Fake Banner
The Problem With Peer Review

In a world where misinformation, voluntary or accidental, reigns supreme; in a world where lies...

Interna

In the past few years my activities on this site - but I would say more in general, as the same...

The Probability Density Function: A Known Unknown

Perhaps the most important thing to get right from the start, in most statistical problems, is...

Summer Lectures In AI

Winter is not over yet, but I am already busy fixing the details of some conferences, schools,...

User picture.
picture for Hank Campbellpicture for Heidi Hendersonpicture for Bente Lilja Byepicture for Sascha Vongehrpicture for Patrick Lockerbypicture for Johannes Koelman
Tommaso DorigoRSS Feed of this column.

Tommaso Dorigo is an experimental particle physicist, who works for the INFN at the University of Padova, and collaborates with the CMS and the SWGO experiments. He is the president of the Read More »

Blogroll
"[...] Given the fact that the nil hypothesis is always false, the rate of Type-I errors is 0%, not 5%, and [...] only Type-II errors can be made, which run typically at about 50% [...] [T]ypically, the sample effect size necessary for significance is notably larger than the actual population effect size and [...] the average of the statistically significant effects is much larger than the actual effect size. The result is that people who do focus on effect sizes end up with a substantial positive bias in their effect size estimation.
UPDATE: BBC radio contacted me to let me know they corrected their mistake. I am very glad to hear that! So you can continue reading BBC after all!

Probability inversion is one of the nastiest mistakes one can do handling the results of a statistical analysis, invalidating to the roots the interpretation of the data to the point that the whole work effectively becomes useless. Unfortunately, it is a very common entertainment for journalists reporting scientific results, and oftentimes scientists themselves fall in the trap.
Maybe more interesting than the just reported result of searches for the Higgs boson into four-lepton final states (ee, eμ, μμ) are the result presented by CMS and ATLAS on the searches for the Higgs decay into tau-lepton pairs. The reason for the interest comes from the fact that last July the rather high rates of Higgs decays to photon pairs had suggested to some that this new particle might have reduced couplings to fermions, and could thus be a non-Standard Model particle after all.
Today new results of Higgs searches have first been shown in Kyoto, at the Hadron Collider Physics conference. Let us see the CMS and ATLAS updates of their measurements in the ZZ-> 4 leptons final state, which constitutes the best signal-to-noise channel to study Higgs properties cleanly and measure mass and spin-parity of the new found particle.
The Hadron Collider Physics symposium opened yesterday in Kyoto. I am not following the works very closely, but I did give a peek at today's talks, which were on the topic of top quark physics.
It has taken a while, but the rare decay of B_s mesons (particles composed of a bottom and an anti-strange quark) to muon pairs has finally been seen. The authors of the find -we cannot yet call it an observation given the scarce statistical significance of the signal- are the members of the LHCb collaboration, one of the four experiments working with the proton-proton collisions delivered by the Large Hadron Collider at CERN.