folded Normals

While having breakfast (after an early morn swim at the vintage La Butte aux Cailles pool, which let me in free!), I noticed a letter to the Editor in the Annals of Applied Statistics, which I was unaware existed. (The concept, not this specific letter!) The point of the letter was to indicate that finding the MLE for the mean and variance of a folded normal distribution was feasible without resorting to the EM algorithm. Since the folded normal distribution is a special case of mixture (with fixed weights), using EM is indeed quite natural, but the author, Iain MacDonald, remarked that an optimiser such as R nlm() could be called instead. The few lines of relevant R code were even included. While this is a correct if minor remark, I am a wee bit surprised at seeing it included in the journal, the more because the authors of the original paper using the EM approach were given the opportunity to respond, noticing EM is much faster than nlm in the cases they tested, and Iain MacDonald had a further rejoinder! The more because the Wikipedia page mentioned the use of optimisers much earlier (and pointed out at the R package Rfast as producing MLEs for the distribution).

foundations of algorithmic fairness

Just forwarding the announcement of an online workshop on algorithmic fairness, on 12 and 16 March (great idea to separate the two afternoons, GT-wise afternoons). It is organised by Paris, Genoa and Saarbrücken ELLIS units, and, although a member of the Paris unit, I am not involved in this event. (The speakers are pictured above.)

no haggis for Burns night!

it was the best of times, it was the worst of times

“old” vs. “new” sports

The Paris 2024 Olympics Committee has removed the 50km men race walk competition from the program, towards a mixed competition, possibly another walk. The argument is bringing more parity to the game (even though 50km women race walks are taking place, as seen above at the 2019 World championship, which was run under hugely inappropriate temperatures) while reducing the number of athletes. While I do realise this is not a very popular sport, I remain impressed by the athletes (who manage to walk over 20km  almost faster than I ran my best ½ marathon times!). Other new mixed competitions will include skeet shooting, two extreme canoe slalom events, three mixed events in sailing, and a new women’s weight class in boxing will replace a men’s class. (In my opinion, boxing should be banned altogether, given its demonstrated and devastating impact on athletes’ brains.) Other new sports include skateboarding, sport climbing (bouldering+lead climbing being separate from speed climbing) and surfing as well as break-dancing, grouped as “youth-focused events”, the last item creating a wee bit of controversy for being one of many forms of athletic dancing, and furthermore proving hard to judge in an objective way, while barring sports like squash from entering the list. Given that the list of Olympic sports is finite (and shrinking) there will obviously be more losers than winners, with some incomprehensibly over-represented disciplines (like, e.g., 18 wrestling competitions!), but it is somewhat annoying to see a rise in spectator sports that are more enjoyable to watch but harder to rank. (Although I do not particularly care for the Olympics and hope to stay away from Paris at the time! Like, attending JSM 2021 in Portland, Oregon.)