Course

This course is structured as a weekly seminar. We will meet every Monday from 14:00-16:00 in E 27.

The seminar is split in three parts:

  1. In the beginning of the semester, we will read some basic papers that give a broad overview of model comparison from different perspectives. You will pick topics that you would like to present and write a report on, form a pair with your colleague, and schedule the date of your presentation.
  2. In the middle of the semester, you will have time to work on your presentation and report.
  3. At the end of the semester you will present your work and hand in your report.
Date Content Attendance1
8.4. Overview of the course, topics Mandatory
15.4. Introduction to Model Comparison, Suggestions of own topic2 Mandatory
22.4. Discussion of Hastie et al. (2009), Submit topic preferences Mandatory
29.4. Discussion of Shmueli (2010), Final assignment to groups and topics Mandatory
6.5. Discussion of Navarro (2019), Schedule presentations3 Mandatory
13.5. Preparing presentations & report, discussion Voluntary
20.5. Whit Monday Free day
27.5. Preparing presentations & report, discussion Voluntary
3.6. Preparing presentations & report, discussion Voluntary
10.6. Presentation day #1 Mandatory
17.6. Presentation day #2 Mandatory
24.6. Presentation day #3 Mandatory
1.7. Presentation day #4 Mandatory
8.7. Presentation day #5 Mandatory
15.7. Course conclusion, Q&A Mandatory
31.7. Deadline - submit report Online4

References

Hastie, T., Tibshirani, R., Friedman, J., Hastie, T., Tibshirani, R., & Friedman, J. (2009). Model assessment and selection. In The elements of statistical learning: data mining, inference, and prediction (pp. 219–259). Springer Series in Statistics. Springer, New York, NY. https://link.springer.com/chapter/10.1007/978-0-387-21606-5_7#preview
Navarro, D. J. (2019). Between the devil and the deep blue sea: Tensions between scientific judgement and statistical model selection. Computational Brain & Behavior, 2(1), 28–34. https://doi.org/10.1007/s42113-018-0019-z
Shmueli, G. (2010). To Explain or to Predict? Statistical Science, 25(3), 289–310. https://doi.org/10.1214/10-STS330

Footnotes

  1. If you cannot attend seminars that are mandatory, please let me know by e-mail beforehand.↩︎

  2. We would like to give you an opportunity to shape the content of the seminar, according to your own interest: If you are interested in a particular model comparison/selection method or a paper related to model selection/comparison/averaging, you can propose to have a presentation about that. Note that you will still need a partner to do the topic with you. We will discuss the suitability of the topic in the next seminar.↩︎

  3. Based on the topics you chose, we will schedule presentations in an (approximate) order of increasing complexity: If you pick a relatively hard topic, you will have more time to prepare your presentation.↩︎

  4. You need to submit your report as a pair, on Moodle, by 31. 7. 23:59 CEST.↩︎