Module Directory

This postgraduate module introduces students to the principles of causal inference, with applications in economics, data science, and policy evaluation.

The module examines how randomised experiments and natural experiments can be used to identify causal effects. Students will learn how to formulate causal questions, assess identification assumptions, interpret empirical evidence, and distinguish credible causal claims from correlational findings.

Students will apply these ideas by designing and evaluating an experimental or quasi-experimental research strategy.

The aim of this module is:

• To introduce students to the principles of causal inference and policy evaluation, with a focus on randomised experiments and natural experiments, and to develop their ability to design, assess, and communicate credible empirical strategies for causal analysis

By the end of this module, students will be expected to be able to:

1. Recall and apply ideas concerning randomised experiments and natural experiments.


2. Demonstrate knowledge of the foundations of causal inference and counterfactual reasoning in empirical research.


3. Demonstrate understanding of key concepts used in experimental and quasi-experimental research, including treatment effects, identification, randomisation, confounding, and external validity.


4. Critically evaluate the strengths and weaknesses of randomised experiments and natural experiments in economics, policy evaluation, and data science, including the plausibility of the identification assumptions.


5. Design an experimental or quasi-experimental research strategy to answer an applied causal or policy-evaluation question.


6. Interpret and communicate empirical findings from causal studies, including their limitations and policy relevance.


7. Critically evaluate the research design of others and of their own work.

Understanding causal relationships is central to modern economic research, policy evaluation, and data science. Governments, firms, and researchers increasingly rely on empirical methods to assess the effects of policies, programmes, and interventions.

This module provides an introduction to causal inference through randomised experiments and natural experiments. It covers the logic of causal identification, the design and interpretation of randomised controlled trials and A/B testing, and the use of quasi-experimental methods such as difference-in-differences and regression discontinuity designs. Students will engage with applications in economics and public policy and develop the ability to judge whether an empirical strategy supports a credible causal claim.

This module will be delivered via:

• One 2-hour lecture per week.
• One 1-hour class per week in the Economics department.