatial Dependence

22. Conclusion

Participants will acquire the skills needed to

competently apply advanced research methods needed to appropriately analyze data;

interpret and present the results of different contemporary research methods. 

The course relies on varies leaning techniques including inter alia lectures, classroom discussion, student presentations, and lab sessions.

Assessment is based on 

- exam (50 percent)

- participation (25 percent)

- assignments (25 percent)

Participants should be familiar with regression modelling and statistical inference. The purpose of the course is not to cover explain estimators and statistical theory, but to dig deeper into applied empirical research.

- introductory statistics

- statistical software (Stata, R,...)

- stochastics