Rouven Michels

Periodically stationary distribution (probability that the fly is active) as a function of the time of day. True stationary distribution is compared to biased approximation, and we see a substantial difference.

Our paper on #HMMs with periodically ⏰ varying transition probabilities is published! 🎉 @carlinafeldmann.bsky.social, Sina Mews, @rmichels.bsky.social @rolandlangrock.bsky.social

doi.org/10.1214/25-AOAS2107

We derive the periodically #stationary distribution and the implied dwell-time distribution

We're all looking forward to the #UEFA #WEURO2025 starting on tomorrow! ⚽

Do you want to know what is the likely course of the tournament and who probably wins? 🏆

Read our blog post: 📰

www.zeileis.org/news/weuro2025/

Rechtsextremistisches Personenpotenzial. Grafik von Dobrindt: Liegt bei etwa 50.000

Achse kleiner, dadurch bei Linksextremismus deutlich längere Balken

Sachen gibt's: Wenn man die Skalierung der Achse ändert, ist auf einmal der Balken beim Linksextremismus länger.

Are Liverpool proof coaches don't matter? Or is Slot just better than Klopp? Liverpool were supposed to struggle once Jurgen Klopp left. Instead, Arne Slot won the Premier League. Do coaches just not matter?

I wrote about the defining story of the Premier League season. How Liverpool lost one of the best coaches in the history of the sport -- and immediately got better: www.espn.com/soccer/story...

Dafür muss man sich nicht grämen, es steckt hier einfach noch alles in den Kinderschuhen. Ich weiß nicht, ob es fürs Gefühl hilft, aber ich lese deinen Content sehr gerne hier auf BlueSky.

Hi, for sure, just drop me an Email (Rouven.michels@tu-dortmund.de)!

Diese Realitätsverweigerung bei gleichzeitiger Behauptung, man würde die Realität aber viel besser sehen, ist schon dreist.

MathSport International in Luxembourg in June

I think this is true for all down but especially interesting for 3rd (and 4th) down plays. My gut feeling is that once you notice that pressure is coming, it is more worthy to push the ball downfield and give your receivers a chance (and thus increasing the TO prob) than taking the sack

Extending the Dixon and Coles model: an application to women’s football data Abstract. The prevalent model by Dixon and Coles extends the double Poisson model where two independent Poisson distributions model the number of goals sco

We recently extended the D&C model, leading to more accurate strength parameters in some cases. If you wanna repeat your analysis for women‘s football, it’s worth a look: doi.org/10.1093/jrss...

Great to hear that you are spreading analytics on American Football in Europe as well :-) It‘s a nice conference with really great people. Unfortunately, I cannot attend this year.

In this year‘s NFL Big Data Bowl 🏈 submission, @rmichels.bsky.social, Robert Bajons, and I employ hidden Markov models to uncover 🔎guarding assignments and use this additional information to improve the prediction of defensive strategies. 📊
#bigdatabowl #rstats

Ravens also lost to the Raiders. Bengals choked too many matches, Not only the Pats game

Sané (and Gnabry) at Bayern are perfect examples. Especially Sané excelled on Friday when he was „forced“ to play on the left side.

Just Zac Taylor things…