Causal InferenceModule description #41042 / Version 2
- 6 CP
- Written exam
- Graded
- Winter semester
- English
This module description is not valid in the current semester (Winter semester 2026/27).
| Module / Version | #41042 / #2 |
|---|---|
| Validity | Summer semester 2023 – Summer semester 2024 |
| Available language(s) | German |
| Credit points | 6 |
| Person responsible for the module | Runge, Jakob Gerhard Bernhard |
| Grading | Graded |
| Exam format | Written exam |
| Language(s) of instruction | English |
Affiliation
| Faculty | Fakultät IV |
|---|---|
| Institute | Institut für Softwaretechnik und Theoretische Informatik |
| Academic chair | 34349202 FG Klimainformatik |
Contact
| Office | EN 15 |
|---|---|
| Contact person | Runge, Jakob Gerhard Bernhard |
| E-mail address | runge@tu-berlin.de |
| Website | https://climateinformaticslab.com/ |
Learning outcomes
"Correlation is not causation" - according to this mantra, data-based inference of causality seems to evade scientific treatment. But in recent decades, modern causality theory, founded by computer scientists such as Judea Pearl and philosophers such as Peter Spirtes and Clark Glymour, has become more mainstream. This theory puts the description of causal relationships on a mathematical footing and establishes the conditions under which causal dependencies can be estimated from observational data. The module aims at an understanding of the mathematical causality concepts as well as the statistical estimation problem and will illustrate the methods with application examples, especially on time series.
Content
Basic concepts of causality according to Pearl and Spirtes are introduced and the associated mathematical apparatus is developed. Learning algorithms are discussed based on the concept of graphical models and conditional independence. An important part is the practical estimation problem for learning causal graphs and statistical methods for estimating conditional independence. Since time series data occur in many applied sciences, particular emphasis will be placed on challenges that are characteristic of time series. The module is concluded by exemplary applications of causal inference methods on climate time series.
Module components
Compulsory area
The following courses are mandatory for this module:
| Courses | Type | Number | Frequency | Language | Hours per week | Course catalog |
|---|---|---|---|---|---|---|
| Kausale Inferenz | Lecture | Winter semester | [en, de] | 2 | ISIS |
Workload and credit points
Kausale Inferenz (Lecture)
| Workload description | Multiplier | Hours | Total |
|---|---|---|---|
| Attendance | 15 | 2 h | 30 h |
| Pre/post processing | 15 | 4 h | 60 h |
| 90 h | |||
Course-independent workload
| Workload description | Multiplier | Hours | Total |
|---|---|---|---|
| Blockvorlesung Kausale Inferenz | 15 | 2 h | 30 h |
| Vor-/Nachbearbeitung | 15 | 4 h | 60 h |
| 90 h | |||
The workload of the module adds up to 180 hours. The module therefore comprises 6 credit points.
Description of teaching and learning methods
The block lecture consists of 15 lectures divided into several blocks. The dates are set at the beginning of the semester. The performance evaluation is done via an written examination. This is subject to change, depending on the number of participants.
Requirements for participation and examination
Desirable prerequisites for participation in the courses:
Mathematical basics, especially probability theory and statistics. Programming knowledge in Python.
Mandatory requirements for the module examination registration:
This module has no examination requirements.
Completion of the module
| Grading | Graded |
|---|---|
| Exam format | Written exam |
| Language | English |
| Duration/Extent | 90 min |
Duration of the module
The following number of semesters is estimated for taking and completing the module: 1 semester(s).
This module can be started in the following semesters: Winter semester.
Maximum number of participants
The maximum capacity of participants is 45.
Registration procedures
Three weeks before the end of the semester students must register for the examination.
Recommended reading, lecture notes
Lecture notes
unavailable
Electronic lecture notes
unavailable
Recommended literature
- Pearl, J. Causality: Models, reasoning, and inference. Cambridge University Press, 2009
- Spirtes, P., Glymour, C., and Scheines, R., Causation, Prediction, and Search (MIT Press, Boston, 2000)
Assigned programs
This module is not used in any program.
Miscellaneous
Zuordnung Studiengebiete (Master): - Grundlagen der Informatik - Data and Software Engineering - Kognitive Systeme