Introductory description

Social scientists constantly make or evaluate arguments about institutions, public policies, laws and individual behaviours. Such arguments depend on underlying facts. “Democratic institutions lead to economic development”. Gun control reduces crime.” “Raising the minimum wage increases unemployment.” “Politicians benefit financially from office”. “Social media increase political polarization’.
How do we know whether these claims are true? In addition to sound theoretical arguments,
rigours empirical analysis is a powerful way to get at such facts. This module offers an accessible introduction to the topic of causal inference in quantitative analysis and its practice. The module strives to minimize technical notation by providing a largely nontechnical overview of the newest methods for causal inference along with practical guidelines for designing and implementing research projects aimed at establishing causal relationships. These techniques are not only used by national governments and international organizations to set and track targets, but they are increasingly applied by managers in the private sector to determine budget allocations and guide decisions.

Module aims

Outline syllabus

This is an indicative module outline only to give an indication of the sort of topics that may be covered. Actual sessions held may differ.

1. Cause-and-effect questions and Counterfactuals
2. Impact Evaluation for Policy Decisions
3. Randomized Experiments
4. Instrumental Variables
5. Regression Discontinuity Design
6. (Reading Week)
7. Difference-in-Differences Method
8. Matching
9. Determining Which Method to Use for a Given Question
10. How to Produce a Policy Research Report

Learning outcomes

By the end of the module, students should be able to:

• - Assess the quality of published research with the aim of showing how the process of knowledge creation through research does or does not lead to clear conclusions regarding causal effects
• - Critically evaluate how research is presented in the public domain (e.g., media) to be a better consumer of reported findings
• - Learn the five basic empirical techniques - random assignment, regression, instrumental variables, regression discontinuity, and differences-in-differences – using Stata
• - Conduct meaningful and creative empirical work that investigates causal relationships

Indicative reading list

Gertler, Paul J., Sebastian Martinez, Patrick Premand, Laura B. Rawlings, and Christel MJ Vermeersch. (2016). Impact evaluation in practice. Second Edition. The World Bank. Available online: https://openknowledge.worldbank.org/handle/10986/25030

Angrist, Joshua D., and Jörn-Steffen Pischke. Mastering'metrics: The path from cause to effect. Princeton University Press, 2014.

Research element

Evaluation of existing research with respect to causal inference.

International

Examples from across Political Science / International Relations will be used.

Subject specific skills

Have an increased understanding of the technical and theoretical/conceptual dimensions of causal inference in quantitative data analysis

Develop substantial competency in the cutting-edge statistical techniques to study cause-and-effect relationships

Understand the value and practical experience of applying statistical methods for causal inference and learn
both their merits and limitations

Present and interpret the results of quantitative statistical analyses appropriately when the aim is establishing causal relations

Transferable skills

Understand the impact of the ways in which quantitative data are generated, manipulated and analysed on the validity and usefulness of research findings.

Manipulate and analyse existing data and present the results of these analyses appropriately using statistical software

Produce original empirical research and develop skills in written communication.

Interpret and critique published quantitative research more accurately