Dear all,

This is the zoom link for the CWI Machine Learning Seminar tomorrow afternoon:

https://cwi-nl.zoom.us/j/83113639352?pwd=U2NtVC9kWmJkY3NOOGdTMUVSVHorUT09 [Meeting ID: 831 1363 9352    Passcode: 551343]

Speaker:  Johanna Ziegel (University of Bern) Title:    Valid sequential inference on probability forecast performance Date:     Friday 10 September, 14:00 Location: CWI L016 and on Zoom (link above)

This seminar will be held live at reduced capacity, and will be live-streamed on zoom for remote attendance.

Please find the abstract below.

Hope to see you then.

Best wishes,

Wouter

Details:

https://portals.project.cwi.nl/ml-reading-group/events/valid-sequential-infe...

============

Valid sequential inference on probability forecast performance

Johanna Ziegel (University of Bern)

Probability forecasts for binary events play a central role in many applications. Their quality is commonly assessed with proper scoring rules, which assign forecasts a numerical score such that a correct forecast achieves a minimal expected score. In this paper, we construct e-values for testing the statistical significance of score differences of competing forecasts in sequential settings. E-values have been proposed as an alternative to p-values for hypothesis testing, and they can easily be transformed into conservative p-values by taking the multiplicative inverse. The e-values proposed in this article are valid in finite samples without any assumptions on the data generating processes. They also allow optional stopping, so a forecast user may decide to interrupt evaluation taking into account the available data at any time and still draw statistically valid inference, which is generally not true for classical p-value based tests. In a case study on postprocessing of precipitation forecasts, state-of-the-art forecasts dominance tests and e-values lead to the same conclusions.