Causal Inference and Experiments

About

This course examines lab, survey, and field experimental methods for causal inference. After providing an overview of the essential aspects of experiments, the course focuses primarily on common threats to inference that arise in experimental settings and how to avoid them. Selected topics will include theory testing, treatment design, estimation of heterogeneous treatment effects, convenience sampling and generalizability, preregistration, and ethics. The course will conclude with an applied session in which students design their own experiments, write a pre-registration, and program their experiments in Qualtrics (if applicable). Students will then peer review each other's designs.

Course leader

D. J. Flynn is Assistant Professor of Political Science and faculty affiliate at the Center for the Governance of Change at IE University in Madrid, Spain.

Target group

Participants will find the course useful if they are interested in:
- Designing, implementing, and/or analysing experiments that take place in lab, survey, or field settings
- Becoming more critical consumers of empirical research that purports to demonstrate causality
- Evaluating the effectiveness of policies or programs on important outcomes in politics, public health, economics, or other fields

Prerequisites:
- At least one graduate-level statistics course that covers hypothesis testing and regression

Course aim

By the end of the course participants will:
- Design valid lab, survey, and field experiments to test causal hypotheses
- Be more critical consumers of academic research in a wide range of fields that purports to make causal inferences

Fee info