Causal Inference and Statistical Designs (Part III, Michaelmas 2026)
About the course
How does the way we collect data determine what we can learn from it? We will examine this question through connecting a statistical analysis to the design and assumptions that justify it.
Lecturer: Qingyuan Zhao · Term: Michaelmas 2026 · Part III, examinable, 16 lectures.
- Time: Monday and Wednesday, 11:00.
- Room: MR14.
- Prerequisites: good understanding of undergraduate probability and statistics; familiarity with asymptotic and applied statistics is helpful.
- Three example sheets and three associated example classes, plus an Easter revision class.
- Example sheets will be posted in due course.
Lecture notes
Read the lecture notes · CC BY 4.0. The collection currently contains Lecture 1; further chapters will be added as they are released.
These notes were automatically generated by AI and lightly reviewed by the lecturer. They may still contain mistakes and factual errors.
Lecture slides
Course discussion on Zulip
Open the course Zulip. Sign in to the course Zulip (invitation link will be sent through Moodle).
- announcements: course updates.
- course-discussion: ask peers and the lecturer for questions/corrections. Start one descriptive topic per question, for example “Lecture 1: potential outcomes”. Keep follow-ups in that topic; start a new topic for a different question.
- Optional AI help in ai-sandbox: mention @Teaching Assistant explicitly, including for follow-ups. The bot may use relevant messages in that topic as context. Its answers can contain mistakes. AI use and participation are optional.
For inline maths, type $$Y_i(1)-Y_i(0)$$. For display maths, type:
```math
Y_i = Y_i(Z_i)
```