UV9255 Causal modelling in non-experimental data
Course content
CEMO organizes a three-day workshop on causal modeling in non-experimental data.
This course combines lectures and hands-on exercises, and builds up knowledge and skills in using advanced econometric modelling techniques.
Outline:
Day 1: Conceptual issues (Nov 25, 2015)
- Introduction to the concept of causality
- Using logic to infer causality/DAGs
- Causal inferences in regression and SEM models
- Data considerations
Day 2: Propensity scores and fixed-effects (Nov 26, 2015)
- Introduction to propensity score matching and weighting
- Practical sessions
- Introduction to fixed-effects models
- Practical sessions
Day 3: Regression discontinuity and instrumental variables (Nov 27, 2015)
- Introduction to regression discontinuity
- Practical sessions
- Introduction to instrumental variables
- Practical sessions
Literature:
- Primary source: Willett, R.J. & Murnane, R.J.(2011). Methods Matter. Improving Causal Inference in Educational and Social Science Research. New York: Oxford UP.
- Supplementary literature: Angrist, J.D. & Pischke, J-S. (2014). Mastering ‘Metrics: The Path from Cause to Effect. Princeton, NJ.: Priceton UP.
An additional compendium or articles will be provided.
Learning outcome
The three-day workshop provides a conceptual and analytical introduction to causal inference in non-experimental data.
Admission
Ph.d.-students at The Faculty of Education will be given priority, but it is also possible for other Ph.d.-students to apply.
Ph.d.-students from the University of Oslo apply through Studentweb. Other apply though Nettskjema.
Registration deadline: 9 Nov 2015
Teaching
Dates: 25, 26, 27 Nov 2015
Location: tba
Time: 09.00-16.00 all days
Course leaders: Henrik Daae Zachrisson and Jan-Eric Gustafsson
Examination
To obtain 1 study point 80% attendance in the lectures is required.
To obtain 3 study points a short paper needs to be submitted after the
course.
Grading scale:
Grades are awarded on a pass/fail scale. Read more about the grading system.