Data Science and Causal Inference

Faculteit Campus Fryslân
Jaar 2021/22
Vakcode CFB048A05
Vaknaam Data Science and Causal Inference
Niveau(s) bachelor
Voertaal Engels
Periode semester II a

Uitgebreide vaknaam Major electives: 300-level: Data Science and Causal Inference
Leerdoelen Upon the successful completion of this course, you will be able to achieve three things:

1. You will be able to discuss a wide range of approaches and methods of causal analysis, acquiring some familiarity with their pros and cons.

2. You will find much of the terminology and jargon that is used in current research more familiar.

3. You will be able to identify weaknesses of empirical research papers, recognize implicit assumptions and implications of causal inferences and you will be able to judge the adequacy of those assumptions and their limitations.
Omschrijving What do the following questions have in common?
• Does foreign aid to developing countries improve human rights in those countries?
• Are AI algorithms racially biased?
• How does having more daughters influence the voting behaviour of parents?

All these questions share several features: first, they are all causal in nature. Second, it would not be practical to answer them accurately, using experimental, randomized control trials. Third, they can all be addressed using modern methods of causal inference in the data sciences.

Recent years have seen the emergence of new methods that probe into causal inference, at the intersection of three traditional academic disciplines: in the computer sciences, Judea Pearl won the Alan Turing prize in 2011 for his fundamental contributions to artificial intelligence through the development of a Bayesian probabilistic framework for causal reasoning. In the social and economic sciences, Joshua Angrist and Guido Imbens were awarded the 2021 Nobel Award for their methodological contributions to the analysis of causal relationships, insights that have spread to other fields and "revolutionised" empirical research. In the philosophy of sciences, Nancy Cartwright and James Woodward (among others) have grounded these empirical frameworks within a critical epistemology, prompting the rise of interventionist theories of causation in philosophy. With its roots in artificial intelligence, economics, social sciences and philosophy, this course is interdisciplinary through and through.

The course will involve a fair amount of coding and require numeric literacy, but the required level is fairly basic, building on the skills you have developed in introduction to programming and your statistics courses.
Uren per week
Onderwijsvorm Lab sessions, seminar, zelfstudie
(Assignments could be prepared in R, Python, Julia or any other relevant statistics programming technology)
(Lab reports + Preparation readings and videos + Quizzes)
Vaksoort bachelor
Coördinator O. Engel, PhD.
Docent(en) O. Engel, PhD.
Entreevoorwaarden Statistics 2 (distributions, multiple linear regression, interactions and dummy variables)
Topics in data science (recommended)
A working knowledge of R/RStudio
Opmerkingen Consider brushing up on your R/RStudio before the course begins. Please mail the course coordinator for ideas on how to do this most effectively.
Opgenomen in
Opleiding Jaar Periode Type
BSc Global Responsibility & Leadership  (Optional Electives) - semester II a Data Science
BSc Global Responsibility & Leadership 3 semester II a keuzegroep