University of Technology Sydney

23716 Principles of Causal Inference

Warning: The information on this page is indicative. The subject outline for a particular session, location and mode of offering is the authoritative source of all information about the subject for that offering. Required texts, recommended texts and references in particular are likely to change. Students will be provided with a subject outline once they enrol in the subject.

Subject handbook information prior to 2024 is available in the Archives.

UTS: Business: Economics
Credit points: 3 cp
Result type: Grade and marks

There are course requisites for this subject. See access conditions.

Description

This subject equips students with the key principles of causal inference as used in economics and econometrics. The subject helps students understand what causality is and how to study the causal effect of a variable on another one. The subject starts by explaining why the concept of experiment is central to empirical research in science. It then presents to the student the alternative “quasi-experimental” approaches which have been developed in economics to study causal relationships using observational data. Such an understanding is of critical importance to graduates who work with data in the industry.

Subject learning objectives (SLOs)

Upon successful completion of this subject students should be able to:
1. Analyse empirical problems, recognising the difference between correlation and causation
2. Explain the wide range of confounding mechanisms which can hide behind the co-evolution of two variables
3. Evaluate the relevance and importance of using different statistical techniques with observational data to make causal inferences

Contribution to the development of graduate attributes

This subject equips students with the key principles of causal inference as used in economics and economics. The subject will help the students understand the abstract notion of causality and how to study the causal effect of a variable on another one in a wide range of applications. The subject will start by explaining why the concept of experiment is central to empirical research in science. It will then present to the student the alternative “quasi-experimental” approaches which have been developed in economics to study causal relationships using observational data. Such an understanding is of critical importance to graduates who will work with data in the industry.

This subject contributes to developing the following graduate attribute(s):

  • Intellectual rigour and innovative problem solving
  • Professional and technical competence

Teaching and learning strategies

This subject is taught through a blend of online resources, self-directed study and seminars.
It will use the potential of online tools to teach this technical content in an interactive, practical and intuitive way. Online tools will, in particular, be used to allow students to interact with data in a way which helps them to experience some of the notions presented in the lectures. Subject content will be presented to students in a variety of formats (lecture slides, notes, videos, articles) and delivered both online and in-class. At the beginning of the unit, students are expected to review materials and complete tasks on their own before attending a weekly Zoom review session with the lecturer. Materials will be provided to students on the UTS Learning Management System but students are also expected to seek information independently.
At the end of the unit, seminars offer face to face interaction to review the material and engage students with the material. Seminars are highly interactive. Students will learn about the concepts and methods of causal inferences and apply these to investigate empirical questions, either individually or in small groups. Students will receive individual feedback in-class from the lecturer.

Content (topics)

  • The notion of causality
  • Correlation is not causation: confounding effects
  • The experimental method
  • Quasi-experimental approaches for observational data

Assessment

Assessment task 1: Quiz (online)*

Objective(s):

This addresses subject learning objective(s):

1 and 2

Groupwork: Individual
Weight: 35%
Length:

30 mins

Criteria:
  • Accurate knowledge

*Note: Late submission of the assessment task will not be marked and awarded a mark of zero.

Assessment task 2: Report on Observational Data Analysis

Objective(s):

This addresses subject learning objective(s):

1, 2 and 3

Groupwork: Individual
Weight: 65%
Length:

Maximum of 2,500 words. For readability please use 12 point type, with 1.5 spacing.

Criteria:
  • Clarity of expression
  • Rigour of analysis

Minimum requirements

Students must achieve at least 50% of the subject’s total marks.

Required texts

None

Recommended texts

Pearl, J. & Mackenzie, D. (2019) The New Science of Cause and Effect, Penguin.

Cunningham, S. (2021) Causal Inference: The Mixtape, https://mixtape.scunning.com