City Centre Campus

Tampere

The course starts from the key concepts of causality, focuses on the identification and estimation of causal effects, and gives an overview of different areas of causal inference. The topics include:- causality in science, decision making and everyday life- difference of prediction and causal inference, confounders, ladders of causality- graphical framework: structural causal model, directed acyclic graph (DAG), directed acyclic mixed graph (ADMG)- potential outcome framework- d-separation and conditional independence- identifiability of causal effects- do-calculus and ID algorithm- estimation of causal effects: g formula, inverse probability weighting (IPW), Bayesian- causal discovery- counterfactual inference- causal data fusion- graphical missing data models20 hours of teaching consists of lectures and exercises. R is used in examples. The course is completed with an exam.

Open University

There are 20 hours of lectures. The lectures are on campus and cannot be attended remotely. In addition to the lectures, the course includes self-study and an exam.For more information on studying in Open university visit our website <a href="https://www.tuni.fi/en/study-with-us/open-higher-education-studies/open-university" target="_blank" rel="noopener noreferrer">https://www.tuni.fi/en/study-with-us/open-higher-education-studies/open-university</a>.

Faculty of Information Technology and Communication Sciences

English

A student who has completed the courseknows the concept of causality,knows the potential outcome framework and graphical framework for causal inference,can represent causal relations with graphical models,can apply do-calculus and the ID algorithm,can estimate causal effects from observational data,knows the basics of causal discovery and counterfactual inference,knows the basics of causal data fusion and graphical missing data models

basic probability (random variables, conditional independence), basic discrete mathematics (sets and graphs), understanding of statistical modeling (e.g. generalized linear models), basics of algorithms, familiarity with R

<h3>Lectures</h3><h4>Lecture: </h4>09.06.2025 09.00 - 09.06.2025 11.00, TAU Linna 4013 opetustila (50) 10.06.2025 16.00 - 10.06.2025 18.00, TAU Linna 4013 opetustila (50) 11.06.2025 09.00 - 11.06.2025 16.00, TAU Linna 4013 opetustila (50) 12.06.2025 09.00 - 12.06.2025 16.00, TAU Linna 4013 opetustila (50) 13.06.2025 09.00 - 13.06.2025 14.00, TAU Linna 4013 opetustila (50)

TUNI Moodle: DATA.STAT.791-03-2024-2025-1 Causal Inference (Lectures)

Lectures

There are 20 hours of lectures. The lectures are on campus and cannot be attended remotely. In addition to the lectures, the course includes self-study and an exam. The exam will be held as a pen &amp; paper exam in Tampere. If necessary and possible, the exam can be taken at the same time as an electronic EXAM exam on other university campuses or as a supervised paper exam. The course is organised in cooperation with the Finnish Statistical Society and the Finnish Society of Biostatistics. For more information on studying in Open university visit our website <a href="https://www.tuni.fi/en/study-with-us/open-higher-education-studies/open-university" target="_blank" rel="noopener noreferrer">https://www.tuni.fi/en/study-with-us/open-higher-education-studies/open-university</a>.

Contact teaching

Independent studies

<h5>Exam at 13-16, room TAU Virta 109</h5>The exam will be held as a pen &amp; paper exam in Tampere. If necessary and possible, the exam can be taken at the same time as an electronic EXAM exam on other university campuses or as a supervised paper exam. The course is organised in cooperation with the Finnish Statistical Society and the Finnish Society of Biostatistics. <h5>Lectures</h5>There are 20 hours of lectures. The lectures are on campus and cannot be attended remotely. In addition to the lectures, the course includes self-study and an exam. The course is organised in cooperation with the Finnish Statistical Society and the Finnish Society of Biostatistics.

Technology and Natural Sciences

Advanced studies

The course does not directly follow any book but the most of the material can be found from these books:Pearl, J., Glymour, M., &amp; Jewell, N. P. (2016). Causal inference in statistics: a primer. John Wiley &amp; Sons.Pearl, J. (2009). Causality: Models, Reasoning, and Inference (Second ed.). Cambridge University Press.Hernán, M. A &amp; Robins, J.M. (2020). Causal Inference: What If. Boca Raton: Chapman &amp; Hall/CRC. <a href="https://eur04.safelinks.protection.outlook.com/?url&#61;https%3A%2F%2Fmiguelhernan.org%2Fwhatifbook&amp;data&#61;05%7C02%7Csimo.ali-loytty%40tuni.fi%7Cb749e36677d74ff5d57108dd50eb06c8%7Cfa6944afcc7c4cd89154c01132798910%7C0%7C0%7C638755692570394657%7CUnknown%7CTWFpbGZsb3d8eyJFbXB0eU1hcGkiOnRydWUsIlYiOiIwLjAuMDAwMCIsIlAiOiJXaW4zMiIsIkFOIjoiTWFpbCIsIldUIjoyfQ%3D%3D%7C0%7C%7C%7C&amp;sdata&#61;VbFZWWQXu%2BnqlCCoU6Af9fjKHste9pPGYvp48F1PptY%3D&amp;reserved&#61;0" target="_blank" rel="noopener noreferrer">https://miguelhernan.org/whatifbook</a>Peters, J., Janzing, D. &amp; Schölkopf, B. (2017) Elements of Causal Inference. MIT Press.Koller, D., &amp; Friedman, N. (2009). Probabilistic graphical models: principles and techniques. MIT press.

DATA.STAT.791-03 Causal Inference, 5 cr

On this page

Course completion at Open University

Required prior knowledge

Implementations and registration

Course objectives

Learning outcomes

Content

Study materials

More information about studying at the Open University

Terms of payment

Contact us

Give feedback on our website!