Universität Wien

040971 UK Computational Statistics (2023S)

4.00 ECTS (2.00 SWS), SPL 4 - Wirtschaftswissenschaften
Continuous assessment of course work
MIXED
Moodle

Registration/Deregistration

Note: The time of your registration within the registration period has no effect on the allocation of places (no first come, first served).

Details

max. 65 participants
Language: German, English

Lecturers

Classes (iCal) - next class is marked with N

We will examine modern statistical methods for data analysis, including their algorithmic aspects and theoretical properties. The course is hands-on and methods are applied using the Python programming language.

This lecture requires rudimentary programming knowledge, such as the ones taught in "UK Statistical Programming", but can theoretically also be completed without previous knowledge.
Before the start of the lecture, it is advisable to familiarize yourself with "Google colab", which will be used in the lecture, or to install Python on your own computer. For this we recommend the package manager Anaconda or Miniconda.

We also reccomend the lecture: Grundlagen von Python of the STV Statistics, which is however not needed for the course "computational statistics",
but provides further insight in certain areas of Python.

  • Monday 06.03. 11:30 - 13:00 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Monday 06.03. 15:00 - 16:30 Seminarraum 5, Kolingasse 14-16, EG00
  • Monday 20.03. 11:30 - 13:00 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Monday 20.03. 15:00 - 16:30 Seminarraum 15, Kolingasse 14-16, OG01
  • Monday 27.03. 09:45 - 11:15 Hörsaal 12 Oskar-Morgenstern-Platz 1 2.Stock
  • Monday 27.03. 11:30 - 13:00 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Monday 17.04. 11:30 - 13:00 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Monday 17.04. 15:00 - 16:30 Seminarraum 15, Kolingasse 14-16, OG01
  • Monday 24.04. 11:30 - 13:00 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Monday 24.04. 15:00 - 16:30 Seminarraum 15, Kolingasse 14-16, OG01
  • Monday 08.05. 11:30 - 13:00 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Monday 08.05. 15:00 - 16:30 Seminarraum 15, Kolingasse 14-16, OG01
  • Monday 15.05. 11:30 - 13:00 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Monday 15.05. 15:00 - 16:30 Seminarraum 15, Kolingasse 14-16, OG01
  • Monday 22.05. 11:30 - 13:00 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Monday 22.05. 15:00 - 16:30 Seminarraum 15, Kolingasse 14-16, OG01
  • Monday 05.06. 11:30 - 13:00 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Monday 05.06. 15:00 - 16:30 Seminarraum 15, Kolingasse 14-16, OG01
  • Monday 12.06. 11:30 - 13:00 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Monday 12.06. 15:00 - 16:30 Seminarraum 15, Kolingasse 14-16, OG01
  • Monday 19.06. 11:30 - 13:00 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Monday 19.06. 15:00 - 16:30 Seminarraum 15, Kolingasse 14-16, OG01
  • Monday 26.06. 11:30 - 13:00 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Monday 26.06. 15:00 - 16:30 Seminarraum 15, Kolingasse 14-16, OG01

Information

Aims, contents and method of the course

Objectives:

In this course, students will
- get with Python
- Use Python for data visualization and analysis
- Draft detailed problem reports
- understand the underlying methods
- learn fundamental concepts in statistical computing

Content:

1. Crash course in Python
2. Linear regression, kNN, Cross validation
3. Hypotheses Tests
4. Confidence intervals and bias-variance tradeoff
5. Simulation
6. Model selection

Assessment and permitted materials

Weekly practice sessions and a final project.
The grade consists of two parts:
1.) 65% from the number of exercises done and their evaluation.
2.) 35% project.
Exact details of the project will be announced during the lecture.
Every week from the second week on, depending on the number of participants, approximately 5 exercises will be given to the participants on a weekly basis. The solutions to those exercises will be presented by the participants during the exercises classes.
The exercises should be marked on Moodle as done before(!) the start of the respective exercise unit and will be checked by the relevant lecturer.
In order to pass the course, at least 50% of the exercises must be solved and positively graded.
The solved and positively graded exercises are graded by the following scheme:
100% - 90%: 1
89%-80%: 2
79% - 70%: 3
69% - 50%: 4
49% - 0%: 5(fail)

If it is not clear that a participant independently solved an exercise, the lecturer is free to deduct points for that.

Minimum requirements and assessment criteria

50 % of exercises done and positively graded as well as a positive grade on the final project.

Examination topics

Contents of the topics covered.

Reading list

Gareth, James, et al. An introduction to statistical learning: with applications in R. Spinger, 2013.

Association in the course directory

Last modified: Th 23.03.2023 14:27