Course finder

<< return to browsing

Semester 1

Causal Inference for Social Sciences (PLIT10168)

Subject

Politics

College

CAHSS

Credits

20

Normal Year Taken

3

Delivery Session Year

2023/2024

Pre-requisites

Visiting students must have completed 4 Politics courses at grade B or above, and at least one course that covers basic statistical analysis including regression. We will only consider University/College level courses, and we cannot consider interdisciplinary courses or courses without sufficient Politics/Government/International Relations focus. **Please see Additional Restrictions below**.

Course Summary

The goal of empirical research in social sciences is to reduce the complexity in order to isolate cause and effect. But what exactly is causation and how can it be determined whether an observed relationship is truly causal? This course will provide an overview of the main classes of modelling approaches to causal inference and statistical methods for working with these models using experimental and observational data.

Course Description

The world has changed in transformative ways. Data and evidence are everywhere. Quantitative evidence shapes everything from health care to local politics to dating to sports to global security. Critical thinking with data is more important than ever. At the core of the issue is the problem of inferring causality from data. How do we assess whether an observed relationship in data is causal? A common mindset is that causal inference is only possible using randomized experiments, but developments in statistical analysis and related fields have shown that this view is oversimplified and restrictive. We now have a much richer set of tools that enable causal inference from observational data. We will analyze the strengths and weaknesses of these methods, and throughout the course, we will illustrate the methods with applications drawn from various subjects, including elections, crime, terrorism, health care and sports. The goal of this course is to provide students with adequate methodological skills for conducting causal empirical research in their own fields of substantive interest. **The structure of the course will mix lectures, discussions, and computer work. Students will learn these methods through practical applications with data and coding. That being said, this is not a computing course. The practical sessions will be held using R, but STATA codes for the same task will also be provided before the sessions. Students are free to choose which software to use. **Topics may include: 1- Introduction and Potential Outcomes Model; 2- Correlation and Causation; 3- Randomized Experiments; 4- Controlling for Confounders; 5- Instrumental Variables; 6- Differences-in-differences; 7- Regression Discontinuity Designs; 8- The Limits of Quantitative Reasoning.

Assessment Information

Written Exam 0%, Coursework 100%, Practical Exam 0%

Additional Restrictions

Unless you are nominated on a Politics exchange agreement, visiting students are only permitted to enrol in one Politics course each, per semester, before the start of the relevant semester’s welcome period – and spaces on each course are limited so cannot be guaranteed for any student. Enrolment in a second Politics course will depend on whether there are still spaces available in the September Welcome Period, and cannot be guaranteed. It is NOT appropriate for students to contact staff within this subject area to ask for an exception to be made; all enquiries to enrol in these courses must be made through the CAHSS Visiting Student Office. This is due to the limited number of spaces available in this very popular subject area.

view the timetable and further details for this course